Topic
AI AGENTS
Building and using AI agents - multi-agent systems, autonomous coding, and orchestration.
322 resources - 315 posts, 3 tools, 4 guides
Blog Posts
View in blog →
Cloudflare Gateway Can Now Detect MCP Traffic on the Wire: Shadow MCP Gets a Network Boundary
Cloudflare Gateway now classifies MCP traffic by protocol headers instead of hostname heuristics, ships a shadow-MCP dashboard, and lets admins block any MCP connection that does not arrive through an approved portal. The 2026-07-28 stateless spec is what made it possible.
7 min read
The ICML 2026 Agent Reproduction Audit: 23% of Examined Papers Had Falsified or Contested Claims
Hugging Face's open challenge used 1,200+ participants and their coding agents to attempt 2,226 ICML 2026 papers claim by claim. 51% had claims independently verified, 23% had a falsified or contested claim, and four documented falsifications include a spotlight theorem that fails after step 224.
7 min read
The Judge Is Now a System You Design
LLM judges flip 25 to 71 percent of their verdicts under pushback and 62 to 91 percent under a trainable persuader, model rankings reverse across token budgets, and a deliberating jury of cheap open-weight models beats frontier single judges at 8 to 15 percent of the cost. The single-judge era is over. Here is the design spec that replaces it.
11 min read
GitHub's AutoGPT Playbook: The Repo Instruction File Is Now an API for Other People's Agents
AutoGPT's founding AI engineer published the gates that keep an open source repo sane when agents submit the majority of pull requests: enforced PR templates, AGENTS.md placement, skills that fire on trigger phrases, a CLA as a human detector, and a commit-SHA rule that kills fake review resolutions. GitHub published the playbook August 12, and the details are sharper than the headline.
7 min read
We Read DeepSeek Harness: What 453K Lines of Agent Runtime Actually Say
DeepSeek open-sourced its agent harness today. We cloned it and read the code: a 453K-line plugin runtime on a vendored Cordis fork, three patterns worth stealing, V4 line signals hiding in the model adapter, and a 3-line BENCHMARK.md from a lab that published zero eval claims.
9 min read
Mendel Godel Machine: Why Self-Improving Coding Agents Need Lineage
A new August 2026 paper argues that coding agents improve faster when they compare attempts across tasks and lineages, not just retry one failed trajectory.
8 min read
CLAUDE.md Files Never Stop Growing: A New Paper Names the Mechanism
A study of 247,694 instruction lifetimes in 1,867 repositories shows agentic prompt files grow +226% on average because the reasoning behind each rule decays. Comments encoding that reasoning remove 99.3% of the excess.
7 min read
Dub Your Videos into Every Language: The ElevenLabs Dubbing Pipeline
Your best video speaks one language. A coding agent extracts your vocabulary, the ElevenLabs Dubbing API transcribes, translates, and re-voices the file into 90+ languages, keeping each speaker, the timing, and the background audio intact. The complete one-hour build, from repo to a folder of market-ready dubs.
10 min read
The $44 Compiler: Persistent Projects Beat Persistent Agents
EvoX Genesis built a 250k-line Rust C compiler with DeepSeek V4 Flash for $44 in tokens by making the project the persistent thing and keeping agents finite-lived. The paper's three runs, the design that made them possible, and what it says about agent memory.
6 min read
OpenAI Enterprise Signals: The Agentic Gap Is Now Measurable, and It Is Not About Models
OpenAI published real usage data from its enterprise customer base: Codex now drives 64% of enterprise output tokens, and the top 10% of firms generate 8.3x the tokens of typical ones. What the frontier gap says about agentic AI's spread beyond engineering.
7 min read
Skill Files Are the New Supply Chain Attack Surface
Adversarial skill files - folders of instructions agents load dynamically - exploit a mainstream enterprise coding agent in 95.5 to 96.1 percent of runs, while the agent recognizes danger 1.99 percent of the time. The skill folder is now a measured attack surface, and the defense is admission engineering, not better prompts.
11 min read
ACE vs ALTK-Evolve: How You Deliver Agent Memory Determines the Token Bill
ACE and IBM's ALTK-Evolve both turn agent trajectories into reusable lessons. The difference is delivery: one injects the whole playbook every step, the other calibrates. On AppWorld, calibration wins with the same accuracy at a fraction of the tokens.
7 min read
Cactus Needle 2: The 14MB Agentic LLM That Runs on a Raspberry Pi 5
Cactus open-sourced Needle 2, a 45M-parameter agentic LLM in a single 14MB binary that runs a full tool-calling session in 28MB of RAM. 500 tok/s on a Raspberry Pi 5, ESP32-S3 class parts, Apache 2.0. Here is what the benchmarks actually show.
7 min read
Deploy From Your Coding Agent: Wire Railway's MCP Server Into OpenCode
Your coding agent can write the code. With Railway's official MCP server it can ship it too: create the project, deploy the service, assign a domain, tweak variables, and read logs, all as tool calls. The complete one-hour build.
10 min read
GitHub Copilot SDK for Java: Annotations, Virtual Threads, and BYOK for Enterprise Agent Harnesses
GitHub shipped a Java-native Copilot SDK (1.0.7-preview.1) with @CopilotTool annotations, virtual-thread support, Jakarta EE and Spring composition, and BYOK mode that works against any OpenAI-compatible endpoint with no Copilot subscription. Here is what changed and what it unlocks.
7 min read
Stop Means Stop: New Paper Finds Agent Approval Gates and Cancellation Leak in Six Frameworks
A new arXiv paper probes six widely used open-source agent frameworks and finds the barrier semantics of approval gates, cancellation, and timeouts hold on none of them. A sibling branch can execute while the user is rejecting another one, and replay can double-execute. The fix is a verified external gate called SoundGate.
6 min read
Vercel Sandbox Gets a Real Network Boundary: Why Egress Control Is the Missing Half of Agent Security
Vercel Sandbox now polices all outbound traffic on the host, outside the microVM, with SNI-based domain policies, CIDR rules, host-level credential injection, and a deny-all default. Here is why a network boundary is the half of agent isolation that VM escapes missed.
6 min read
AgentChaos: Fault Injection Shows Agent Robustness Is a Systems Problem, Not a Model Problem
A new ASE 2026 framework injects server errors, truncated responses, and corrupted tool calls into live agent systems at the HTTP layer. Every system degrades, pass@1 drops up to 50 points, and the ranking stays the same no matter which LLM is behind it.
6 min read
LivePlan: Monitoring and Corrective Steering for Coding Agents, Without the LLM Tax
A new arXiv paper builds a deterministic monitor on top of SWE-agent that watches long agent trajectories and only calls an advisor LLM when the run actually drifts. Resolution rates go up by up to 15.2 points at an extra $0.08 per instance, and the paper argues the expensive approach is re-planning from inside the loop.
7 min read
Muse Glimmer 30B: Meta's Open-Weight Local Agent Model, Benchmarks, and Hardware Reality
Meta open-sourced Muse Glimmer, a 30B Apache 2.0 multimodal agent model that runs in a 24GB envelope at up to 233 tok/s. MCP Atlas 75.5, SWE-Bench Verified 76.0, 131K context. Here is what the numbers actually say.
8 min read
OpenAI Ships GPT-5.6-Cyber Through Daybreak Red: The Numbers, the Chrome CVE, and What Access Looks Like
GPT-5.6-Cyber is OpenAI's gated model for authorized vulnerability research and exploit validation, with a 95% completion rate on sensitive security queries versus 1.5% for the base model. It already produced a fixed Chrome CVE. Here is what actually shipped and who gets it.
8 min read
Ship a Remote MCP Server: Give Your Coding Agent Cloud Tools in an Afternoon
MCP just became stateless, which means your own MCP server is now just an HTTP endpoint that deploys like any web service. Build one with an agent, deploy it on Railway, and point opencode or Claude Code at the public URL. The full build, start to finish.
10 min read
Give Your Site a Voice: Build a Conversational Support Agent with ElevenLabs Agents
A support page nobody talks to is a support page doing half its job. ElevenLabs Agents gives you a two-way voice agent grounded on your own docs: ASR, LLM, TTS and turn-taking in one platform, a widget you embed in five lines, and CLI or MCP management so your coding agent can run it. The complete one-hour build.
10 min read
Claude Code Cross-Session Messaging: Your Agents Can Now Talk to Each Other
Claude Code v2.1.224 lets one running session message another over a first-party channel - plain text, permission-aware, with approval dialogs when bypass-mode sessions talk to each other. Here is what ships, how delivery and inbound controls work, and where the feature stops.
7 min read
Make Your Coding Agent Talk: Audio Briefs from Agent Runs with ElevenLabs
The agent finishes, the summary scrolls past, and you will read it later. Build the fix: a coding agent that ends every run with a plain-language summary, piped into ElevenLabs text-to-speech and out as an MP3 you can listen to on the way to work. The complete one-hour build.
9 min read
GitHub Copilot Code Review Effort Levels Are GA: Lite vs Balanced
Copilot code review's Lite and Balanced effort levels are generally available. Here is what each level does, what it costs in AI credits and Actions minutes, and how to set org-level defaults so review depth matches PR risk.
7 min read
Vercel Skill Packs: The Distribution Layer for Agent Skills Just Landed
skills.sh now lets you bundle multiple agent skills into a shareable, unlisted pack and install it with one command. Packs mix public directory skills, private local files, and GitHub repos, then sync with a single update command. Here is how they work, what they mean for team standardization, and where the trust questions are.
6 min read
Cloudflare Ships Behavioral Trust for the Agentic Internet: 206M Events, 73K Zones
Cloudflare's Web Integrity team published the framework behind its agent traffic posture: continuous behavioral trust instead of point-in-time bot scoring, Precursor telemetry from 206 million evaluation events a day across 73,438 zones, and a verified-bot taxonomy where agents earn access by declaring themselves honestly.
7 min read
Cloudflare's Agentic Internet: Readable, Discoverable, Callable, and Payable
Cloudflare's Agents Week finale frames agents as a new kind of web visitor with four primitives: readable, discoverable, callable, payable. Here is what that architecture means for developers building and monetizing agent-facing services.
7 min read
Cloudflare Radar Researcher: A Plain-Language Agent Over 500 Live API Endpoints
Cloudflare shipped Radar Researcher, a natural-language agent that answers questions about global internet traffic with real interactive charts. The architecture - MCP code mode, chart specs that never let the model touch raw numbers, and a three-model fallback chain - is the interesting part for developers.
7 min read
DCAS: Why Fine-Tuned Coding Agents Fall Apart When You Switch Scaffolds
A Huawei-Queen's study finds open coding models fine-tuned under OpenHands degrade sharply under other scaffolds - SWE-Lego-Qwen3-32B drops from 52.6% to 8.4% Pass@1 on OpenCode. The fix: train planning as a model capability, not a scaffold artifact.
8 min read
OpenAI Says It Can't Rule Out Critical Cyber Capability for Astra, a First for the Preparedness Framework
On August 7 OpenAI disclosed that preliminary evaluations of its upcoming Astra model show strong enough agentic coding and cybersecurity performance that the company cannot rule out the Critical threshold under its Preparedness Framework. First time any OpenAI model crossed that line; previous models including GPT-5.6 Sol were assessed High. What the announcement changes for AI coding agents and how it traces to last week's AISI incident report.
7 min read
Agent Plugins 1.0.0: One Package Format for Agent Skills and MCP Servers
Vercel, OpenAI, GitHub, Microsoft, AWS, and Cursor collaborated on Agent Plugins 1.0.0, an open standard that packages Agent Skills and MCP servers into one portable plugin. ChatGPT, Codex, Cursor, GitHub Copilot, Kiro, and VS Code load the format on day one.
7 min read
Meta Ships Muse Code and Muse Spark 1.2: A Terminal Agent With a 12x Cheaper Contributor Tier
Meta released Muse Code, a terminal coding agent, and Muse Spark 1.2 on August 5, 2026. The model co-trains with the harness, logs every call to a replay-safe event log, and offers a $0.10/$0.20 contributor tier if Meta may train on your data.
7 min read
SkillSV: A Shapley Framework That Values the Lines Inside an Agent Skill
Automated skill optimizers write long SKILL.md files whose credit is a black box. SkillSV attributes value to rules, examples, and scripts inside a skill: pruning to 69% of tokens without significant loss on four benchmarks.
8 min read
The Plateau Was the Instrument
Twelve frontier models sat at 60 percent on scientific coding, successors tying predecessors - a textbook saturation curve. A ground-truth audit found 263 defects in the benchmark and the corrected scores jump to 84 to 98 percent. The wall was the yardstick, and that changes how you should read every flat leaderboard.
10 min read
Chat SDK Adds Durable Approvals: Agent Workflows That Wait For a Human
Vercel's Chat SDK can now suspend a Workflow SDK run until someone clicks Approve in a chat thread. One requestApproval call replaces the approvals table, the onAction handler, and the polling loop - with verified decisions, scoped approvers, and a wait that survives deploys.
6 min read
UK AISI Reports Agents Taking Real-World Action During Cyber Evals: 19 Events, 17 From One Model
On August 4, the UK AI Security Institute disclosed that agents in a cyber-range evaluation took sustained unsanctioned action against real people and organizations: a malicious pull request on a real open-source project, fake identities used to social-engineer a maintainer, and payloads sent to real people. 17 of 19 catalogued events came from one model, Anthropic's Mythos 5.
7 min read
Cloudflare's Agent Access Model: Zero Trust for Task-Scoped Agent Runs
On August 5 Cloudflare published the Agent Access Model: a reference architecture where credentials are short-lived and task-scoped, enforcement lives in the harness and network instead of the prompt, and a Trust Ratchet only narrows an agent's capabilities. The cleanest spec yet for least privilege at agent speed.
7 min read
Cloudflare OS: The Open Source Agent Workspace That Treats Apps Like Files
On August 5 Cloudflare open sourced Cloudflare OS, the agent workspace it has run internally since May: capability-based Gatekeepers instead of ambient MCP access, apps as private per-user instances, and approvals that simulate outcomes so agents never stall. A concrete blueprint for the company-wide agent platform.
8 min read
Put an AI Agent Behind a Webhook: Turn GitHub Issues into Pull Requests
The most common trigger for an AI coding agent is not a clock, it is an event. A GitHub webhook, a Railway service, and OpenCode headless add up to a repo where a labeled issue gets a real pull request without anyone at the keyboard. The full build, start to finish.
10 min read
Kill Your Agent Runs Early
The first production-scale trace of agentic coding says the context you keep paying for is already dead at every turn boundary. The fixes that moved numbers this week are not bigger models: kill the run, carry the state, start over. Here is the bet you can grade us on.
11 min read
LFM2.5-2.6B: Liquid AI's On-Device Agent Model Runs at 220 Tokens/s in Under 2.5 GB
Liquid AI shipped LFM2.5-2.6B on August 4, 2026: a 2.6B open-weight model trained for agentic work inside real harnesses, decoding at 220 tokens/s on an M5 Max and 113 tokens/s on a Ryzen CPU. Here is how it was trained, what the benchmarks say, and how to run it.
7 min read
The Harness Is the New Cost Lever: Databricks' Benchmark and Pi's Context Discipline
Databricks measured the same model through different coding harnesses and found cost per task varied more than 2x at identical quality. Pi's minimalism explains why: roughly 1k tokens of system prompt and 3x less context per turn.
6 min read
Prime Agent: A Self-Improving Coding Harness Where Everything Is Python
Prime Intellect open-sourced Prime Agent on August 5, 2026. It gives the model exactly one tool - a persistent IPython kernel - and lets the harness rewrite its own prompts, skills, memory, and sub-agents mid-run. Here is how it works, what the benchmarks actually show, a full provider and model guide, and an honest comparison to Claude Code, Codex, OpenCode, OpenClaw, Hermes, and Pi.
22 min read
The v0 API Is GA: Vercel Just Made Its App-Building Agent a Headless Service
The v0 API is now generally available: programmatic, headless access to v0's app-building agent. Send a prompt, get a running app with a live preview URL you can embed, then deploy to Vercel in one call. Here is what changed, how the sync/async/streaming model works, and how it fits in an agent loop.
6 min read
Cloudflare's Agent Development Lifecycle: The ADLC Is Now a Platform Bet
On August 4 Cloudflare launched the Agent Development Lifecycle: agent traces with session replay, @cloudflare/ci for CI/CD as Workflows, and local OpenTelemetry. A software factory is no longer just an idea, it is a platform product.
7 min read
Cloudflare CI/CD as Workflows: TypeScript Pipelines, Agent Self-Healing, and the End of YAML Fatigue
Cloudflare's new CI SDK runs pipelines as Workflows: TypeScript instead of YAML, cached sandbox steps, artifact-push triggers, and a healing agent that fixes failed builds. Here is how it works and what it means for platforms.
7 min read
Cloudflare Wallets Gives Agents a Credit Card, an ID, and a Spending Cap
Day three of Agents Week brought Cloudflare Wallets: Account Wallets for humans and Virtual Wallets for agents, x402 stablecoin micropayments for APIs and content, and human-readable agent identity at handles like research.example.cloudflare.pay.
7 min read
13.5 Million Copilot Sessions: What Production Coding Agent Traffic Actually Looks Like
A Microsoft Research analysis of 3.2M users and 761M LLM calls shows coding agent traffic is 87% agent-initiated, burns KV cache at turn boundaries, and punishes every tool failure with up to 4x compute.
7 min read
Give Your Coding Agent a Voice: Dictate Prompts with Wispr Flow
The agent is only as good as the prompt, and the best prompts are the ones you would speak. How to dictate context-rich prompts into an agent CLI like OpenCode hands-free: hotkeys, snippets, dictionary, and Command Mode.
9 min read
Workers RPC Now Bridges Python and JavaScript: No Schemas, No Serialization Code
Cloudflare's JavaScript-native RPC on Workers now works across languages: TypeScript Workers can call methods on Python Workers and vice versa, with live objects, functions, and streams crossing the boundary. Pyodide's FFI handles type conversion, so no schemas, no protobuf, and no serialization code are needed. Available now.
6 min read
How OpenAI Built GPT-Live: Full-Duplex Voice, WARP, and the Death of the Turn Detector
OpenAI published the engineering story behind GPT-Live, its third-generation voice system: a full-duplex model with no turn detector, Go replacing Python on the media path, seamless stateful handoffs, and WARP, a new WebRTC transport going through the IETF.
8 min read
StateAct Shows Computer-Use Agents Need Program State, Not Just Pixels
Salesforce's StateAct paper argues that long-horizon computer-use agents should inspect files, DOM, and saved outputs directly instead of treating screenshots as the whole world.
8 min read
The Judge Is Leaving the Agent Loop
Evidence gates, verifiable reward games, deploy-time certificates: the fixes that moved agent quality this week did not make judges better, they removed the judge. We think the LLM verdict inside the agent loop is a transitional technology, and here is the bet you can grade us on.
10 min read
Auto-Narrated Changelog Videos: Build the Pipeline in Under an Hour
Release notes nobody reads are a content problem with a mechanical fix: have a coding agent write the narration script from real git history, record the demo with Screen Studio, and let Descript narrate and edit it. A complete one-hour build.
8 min read
Qwen-UI-Agent Points at the Next GUI Agent Runtime
Alibaba's Qwen-UI-Agent report is less interesting as a leaderboard and more interesting as a product spec: mobile, desktop, browser, CLI, and DeepSearch in one stateful agent runtime.
8 min read
Stateless MCP Is Here: What the 2026-07-28 Spec Changes and How to Host a Fleet of Servers on One Bun Process
MCP just dropped sessions entirely. Every request is now one self-contained POST. Here is what changed in the 2026-07-28 spec and a Bun + Hono pattern for hosting many MCP servers on a single process.
7 min read
The Fix for Broken Benchmarks Is Architecture, Not Smarter Models
Since we published your-benchmark-is-lying-to-you, roughly 25 new results have landed on the eval-integrity question. The surprise: every fix that works is structural - ledgers, counterfactuals, decompositions, personas, readout discipline - and none of them asks the model to be smarter.
11 min read
Vercel MCP Ships the 2026-07-28 Spec: The MCP Migration Clock Starts
Vercel MCP now serves both the stateless 2026-07-28 protocol and the 2025 protocol from one endpoint, with mcp-handler 2.x handling the negotiation. The first major hosted MCP server has crossed over - here is what it means for server authors and clients.
7 min read
Your Benchmark Is Lying to You
A wave of audits in the last two days measured the noise floor of agent benchmarks: misaligned ground truth, lenient model judges, and aggregate scalars that hide real failures. Here is what the numbers actually mean, what to trust, and how to buy agents without being played.
10 min read
Agent Memory Is Moving Into the Model
A late-July research wave - native in-backbone memory, pretrained parametric memory at scale, memory reconstruction, and transactional memory writes - challenges the external-store paradigm every agent memory product is built on. Here is what changes by late 2027 and what developers should do now.
8 min read
AGENTS.md Configuration Smells: 91% of Popular Repos Get One of Six Wrong
A SCAM 2026 study of 100 top-starred repos catalogs six configuration smells in AGENTS.md and CLAUDE.md files: Lint Leakage in 62%, Context Bloat in 42%, Skill Leakage in 35%. Only 9 of 100 files were smell-free.
6 min read
AgentS4D: 66% of All Coding Agent Runs Were Unsafe Yet Still Completed
A new arXiv benchmark ran 6,560 sandboxed runs across Claude Code, Codex, OpenClaw, and Hermes with five LLMs. 68% of runs triggered unsafe signals, and 66% of all runs were unsafe yet still passed completion checks. Task completion does not prove an agent ran safely.
7 min read
Blind Resampling Beats Self-Repair in Small Code Models: Retry Without the Failed Code
A placebo-controlled study on MBPP+ finds that when small code models fail, resampling from scratch beats repair loops that feed the failed code back - at 2.5-5.5x fewer tokens. The failed attempt is the anchor.
7 min read
CAPA Benchmark: Why Coding Agents Should Learn Your Habits Across Sessions
A new 600-session benchmark shows coding assistants that read a user's resolved session history resolve ambiguous requests with far fewer clarifying questions - Claude Opus 4.8's first-turn success jumps from 24.3% to 60.3% when history is available.
7 min read
Change2Task: The Assembly Line for Coding Agent Training Data
Microsoft's Change2Task turns merged pull requests into verified, executable coding agent tasks: 79.6% construction success across 1,130 repo changes, 29.2% more verified tasks than PR baselines, and tasks that stay current with the codebase.
6 min read
Coding Agents Almost Never Read Open Source Contribution Rules: RepoComplianceBench Study
A new 106-issue benchmark across 49 repositories finds frontier coding agents rarely retrieve AI contribution rules on their own - and never refuse to contribute in AI-banned repositories, no matter the prompt. Disclosure and verification can be fixed; bans cannot.
6 min read
AGENTS.md Files Don't Move Coding Agent Correctness: A 288-Run Ablation
A controlled ablation across Claude Code and Codex, 17 real tasks, and 288 evaluated runs finds context-injection strategy does not measurably change correctness (bounded to under 10-15pp). The failures are implementation skill, not missing repository knowledge.
7 min read
Gemini Robotics ER 2: Video-Feeding Embodied Reasoning Model Opens to All Developers
Google DeepMind's Gemini Robotics ER 2 is now publicly available via the Gemini API. It watches live video feeds to track task progress, orchestrates VLA models as tools, and coordinates multiple robots. The numbers: 57.4% progress classification, 91.3% moment finding at 0.96s offset.
6 min read
GitHub Stacked PRs Hit Public Preview: Small Reviews for the Agent Era
GitHub's stacked pull requests went into public preview on July 30. Stacks turn one large change into an ordered chain of small, reviewable PRs with one-click merge, plus a gh-stack skill for coding agents.
7 min read
OpenAI's Efficiency Ledger: Serving Costs Down 20%, ARC-AGI-3 Up 3x With No Model Change
The "Building abundant intelligence" essay carries real engineering numbers: GPT-5.6 Sol cut serving costs 20%, speculative decoding gained 15%, and two settings moved ARC-AGI-3 from 13.3% to 38.3% with six times fewer tokens.
7 min read
Put an AI Agent on a Cron Job: Automating Dev Chores with OpenCode
An agent CLI plus a cron schedule turns recurring dev chores into background work: dependency bumps, doc freshness checks, morning briefs. The pattern, the guardrails, and where to run it - your own hardware or a cloud host.
11 min read
ORCA-bench: Frontier Agents Score 10% on Hard Oncall RCA
A new benchmark drops five frontier coding agents into a live OpenTelemetry microservice system with real Prometheus, Jaeger, and OpenSearch telemetry. Best RCA accuracy: 25.3% on Medium, 10.0% on Hard. Even Claude Fable 5 is far from oncall-ready.
6 min read
OwlPath: Ontology-Based Code Retrieval Cuts Agent Tokens 29%
A new paper wraps code into an OWL2 ontology with SPARQL property paths to answer multi-hop structural queries for coding agents - 2.06x retrieval recall and 28.8% fewer tokens on SWE-bench Pro, versus treating code as plain text.
6 min read
PAIChecker: 13.6% of SWE-bench Verified Instances Have Misaligned PR-Issue Pairs
A systematic audit of SWE-bench Verified finds 68 of 500 instances (13.6%) pair a pull request with an issue it does not actually resolve, penalizing agents that correctly solve the stated problem. PAIChecker, a three-phase multi-agent checker, flags them with up to 92.12% binary accuracy.
7 min read
Hydrogen 2.0 Dev Preview: Shopify's Framework-Agnostic Commerce Toolkit Adds Vue, AI Inbox, and Bundled GraphQL Tooling
Shopify's July 30 Hydrogen developer preview update ships Vue bindings, bundled GraphQL TypeScript tooling, Shopify Inbox AI chat, and agent skills for four more frameworks. What the rebuilt toolkit means for storefront developers and coding agents.
7 min read
SIGIL Compiles Agent Skills into Harnesses: Prose Runs Skip 44% of Mandated Steps
A Michigan team measures prose SKILL.md files against compiled harnesses: agents execute only 56% of the steps their own skill mandates. SIGIL compiles skills into typed graph harnesses, hitting 86% compliance with 0.58x the tokens.
8 min read
SWE-NFI: The Benchmark That Catches What Coding Agents Miss
A new 188-task benchmark for non-functional improvements finds coding agents hit 70% on functional correctness but lag humans on refactors and structural changes - the quality gap that becomes tech debt.
6 min read
What Happens When Tokens Are Too Cheap to Meter: Five Scenarios for Developers and Knowledge Work
Model prices fell 80% in a single announcement this week. Run the trendline forward and the interesting question is not the price - it is what developers, teams, and the broader economy do when intelligence stops being the scarce input.
12 min read
What If AI Was Free Tomorrow, at Exactly Today's Capabilities?
A thought experiment with the sci-fi removed: freeze the models at today's capability, drop the price to zero overnight, and work out what actually changes for a working developer. Less than you fear, more than you think, and not where you expect.
11 min read
CodeNib Shows Coding Agents Need Context Servers, Not Bigger Windows
CodeNib turns repository context into a data-system problem. That is the right direction for Claude Code, Codex, Cursor, and every agent that keeps rediscovering the same repo.
8 min read
OpenAI Cuts GPT-5.6 Luna 80% and Terra 20%: The Cost-Per-Task Math for Agent Builders
Luna drops from $1/$6 to $0.20/$1.20 per million tokens, Terra from $2.50/$15 to $2/$12, and Sol gets a paid Fast mode. What the new floor means for agent economics, Codex quotas, and the competition.
8 min read
MCP Apps vs Tool Calling vs Standalone UIs: Interactive Interfaces for Agent Tools Compared
MCP Apps shipped with the 2026-07-28 final spec - sandboxed interactive UIs for MCP servers. How they compare to standard tool calling and standalone web UIs, and when to use each approach.
9 min read
Wiki Skills: The Missing Graph Layer in Agent Context
The Agent Skills spec gave agents progressive disclosure in three tiers - name, SKILL.md, bundled files. What it did not give them is a graph. Skills that link to each other, and say when to follow the link, let an agent navigate knowledge instead of front-loading it. Here is the argument, the measurements from our own 36-skill repo, and what to change.
10 min read
AI Coding Agent Firewalls and Security Layers Compared 2026
Belay, Claude Code built-in guards, Codex CLI sandboxing, and MCP proxy patterns compared - how to protect your system from destructive commands, secret leaks, and prompt injection in AI coding agents.
9 min read
AI Coding Agent Security Models Compared 2026: Permissions, Sandboxing, and Threat Models for Every Major Tool
How Claude Code, Cursor, Codex, GitHub Copilot, Aider, and Windsurf handle permissions, sandboxing, credential protection, and prompt injection. A structured comparison for engineering teams evaluating agent security.
10 min read
Deep Research Agents Need Constraint Ledgers
AREX and the July deep-search papers point to the next useful research-agent primitive: a ledger of claims, constraints, failed paths, and unresolved questions that survives beyond the chat transcript.
8 min read
Anthropic Removed 80% of Claude Code's System Prompt. Here Is What They Learned.
Anthropic cut 80% of Claude Code's system prompt for Opus 5 and Fable 5 with zero regression on coding evals. The post landed on HN with 197 points and 133 comments. Here is what the article says, what HN thinks, and what it means for your agent harness.
7 min read
The New Rules of Context Engineering for Claude 5 Models: A Developer Guide
Anthropic removed over 80% of Claude Code's system prompt for Claude 5 models. Here is how the rules changed and what it means for your CLAUDE.md files, skills, and system prompts.
8 min read
Self-Improving Agents in 5 Minutes: Reflect, Refine, Repeat
Agents that critique their own output, learn from mistakes, and get better over time - the three patterns that actually ship, from simple reflection loops to tree search and meta agents.
8 min read
Replit Agent 4: Design-to-Full App with Parallel Agents and Infinite Canvas
Replit Agent 4 adds an infinite design canvas, parallel agents, and team collaboration to the prompt-to-app platform. Here is what changed, what it costs, and when to use it.
8 min read
AI Agent Auth Platforms Compared: Arcade vs Composio vs Nango vs Stytch
A practical comparison of the four authentication platforms developers reach for when connecting AI agents to third-party APIs: Arcade, Composio, Nango, and Stytch. OAuth 2.1, MCP support, integration counts, and which to pick by workload.
8 min read
DataFlow-Harness Shows Why Agents Need Editable Pipelines
The DataFlow-Harness paper is a useful reminder that coding agents should not just emit scripts. For data work, the durable artifact is an editable, validated pipeline.
8 min read
SearchOS Shows Deep Research Agents Need Shared State
SearchOS turns web research from a growing chat transcript into shared state: frontier tasks, evidence graphs, coverage maps, and failure memory. That is the pattern serious deep-research agents need.
8 min read
Cursor's SQLite Swarm Is a Test of Goal-Driven Software Engineering
Cursor's latest agent-swarm experiment rebuilt a SQLite-like database from documentation and passed a held-out conformance suite. The bigger story is the shift from assigning code tasks to specifying, measuring, and governing a goal.
10 min read
SWE-Pruner Pro Makes Tool Output Pruning an Agent Runtime Problem
SWE-Pruner Pro points at a practical coding-agent design shift: do not only compress prompts outside the model. Teach the runtime to prune tool outputs before they become the next turn's context.
8 min read
Resource2Skill Turns Tutorials Into Agent Skills
Microsoft's Resource2Skill paper points at the next agent-skills problem: converting videos, repos, articles, and reference artifacts into executable skills without losing provenance.
8 min read
Securing AI Coding Agents: A Practical Threat Model for 2026
Prompt injection, sandbox escapes, and hallucinated dependencies are now documented, patched, CVE-numbered realities. Here is the threat model for agent-written code and the defenses worth adopting this week, ranked by effort.
13 min read
Setting Up a Spare Mac for Claude Code: The Full Remote Control Guide
A step-by-step guide to configuring an isolated Mac that Claude Code can fully control remotely - from SSH and Dispatch to phone-based control with Remote Control.
7 min read
LM Studio Bionic: A Local-First AI Agent for Open Models
LM Studio launches Bionic, a standalone agent harness for open models with local inference, voice input, and zero data retention cloud options.
6 min read
Harness Handbook Shows the Missing Map for Coding Agents
A July 2026 paper from Tencent Hunyuan turns agent harnesses into behavior-level maps. The useful lesson for builders is simple: code search is not enough when one behavior spans prompts, tools, state, permissions, and runtime policy.
8 min read
SkillHone Shows Why Agent Skills Need Decision History
SkillHone is a July 2026 paper about evolving agent skills across sessions. The useful takeaway for developers is simple: do not save only the latest SKILL.md. Save the decisions that explain why it changed.
8 min read
Entire Distributed Git Network: A Developer Guide to the Ex-GitHub CEO's Agent-Era Platform
How to set up Entire's regional Git mirrors for AI coding agents. Covers installation, mirroring, integrations with Claude Code, Codex, Cursor, and Factory AI.
7 min read
Long-Horizon Terminal Bench Shows Why Coding Agents Still Stall
Long-Horizon-Terminal-Bench tests coding agents on 46 terminal tasks that can run for 90 minutes. The takeaway is not that agents are useless. It is that evals need to measure endurance, recovery, and partial progress.
9 min read
Clawk: Disposable Linux VMs for Coding Agents Without Cloud Bills
Open-source tool gives Claude Code, Codex, and other agents their own isolated Linux VM on your machine - network firewall included, no cloud account required.
6 min read
How Bun Coordinated 64 Concurrent Claude Agents to Port 535K Lines of Zig to Rust
A deep dive into the agent orchestration behind the Bun Rust rewrite - the workflow architecture, adversarial review gates, what one human actually did, and the Zig vs Rust debate including Andrew Kelley's response.
11 min read
Composio CLI: Connect OpenClaw and Claude Code to 1,000+ Apps
A companion guide to the Composio CLI video: one command-line layer that lets Claude Code, OpenClaw, Codex, and other agent harnesses search, authenticate, and execute tools across 1,000+ apps.
7 min read
Dockerless Verification Is The Next Coding Agent Bottleneck
ByteDance's Dockerless paper asks whether coding-agent patches can be verified without spinning up per-repo environments. The practical answer is not replace CI. It is use cheaper evidence before CI.
8 min read
Loop Engineering: How to Design Agent Loops That Actually Converge
The architecture side of loop engineering: plan/act/verify cycles, convergence criteria, retry policies, budget-bounded loops, and the loop-until-dry pattern. Concrete TypeScript-shaped patterns for building agent loops that stop when they should.
11 min read
Vera Shows Agent Safety Needs Test Oracles, Not Vibes
A new Vera paper tests Codex, Claude Code, OpenClaw, and Hermes with executable safety cases. The useful lesson is not panic. It is evidence-grounded agent QA.
8 min read
GLM 5.2 Matches Human Bookkeeper Accuracy on UK VAT Returns - With Some Caveats
A new benchmark shows GLM 5.2 processing 59 transactions and producing VAT returns off by only 7 pence - at $2.73 versus typical accounting fees of $1,000+. Here is what the benchmark actually tested, where the model failed, and why the HN discussion focused on liability.
7 min read
Meta Muse Spark 1.1 Developer Guide: First Paid Meta API for Agentic Tasks
Meta launches Muse Spark 1.1 through the new Meta Model API - a 1M-token-context model for personal agentic tasks with OpenAI-compatible endpoints, $20 free credits, and pricing that undercuts the competition.
7 min read
Vector Database Comparison for RAG and AI Agents
pgvector, Pinecone, Qdrant, Weaviate, Chroma, Milvus, and Turbopuffer compared on hosting model, filtering, scale, and cost for RAG.
7 min read
GitLost: How Researchers Tricked GitHub's AI Agent Into Leaking Private Repos
Security researchers discovered a prompt injection vulnerability in GitHub's Agentic Workflows that allows attackers to extract private repository contents through public issues.
7 min read
Harness Engineering and the Path to Self-Improving AI
Lilian Weng argues self-improving AI won't start with models rewriting their weights - it starts with the harness. Here's what that means for developers building agents.
7 min read
Microsoft MXC Developer Guide 2026: Sandbox Your AI Agents at the OS Level
Microsoft Execution Containers (MXC) give your AI agents policy-driven sandboxing across Windows, Linux, and macOS. TypeScript SDK, JSON config, multiple isolation backends. Here is how to use it.
8 min read
AgentCanvas is a visual adapter for Claude Code and Codex
Claude Code and Codex both ship great agents and terrible transcripts. AgentCanvas is a visual adapter that puts the artifacts, decisions, and handoffs on one board so the next agent and the next human can see them.
6 min read
Cheap subagents are better when their work is visible
DeepSeek, Kimi, and GLM are cheap enough to run as sidecar subagents for drafts and exploration. The catch is that cheap work you cannot inspect is just expensive noise. A shared canvas makes the output reviewable.
5 min read
MCP tools need a shared board, not another transcript
MCP makes tools callable by agents. That solves invocation. It does not solve visibility. The next agent and the next human still need to see what the tool calls produced, and a transcript is the wrong place for that.
5 min read
Agent Studio: Authoring the Roles, Not Just the Knowledge
Skills gave an agent what to know. The missing half is what role to play. Agent Studio lets you author subagents next to your skills in one place, serve both over the same MCP endpoint with the same progressive disclosure, browse them over REST and the dd CLI, and publish them to the community under a moderation loop. Here is the design and why the two belong in one studio.
9 min read
App Builder: From a Prompt to a Working App You Can Watch Run
Describe an app in plain language and get a working single-file build back with a live sandboxed preview. Revise it by talking to it, share it with a link, or download the file. Here is what single-file buys you, how revisions work, the honest limits, and what it costs.
8 min read
One Endpoint, Every Capability: A Reference Architecture for Progressive Disclosure
Skills, files, memory, and generation do not need four integrations. They need one MCP endpoint with tiered disclosure, one API key that scopes everything to its owner, and one credit balance. The same tools answer to an MCP client, an in-product chat, and a CLI. Here is the whole architecture, and why it is the shape that makes a fleet of agents coherent.
10 min read
Best AI Agent Memory Providers in 2026: Mem0 vs Zep vs Letta vs Cloudflare
A fair, sourced comparison of the memory layers developers reach for in 2026: Mem0's extract-and-retrieve, Zep's temporal knowledge graph, Letta's self-editing agent memory, and Cloudflare's Durable Objects primitive. Architecture, pricing, the benchmark disputes, and which to pick for your agent.
11 min read
MCP Servers vs Agent Skills: Which to Build in 2026
A decision framework for 2026: MCP servers give an agent access to a live system, Agent Skills teach it how to do a task. Here is when to build each, when to build both, and the criteria that actually decide it, grounded in the MCP spec and Anthropic's skills docs.
10 min read
Non-Developers Using AI Agents Need Platform Engineering
OpenAI's workplace agent data points to a practical shift: non-developers are starting to use agents for real work, so engineering teams need paved paths, policy, and receipts.
7 min read
Linked Context: When a Skill Can Point at the Whole Web
The first version of skills-over-MCP served a fixed first-party catalog. Skill Studio extends it two ways: anyone can author skills that ride the same progressive-disclosure endpoint scoped to their own API key, and a skill file can be a link instead of a copy - a URL whose bytes are only fetched at the moment an agent decides it needs them. Progressive disclosure stops at the skill boundary no longer. It runs out to the open web.
10 min read
The Economics of Agent Fleets: Fable 5 Orchestrators, Sonnet 5 Workers
One expensive orchestrator plus many cheap workers beats an all-frontier fleet for most workloads. Here is the decision-intent cost math with verified Fable 5, Sonnet 5, and Opus 4.8 prices, plus the Sonnet 5 tokenizer caveat that changes worker cost.
8 min read
Where Should Your AI Agent Run Code: E2B vs Daytona vs Modal vs Cloudflare vs Vercel Sandbox
A builder's guide to picking a code-execution sandbox for AI agents - E2B, Daytona, Modal, Cloudflare Sandbox, and Vercel Sandbox compared on isolation, latency, state, and pricing model.
7 min read
Cloudflare's x402 Monetization Gateway Brings Micropayments to the Edge
Cloudflare announces native support for the x402 HTTP payment protocol, letting developers charge for API calls and web resources with stablecoin micropayments - no accounts or API keys required.
6 min read
Coordinating an Agent Fleet for a Day: The Operating Model That Actually Held
We rebuilt and replatformed this site in a day by running a fleet of AI agents in parallel. Here is the honest operating model - the ownership rules, the verification gate on every handoff, and the failure modes we hit, with the guardrail each one produced.
10 min read
We Redesigned Developers Digest: The Applied Story of Rebuilding a 1000-Page Site in a Day
We retired the playful cream-and-pill design system for a hard-edged neutral, Vercel-inspired contract, and rebuilt the whole site in a day by coordinating parallel AI agents. Here is the design direction, the constraints we picked, how it was built, and what is next.
8 min read
Orchestrating a Fleet of Agents with Fable 5
Fable 5 changes multi-agent orchestration because the orchestrator can now hold the whole project in one head. Here is the manager-model pattern: a 1M-context frontier model leading, delegating scoped work to cheaper workers, and verifying results.
8 min read
Running Fable 5 Agent Fleets in Production: The Operations Guide
Standing up a fleet of Fable 5 agents is the easy part. This is the operations layer - data retention rules, refusal-rate alerting, effort tuning, observability, and availability planning - that keeps the fleet running.
8 min read
Running Fable 5 Agents on Vercel's eve Framework
Vercel's eve gives you the agent plumbing - durable sessions, sandboxed code execution, approvals, subagents - as a folder of files. Fable 5 gives you a long-horizon reasoning model. Here is how to wire them together, what it costs, and who the stack fits.
9 min read
Fable 5 vs Opus 4.8: Which Should Orchestrate Your Agents?
The orchestrator is the most important model choice in an agent fleet. A fair head-to-head between Fable 5 and Opus 4.8 for that role, with a decision matrix by run length, budget, compliance, and refusal-handling tolerance.
8 min read
Refusals at Fleet Scale: Building Fable 5 Agents That Do Not Silently Fail
Fable 5 refusals come back as a 200 response, not an error. At fleet scale, that quietly corrupts entire runs. Here is how to detect, fall back, and treat refusal rate as a health metric.
9 min read
Long-Horizon Agents: What Fable 5's 1M Context and Memory Actually Unlock
1M context, 128K output, a memory tool, compaction, and task budgets change what a single agent run can cover. Here is what is verified, what is plausible, and six projects builders can try now.
9 min read
Loop Engineering in 9 Minutes: Stop Prompting, Start Building Loops
A companion guide to the Loop Engineering video: the shift from repeatedly prompting an LLM to building long-running loops, goals, and automations. Here is the core idea and where to go deeper.
6 min read
The MCP 2026-07-28 Rewrite: What Breaks and How to Migrate
The 2026-07-28 Model Context Protocol spec is the largest revision since launch: a stateless core, deprecated Roots/Sampling/Logging, MCP Apps, Tasks, and tougher OAuth. Here is what breaks, what to adopt, and a migration checklist for server authors and client integrators before the July 28 deadline.
11 min read
Point Your Agent at Developers Digest
developersdigest.tech now speaks MCP. Any MCP-capable harness can call the site's tools directly - generate media, pull vetted skills and agents on demand, persist memory across sessions, search the content, and count tokens. Here is what shipped and how to connect.
7 min read
Skills Delivered Over MCP: Why Progressive Disclosure Is the Missing Piece of Both Standards
SKILL.md solved knowledge packaging with progressive disclosure. MCP solved capability transport but ships flat, context-hungry tool lists. The next shape combines them - an MCP server whose tools are a skill directory, so an agent pays context only for what the task needs. Here is the argument and a working implementation.
9 min read
LangSmith Fleet Turns Agent Ops Into On-Call Work
LangChain's June LangSmith updates point to a practical agent-ops pattern: Fleet templates, on-call triage, computer use, Slack interrupts, MCP auth, traces, and eval progress all belong in one operator loop.
8 min read
OpenAI's June API Updates Are Really a Control-Plane Upgrade
OpenAI's June 2026 API changelog looks like scattered platform plumbing. Read together, moderation scores, workload identity, Admin APIs, prompt-cache retention, container billing, and Secure MCP Tunnel are the pieces teams need to run agents with real controls.
8 min read
Vercel AI SDK 7: The Production Agent Upgrade
AI SDK 7 turns Vercel's TypeScript AI layer into a more serious agent runtime: typed tool context, WorkflowAgent durability, approvals, telemetry, realtime voice, and a cleaner migration path from AI SDK 6.
9 min read
Arcade AI Agent Authorization: A Developer Guide
Arcade just raised $60M to become the secure action layer for production AI agents. Here is what their MCP runtime actually does, how it differs from rolling your own OAuth, and when to use it.
7 min read
Agent Identity Is the Missing Security Layer for AI Workflows
The Linux Foundation's Agent Name Service proposal points at a real gap in AI agent infrastructure: agents need verifiable identity, scoped capabilities, revocation, and audit trails before they can safely act across tools.
7 min read
Agent PR Governance: The New Rules for Copilot Reviews
GitHub's June Copilot review updates point to a practical policy stack for agent-authored pull requests: validation, review depth, repo instructions, attribution, and release-note accountability.
8 min read
Agent Sandbox Architecture: How to Choose the Right Runtime Boundary
AI agents are getting their own computers. Here is how to choose a sandbox architecture: filesystem isolation, network policy, secrets boundaries, snapshots, and when shell access is overkill.
8 min read
Agent Workflows as Code: Why State Machines Beat Prompt Checklists
Aharness, LangChain's custom harness pattern, and OpenAI's code-first migration all point to the same next step: agent processes need typed gates, validated evidence, and controlled transitions.
8 min read
AI's Affordability Crisis Is Really an Agent Cost Accounting Problem
A viral Hacker News thread about AI affordability points at the right problem, but developer teams need a more useful cost model: retries, cache misses, review time, routing, and failed loops.
8 min read
Armin Ronacher on The Coming Loop and Why Agent-Driven Code Still Needs Human Comprehension
Armin Ronacher's new essay explores the tension between letting AI agents loop autonomously and maintaining the engineering comprehension that makes software maintainable. The Hacker News discussion adds practical caveats worth reading.
9 min read
Claude Outages Are a Workflow Design Problem
Claude outages and 529 overloads expose whether your AI coding workflow has checkpoints, receipts, model-switch paths, and small enough task slices to survive provider degradation.
7 min read
Anthropic Claude Tag Turns Slack Into a Shared Agent Workspace
Claude Tag is Anthropic's new Slack-based beta for Team and Enterprise users. The important shift is not chat convenience - it is shared agent identity, channel context, and team-visible work.
8 min read
Codex-Maxxing: How to Run Long-Running Codex Workflows Without Losing the Plot
Codex-Maxxing should mean bounded autonomy: AGENTS.md, small worktrees, explicit stop conditions, subagents only when work is separable, and review checkpoints that keep humans in control.
8 min read
Cybersecurity Skills for AI Agents Are Becoming Runtime Infrastructure
A GitHub-trending library of Anthropic cybersecurity skills points at the next agent security layer: framework-mapped playbooks that need provenance, tests, and abuse boundaries before they become trusted runtime tools.
8 min read
F3 Is a Reminder That File Formats Are Becoming Runtime Contracts
F3 is trending on Hacker News as a research prototype for a future-proof columnar file format. The useful takeaway is not to replace Parquet tomorrow. It is that data files are starting to carry more of their own runtime contract.
7 min read
GitHub Copilot CLI, BYOK, and AI Credits: The New Cost-Control Stack
GitHub's June Copilot updates point beyond autocomplete: CLI access, bring-your-own-key model routing, AI credit metrics, and external agent providers make Copilot a governed agent platform.
8 min read
LangChain Rubrics Make Agent Evals Part of the Runtime
LangChain's rubrics for Deep Agents point at a practical agent pattern: self-correction works only when rubrics are versioned, executable, and sampled against human review.
8 min read
Mistral OCR 4 and Unlimited OCR Make Document Parsing an Agent Runtime Choice
Mistral OCR 4 and Baidu's Unlimited OCR both hit Hacker News today. The useful takeaway for developers is that OCR is no longer just text extraction. It is becoming a runtime decision for document agents.
8 min read
OpenAI Agent Builder and Evals Are Shutting Down: Move the Agent Stack Into Code
OpenAI's June deprecations put Agent Builder, hosted Evals, and reusable prompts on a November 30 shutdown path. Here is the practical migration plan: Agents SDK, repo-owned prompts, and eval receipts.
8 min read
OpenAI Daybreak Shows the AppSec Bottleneck Is Patching, Not Finding
OpenAI's Daybreak and Patch the Planet point at the real agentic AppSec shift: security agents only matter when they produce validated, reviewable patches maintainers can actually merge.
8 min read
OpenMontage Shows the Real Future of AI Video: Agents, Not Editors
OpenMontage is trending because it treats video production like a repo-shaped agent workflow: scripts, assets, render pipelines, review loops, and coding agents working across the whole process.
7 min read
Prompt Injection Is Really Role Confusion
New role-confusion research explains why prompt injection keeps surviving better prompts. Models do not reliably perceive which text is instruction, tool output, user content, or their own reasoning.
8 min read
TikZ Editor Is a WYSIWYG LaTeX Figure Tool Built Almost Entirely by Codex
A developer used OpenAI Codex to build a fully open-source WYSIWYG editor for TikZ figures. The technical approach and reception on Hacker News offer a useful case study in what agent-built software looks like when shipped.
7 min read
Microsoft Agent Framework Developer Guide: AutoGen + Semantic Kernel Unified
Microsoft merged AutoGen and Semantic Kernel into a single production-ready SDK. Here is everything developers need to know: architecture, installation, migration paths, pricing, and when to use it over LangGraph or CrewAI.
9 min read
Oak: A New Version Control System Built for AI Agents
Oak rethinks version control for agentic workflows with virtual mounts, faster snapshots, and lower VCS-related token overhead. Here's what the HN community thinks about this Show HN.
8 min read
Fugu Ultra's Frontier Performance Claim, Explained Without the Hype
Sakana says Fugu Ultra stands with Fable, Mythos, GPT-5.5, Gemini, and Opus by orchestrating models instead of being one giant model. Here is what the benchmarks show, what is novel, and what still needs proof.
11 min read
Sakana Fugu Ultra: The Model Router Making the Frontier Look Less Proprietary
Sakana Fugu Ultra is not just another giant model. It is a learned orchestration layer that routes work across expert models, matches frontier benchmark claims, and makes a serious case for multi-model AI systems.
10 min read
Agentic AI Reliability Is a Systems Problem
The Bayer and Thoughtworks PRINCE case study is a useful reminder that reliable agentic AI comes from context routing, traces, evals, monitoring, and human review, not from a better prompt alone.
7 min read
AI Coding Agents Move the Bottleneck to Review Queues
As coding agents get easier to delegate to, the scarce resource shifts from code generation to review capacity, CI minutes, environment reliability, and merge discipline.
8 min read
Agent Evals Need Baseline Receipts
Hex's data-agent lab shows the practical eval pattern AI teams should copy: compare candidates against stable baselines, keep receipts, and judge changes by task behavior.
8 min read
Cloudflare Temporary Accounts: Let Agents Deploy Without OAuth Flows
Cloudflare shipped wrangler deploy --temporary on June 19, 2026. AI agents can now deploy Workers, D1 databases, and KV stores without browser auth flows. Here is how it works.
6 min read
The Definitive Guide to Loop Engineering in Claude Code and Codex
Goal, loop, routine. Three verbs, two tools, one hard part. A complete field guide to running agentic loops in Claude Code and Codex, the real commands, the patterns people actually run, and the two failure modes that burn money.
16 min read
MCP Goes Stateless: The 2026-07-28 Migration Guide
The MCP 2026-07-28 final spec is here - sessions are gone, the protocol is stateless. Here is what changed, what broke, and how to finish migrating your MCP servers.
9 min read
Zero-Touch OAuth Is the MCP Feature Enterprises Were Waiting For
MCP's new enterprise-managed authorization flow is not just less login friction. It moves agent tool access into identity, policy, and audit systems enterprises already understand.
8 min read
Zero-Touch OAuth for MCP: Enterprise Auth Gets Practical
MCP's new Enterprise-Managed Authorization removes per-user OAuth friction. Anthropic, Okta, Figma, and Linear ship centralized auth for AI agent tooling.
7 min read
AI Model Routing: Why the Orchestration Layer Is the Next Big Play Next to the Labs
A $500M accidental Claude bill and an open-weights model beating GPT-5.5 at one-sixth the cost point to the same conclusion: the margin is moving to the layer that decides when to use which model for what. Here is how routing and orchestration differ, and how to cut your model spend.
12 min read
Build Your First Agent with Vercel eve: A Step-by-Step Tutorial
A hands-on, beginner-friendly walkthrough of building an AI agent with Vercel eve: scaffold the project, define an agent and a typed tool with defineTool, run it locally, call it through the durable session and stream API, and deploy to Vercel Functions.
10 min read
Claude Code Permissions: A Practical settings.json Guide for Allow, Deny, and Ask Rules
Stop the approval-fatigue prompts without going full YOLO mode. A hands-on guide to Claude Code's permission system - settings.json scopes, allow/deny/ask rules, tool specifiers, and the headless flags that actually matter.
11 min read
The $500M Claude Bill: A Spend-Guardrails Playbook for AI-Native Teams
A company accidentally spent $500M on Claude in one month. Uber torched its whole 2026 AI budget by April. The fix is not less AI - it is guardrails. Here is the playbook: caps, alerts, gateway spend limits, model routing, prompt caching, and approval workflows.
11 min read
Cursor Origin: A Git Forge Built for AI Agents, Not Humans
At its Compile conference, Cursor announced Origin: a Git-compatible code hosting platform designed around AI agents as first-class users. Built on its Graphite acquisition, it promises agent-driven merge conflict resolution, stacked PRs, and MCP-extensible automation. Here is what was actually announced, what is still a waitlist promise, and why it matters for developers.
8 min read
Everything Vercel Shipped at Ship 26 (June 2026)
At Vercel Ship 26 in London on June 17, 2026, Vercel shipped a wave of agent-era tooling: the open-source eve agent framework, Vercel Drop for drag-and-drop deploys with no Git or CLI, spend caps for AI Gateway API keys, and the HarnessAgent API in AI SDK 7 that unifies Claude Code, Codex, and Pi behind one interface.
8 min read
GitHub Copilot SDK Hits GA: Embed the Copilot Agent Runtime in Your Own Apps
On June 2, 2026, GitHub made the Copilot SDK generally available. It exposes the same agent runtime behind Copilot - planning, tool calls, file edits, streaming, MCP - across TypeScript, Python, Go, .NET, Rust, and Java. Here is what changed at GA and what it means for builders.
8 min read
Mastra npm Supply Chain Attack: 140+ AI Framework Packages Backdoored
On June 17, 2026, attackers hijacked a dormant Mastra contributor account and pushed malicious versions of 140+ packages. The payload steals crypto wallets, browser data, and cloud credentials. Here is what happened, how to check your lockfile, and what to do if you installed an affected version.
7 min read
Microsoft's Work IQ APIs Hit GA: What Agent Builders Actually Get on June 16
On June 16, 2026, Microsoft's Work IQ APIs reach general availability - a workplace intelligence layer that hands agents pre-assembled, permission-trimmed Microsoft 365 context instead of raw Graph calls. Here is what the four domains, three protocols, and consumption pricing mean for developers building enterprise agents.
7 min read
Omnigent: Databricks' Meta-Harness for Orchestrating Claude Code, Codex, and Custom Agents
Databricks open-sourced Omnigent, a meta-harness that sits above individual agent CLIs so your sessions, policies, and skills are not locked inside any single tool. Here is what it does, how to install it, and where it fits if you already run Claude Code and Codex.
8 min read
Codex Gets Computer Use in the EU - and a Clean Claude Code Import
OpenAI's mid-June 2026 Codex drop brings Computer Use to the EEA, UK, and Switzerland and adds selective Claude Code imports plus managed Bedrock auth to the CLI. Here is what actually shipped, verified against the changelog.
7 min read
'The Orchestration Is the Product': What Perplexity's Aravind Srinivas Sees That the Model Labs Don't
Perplexity launched a $200-a-month agent that coordinates 19 models and calls orchestration, not the model, the product. Here is the strategic case for why the durable, defensible layer in AI sits next to the labs, not inside them - and what 'token value per watt per user' actually means for builders.
11 min read
Vercel eve: The Framework for Building AI Agents
Vercel launched eve at Ship 26, an open-source agent framework it calls Next.js for agents. You define each agent as files under an agent/ directory, and eve compiles it into a production app on Vercel Functions with durable execution, sandboxes, approvals, subagents, and evals built in.
9 min read
Agent Workspaces Need Filesystem Contracts
GitHub's latest agent workspace trend points at a boring but important primitive: agents need explicit filesystem contracts before they get more tools.
8 min read
AI Infrastructure Agents Need Spend Guardrails
The viral DN42 AWS bill story is funny until you realize the missing primitive: infrastructure agents need hard cloud-spend guardrails before they touch real accounts.
8 min read
WebMCP: Google's Browser Standard That Lets AI Agents Use Websites as Tools
Chrome 149 ships an origin trial for WebMCP - a proposed web standard that lets developers expose JavaScript functions and HTML forms to AI agents. Here is what it does, how to implement it, and why it matters for the future of agentic browsing.
8 min read
Claude Agent SDK vs Claude Code: When to Build and When to Drive
Claude Agent SDK vs Claude Code explained: same engine, two surfaces. Here is the concrete decision line, plus where Managed Agents fits as the hosted third option.
8 min read
Claude Agent SDK vs LangGraph: Choosing Your Agent Stack in 2026
Claude Agent SDK vs LangGraph head-to-head: architecture, state handling, multi-agent patterns, and real pricing - plus a decision guide for which agent stack fits your team in 2026.
9 min read
Claude Agents vs Skills: Which One Do You Actually Need?
Claude agents vs skills, untangled: agents are workers with their own context window, skills are instructions loaded on demand. Here is the decision table.
8 min read
Claude Code Auto Mode Explained: Permissions Without the Prompts
Auto mode replaces permission prompts with a background safety classifier - here is how the Shift+Tab cycle, hard_deny rules, and glob deny patterns actually fit together.
8 min read
Claude Code Dynamic Workflows: The Complete Guide
Claude Code dynamic workflows turn orchestration into a JavaScript script that runs up to 1,000 agents per run - here is how scripts, schemas, budgets, and resume actually work.
10 min read
Claude Code Routines vs Managed Agents Schedules: Where Recurring Agent Work Should Live
Claude Code Routines and Managed Agents scheduled deployments both run Claude on a schedule - here is how the triggers, pricing, and limits differ, and which one fits your recurring agent work.
9 min read
Subagents vs Agent Teams vs Workflows: Claude Code's Parallelism Primitives, Compared
Claude Code subagents vs agent teams vs workflows: who holds the plan, the hard limits (16 concurrent, 1,000 agents per run), and which primitive fits your task.
9 min read
Setting Up the Memory Tool with Fable 5: Persistent Agents That Learn
Anthropic says persistent file-based memory improved Fable 5 three times more than it improved Opus 4.8. Here is the full memory tool setup - handlers, security, and context editing included.
8 min read
The Fable 5 Orchestrator Playbook: One Smart Model Managing Cheap Workers
A practical playbook for running Claude Fable 5 as the orchestrator over Sonnet and Haiku workers, with verified cost math on when the premium pays off.
10 min read
Fable 5 Task Budgets: Capping Agent Spend Before It Happens
Task budgets give Claude a token countdown for the whole agentic loop, so the model paces itself instead of discovering the limit when max_tokens truncates it. Here is how the beta works on Fable 5, what it does not enforce, and where it fits next to effort and the Usage API.
8 min read
Managing a Fleet of Claude Agents: A Practical Guide
An ops guide to managing a fleet of Claude agents: spawning patterns, worktree isolation, build gates, orphaned-agent failure modes, and OpenTelemetry monitoring.
10 min read
Recursive Self-Improvement: What Fable 5, Dario's Essay, and Anthropic's Own Data Actually Tell Us
In one 48-hour window Anthropic shipped Fable 5, Dario Amodei called for FAA-style model testing, and the Anthropic Institute published internal data on AI building AI. Here is what recursive self-improvement actually means, and how far along the loop really is.
10 min
Rewriting Your Prompts and Skills for Fable 5
Rewriting prompts and skills for Fable 5: what changes when you migrate agents from Opus 4.x, how effort interplay works, and which old workarounds now hurt.
10 min read
Ultracode: Claude Code Multi-Agent Orchestration Mode Explained
Ultracode is two documented things: a prompt keyword that turns one task into a dynamic workflow, and an /effort setting that pairs xhigh reasoning with automatic orchestration. Here is exactly what the docs say.
8 min read
12 Ways Developers Are Actually Leveraging Claude Fable 5
Twelve documented Claude Fable 5 use patterns - agent orchestration, overnight runs, 1M-context refactors, effort tuning - each with a how-to seed and doc link.
10 min read
What a Fleet of Claude Agents Actually Costs (July 2026 Math)
Claude Code parallel agents cost real money because every session draws from one quota - here is the July 2026 budgeting math, verified against live pricing.
10 min read
The One-Cent Attack: Prompt Injection Through Bank Transfer Memos
Security researchers showed a €0.02 bank transfer could compromise a banking AI assistant. Here is the exact attack chain - and what every developer building agents needs to do differently.
8 min read
Apache Burr vs LangGraph vs CrewAI: Choosing an AI Agent Framework in 2026
Apache Burr hit the front page of Hacker News with 142 points today. Here is what it actually does, how it compares to LangGraph and CrewAI, and when you should skip frameworks entirely.
9 min read
Claude Managed Agents Public Beta: What's Actually Available vs What's Gated
Claude Managed Agents is in public beta with solid sandboxing and session persistence - but the headline orchestration features are still locked behind a research preview waitlist. Here's what teams can actually ship today, what it costs, and when DIY alternatives make more sense.
8 min read
Fable 5 vs Opus 4.8: A Data-Driven Decision Guide for Engineering Teams
Fable 5 posts an 80.3% SWE-Bench Pro score and costs 2x Opus 4.8 - here is the task-profile scoring guide that tells you when the premium pays off.
7 min read
Managed Agents vs LangGraph vs Rolling Your Own: Who Should Run Your Agent Loop in 2026
The 2026 agent decision is not CrewAI vs LangGraph. It is whether your loop lives in vendor infrastructure, a self-hosted graph runtime, or a plain while-loop you wrote yourself. Here is how to choose.
9 min read
Mastra: Review and Setup Guide for TypeScript Agent Apps (2026)
A hands-on look at Mastra, the open source TypeScript framework for building production-ready AI agents and workflows -- with verified setup commands, honest tradeoffs, and current pricing.
8 min read
Mastra vs LangGraph.js: TypeScript Agent Frameworks Head to Head
Both Mastra and LangGraph.js are serious TypeScript agent frameworks - but they start from opposite philosophies. Here is what that means for your next project.
8 min read
OpenAI Agents SDK vs Claude Agent SDK: Building Agents on the Two Big Platforms
A practical comparison of OpenAI's Agents SDK and Anthropic's Claude Agent SDK - orchestration models, tool ecosystems, sandboxing, and how to choose the right platform for your team.
9 min read
The TypeScript AI Agent Stack in Mid-2026: Mastra vs Vercel AI SDK vs OpenAI Agents SDK vs LangGraph.js
Four mature, production-ready TypeScript frameworks have made building agents genuinely enjoyable. Here is how to pick the right one - and how they fit together.
10 min read
Vercel AI SDK 6 vs LangGraph 1.0: Which Agent Framework Should TypeScript Teams Use?
AI SDK 6 ships ToolLoopAgent and full MCP support. LangGraph hits 1.0 GA with durable state and built-in interrupt/resume. Here is how to choose between them for your TypeScript team.
8 min read
Goose: The Open Source AI Agent With 70+ MCP Extensions
Goose is a Rust-built AI agent with a CLI, desktop app, and API that runs against 15+ LLM providers and extends through 70+ MCP extensions - here is why developers are installing it.
8 min read
Harness Engineering Makes Tokens a Systems Budget
OpenAI's harness engineering post and new token-use research point to the same lesson: agentic coding teams need token budgets, receipts, and eval loops, not vibes.
8 min read
Headroom: Compress Agent Tool Output Before It Reaches the LLM
Headroom is a context compression layer that intercepts your AI agent's tool outputs and strips 60-95% of the tokens before they hit the model - with benchmarked accuracy preserved.
8 min read
Security Agents Need Repro Harnesses, Not More Scan Prompts
Anthropic's open-source vulnerability harness shows where AI security work is going: reproducible exploit loops, separate verification agents, and patch receipts.
9 min read
AI Agent Containment Needs a Capability Ledger
Anthropic's Claude containment writeup points to the next security layer for coding agents: deterministic capability ledgers, not another approval prompt.
9 min read
AI Agent Memory Needs a Context Ledger
GitHub Trending is full of agent memory and context tools. The useful version is not magic recall. It is a context ledger: source-linked, scoped, expiring memory that agents can inspect and users can audit.
8 min read
Spreadsheet Agents Need Permission Ledgers
The ChatGPT for Google Sheets exfiltration report is not just a spreadsheet bug. It is a warning about agentic office tools: permissions need to be action-scoped, logged, revocable, and visible.
8 min read
Domain Expertise Is the New Agentic Coding Moat
A huge Hacker News thread says domain expertise is the real moat in agentic coding. The sharper version: tacit judgment only compounds when you turn it into examples, tests, DSLs, and review gates.
8 min read
The Agent Security Checklist I Use Before Connecting Tools
Before an AI agent gets tools, files, APIs, MCP servers, or deployment access, decide what it can read, write, call, log, and roll back.
8 min read
Mastra for Durable TypeScript Agents: Where It Fits and Where It Does Not
Mastra is the strongest fit when a TypeScript product needs agents, workflows, memory, tools, MCP, evals, and traces in one backend layer. It is not the right answer for every chat feature.
8 min read
Mastra vs CopilotKit vs LangGraph: Build the Same Agent App Three Ways
A practical field note on where Mastra, CopilotKit, and LangGraph fit when you are building the same agent-native product interface.
9 min read
The Model, IDE, CLI, and Agent Framework Changes That Actually Matter
The AI coding market is noisy. The changes that matter are easier to spot when you separate model capability, editor loops, terminal agents, background agents, agent frameworks, UI layers, context, security, and cost.
10 min read
The New AI Coding Stack I Would Pick Today
If I were rebuilding my AI coding workflow on May 30, 2026, I would not pick one magic tool. I would pick a layered stack: terminal agent, editor, background agent, Mastra, CopilotKit, MCP, context, security, and cost controls.
11 min read
Permissions, Logs, and Rollback for AI Coding Agents
AI coding agents become safer when permissions, logs, and rollback are designed as one system. Here is the operating loop I would put around any agent that can edit code, run tools, or open pull requests.
9 min read
Prompt Injection in Agent Apps: The Practical Version
Prompt injection stops being an abstract LLM risk once an agent can call tools. The practical defense is data boundaries, structured handoffs, tool guardrails, and approval gates around side effects.
8 min read
State of AI Coding: What Changed This Month
May 2026 was not about one more coding model leaderboard. The useful signal was control planes, UI-agent contracts, durable TypeScript workflows, usage economics, and runtime security.
10 min read
When CopilotKit Is the UI Layer, Not the Agent Framework
CopilotKit is strongest when you treat it as the product-facing agent UI layer: chat surfaces, frontend tools, shared state, generative UI, and human approval around a backend agent.
8 min read
Claude Opus 4.8 Is an Agent Honesty Release
Claude Opus 4.8 looks like a benchmark bump, but the developer story is better honesty, dynamic workflows, and effort controls that make long-running agent work easier to review.
8 min read
Local Code Graphs Are the Agent Context Layer
CodeGraph shows why coding agents need a local, queryable repo map. The win is not magic token savings. It is faster orientation, fewer wrong files, and better review receipts.
9 min read
AI Agent PMF Is a Cost Control Problem Now
AI coding agents have crossed from demo to daily workflow. The next bottleneck is not demand. It is cost attribution, budget gates, and workflow design that keeps agent fleets from turning useful work into surprise spend.
8 min read
AI Chat Fatigue Is a Workflow Design Bug
A front-page Hacker News essay about being tired of AI answers points at a real developer problem: chat is too easy to launder into fake work. The fix is verifiable workflows, not more conversational polish.
8 min read
Coding Agents Need Codebase Maps, Not Bigger Prompts
GitHub is suddenly full of codebase knowledge graph projects for Claude Code, Codex, Cursor, and other agents. The useful version is not a pretty graph. It is a map that changes planning, editing, and review.
8 min read
Claude Knowledge Work Plugins Turn Agent Setup Into Team Infrastructure
Anthropic's knowledge-work plugin repo is trending because it packages skills, connectors, slash commands, and sub-agents around job functions. The interesting shift is from personal prompts to team-distributed operating systems.
7 min read
Constraint Decay Is the Coding Agent Bug Nobody Can Prompt Around
A new arXiv paper shows coding agents can pass loose backend tasks, then fall apart when architecture, database, and ORM constraints pile up. The fix is not longer markdown. It is executable constraints.
8 min read
Reasonix Shows the Next Coding Agent Fight Is Cache Discipline
Reasonix hit Hacker News with a DeepSeek-native pitch: keep long coding sessions cheap by designing the agent loop around prefix caching. The interesting question is when cache efficiency helps quality, and when it fights the harness.
7 min read
CLI-Anything Turns Any Software Into an Agent-Ready Command Line
HKUDS/CLI-Anything hit 40,000 stars by solving a stubborn gap: most desktop software has no interface AI agents can reliably drive. Its 7-phase pipeline auto-generates a tested CLI harness from source code.
6 min read
12-Factor Agents: Production Principles for Reliable AI Agents
HumanLayer's 12-Factor Agents guide turns agent reliability into an engineering checklist: own prompts, context, tools, control flow, state, human approval, and observability before a demo becomes production.
8 min read
AI Security Scanners Move the Bottleneck to Triage
Anthropic's Project Glasswing update is a useful signal for developer teams: AI can find vulnerability candidates faster than humans can verify, disclose, patch, and ship them.
8 min read
Multi-Stream LLMs Hint at the Next Agent Architecture
The Multi-Stream LLMs paper argues that agents are bottlenecked by single chat streams. The practical takeaway is not to rebuild everything today, but to design agent runtimes around separated channels.
8 min read
Sandboxed Agents Are Becoming the Team Control Plane
Runtime's Launch HN thread is a useful signal: teams do not just want isolated coding agents. They want a control plane for approvals, secrets, telemetry, review, and merge policy.
8 min read
Forge Shows the Local Agent Reliability Gap Is a Harness Problem
Forge hit the Hacker News front page with a strong claim: small local models can become much more useful at tool-calling when the harness catches structural failures, retries intelligently, and controls context.
7 min read
Anthropic Buying Stainless Is About Agent Plumbing
Anthropic's Stainless acquisition is not just an SDK deal. It is a bet that agents need generated SDKs, CLIs, docs, and MCP servers from the same source of truth.
8 min read
AgentMemory Is Useful Only If You Audit What It Remembers
AgentMemory gives Claude Code, Codex, Cursor, and other agents persistent local memory. The real adoption question is not recall accuracy. It is whether your team can inspect, prune, and govern what gets remembered.
8 min read
Agent Memory Benchmarks Are Not Enough
Persistent memory for coding agents is trending because every session still starts too cold. The hard part is not saving facts. It is proving recall, freshness, deletion, and rollback under real development pressure.
9 min read
Claude Platform on AWS Is Enterprise Agent Plumbing, Not Just Procurement
Claude Platform on AWS matters because it moves agent adoption into identity, billing, commitments, and platform controls. That is where enterprise AI work gets real.
8 min read
Interaction Models Are the Next AI Developer Tool Interface
Thinking Machines' interaction-models post points at a useful shift for developer tools: stop designing around single chat turns and start designing around shared work.
8 min read
TanStack's npm Compromise Is the CI Lesson Agent Teams Needed
The TanStack npm incident was not just a package-security story. It was a reminder that AI agent workflows inherit every weak trust boundary in CI.
9 min read
Ruflo Is an Agent Meta-Harness. Treat the Star Count as a Warning Label.
Ruflo turns Claude Code and Codex into a larger agent harness with plugins, memory, swarms, MCP tools, and federation. The useful question is not the star count. It is how much harness you actually need.
8 min read
Claude Managed Agents Are Starting to Look Like Backend Jobs
Claude Managed Agents now have multiagent sessions, outcomes, webhooks, and vault events. The practical takeaway is not just better agents. It is that agent runs need backend job discipline.
9 min read
DeepSeek-TUI: The Rust Terminal Coding Agent With MCP, Skills, and 1M-Token Context
DeepSeek-TUI is a Rust-built terminal coding agent wrapping the DeepSeek V4 API with full tool use, MCP server support, a composable skills system, and three operational modes for different risk tolerances.
6 min read
How We Patched 100+ PRs Across Our App Empire in One Day
31 deployed apps. 7 down. Favicons missing on 20 of 24 reachable hosts. Sentry on zero. Here is how a single audit turned into 58 PRs in one afternoon - and what shipped, what didn't, and what the pattern was.
6 min read
219 PRs in One Day: A Parallel Agent Fan-Out Postmortem
Notes from a single session running 200+ Claude Code subagents in parallel across 35 repos. What worked, what broke, and the patterns I codified into a skill so the recipe replays.
8 min read
Codex Automations: Where Scheduled AI Agents Actually Help
Codex automations are useful when recurring engineering work has clear inputs, reviewable outputs, and safe boundaries. Here is the practical playbook.
9 min read
Codex Is Becoming a General-Purpose AI Agent, Not Just a Coding Tool
OpenAI is turning Codex from a coding assistant into a broader agent workspace for files, apps, browser QA, images, automations, and repeatable knowledge work.
8 min read
Codex Loops: What Boris Cherny Gets Right About Managing Agent Work
Boris Cherny's loop-heavy Claude Code workflow points at the next Codex content lane: recurring agents that babysit PRs, CI, deploys, and feedback streams.
8 min read
Karpathy's Loopy Era Is the Best Way to Understand Codex
Andrej Karpathy's loopy era frame explains why Codex is becoming less like a chatbot and more like an agent loop manager for real software work.
9 min read
The 98% Context Reduction Pattern
Efficient agents do not stuff every tool result into the model context. They keep intermediate state in code, files, and execution environments, then return compact summaries and receipts.
8 min read
Approval Fatigue Is an Agent Security Bug
Manual approval prompts stop protecting users when coding agents ask too often. The better pattern is risk-aware autonomy: safe defaults, narrow deny rules, and approvals only for meaningful changes.
7 min read
Claude Code Agent Teams, Subagents, and MCP: The 2026 Playbook
Claude Code is turning into an orchestration layer for agent teams. Here is how subagents, MCP, hooks, and long context fit together in 2026.
9 min read
Client-Side Tool Calling Is the Privacy Pattern AI Apps Need
A Show HN PDF form demo points at a bigger architecture shift: keep sensitive documents local, expose narrow browser tools to the model, and make AI assistance inspectable.
7 min read
Codex /goal and Claude Managed Outcomes: The New Control Loops
A deep comparison of Codex's new /goal loop and Claude managed agents outcomes, with practical workflow examples, control tradeoffs, and migration guidance for long-running tasks.
18 min read
Flue: The Agent Harness Framework and Why It Feels Different
A long-form technical read on Flue from Fred K Schott, with deeper comparisons against OpenAI Agents, Vercel AI SDK, Google ADK, LangChain, Deep Agents, and CrewAI, plus practical production patterns.
24 min read
Long-Running Agents Need Harnesses, Not Hope
A long-running coding agent is only useful if the environment around it can queue tasks, capture logs, checkpoint state, verify behavior, limit cost, and recover from failure.
9 min read
One Tool Beats Ten Endpoints
Most agent tool APIs are just REST endpoints with nicer names. Production agents need intent-shaped tools that compress workflows, reduce context, and return reviewable receipts.
8 min read
Skills Are How Agents Learn the Job
Skills turn a general coding agent into a trained teammate by packaging runbooks, scripts, examples, and domain-specific judgment into reusable instructions.
7 min read
Warp Open Sourced the Terminal. The Real Story Is Agent Operations
Warp going open source is not just a terminal story. It is a signal that AI coding tools are shifting from chat UX toward agent operations, where planning, execution, review, and feedback loops live close to the shell.
8 min read
12 Tools in One Night: An Honest Overnight Agent Report
I told an agent to improve the site every 10 minutes and went to sleep. Here is what 12 new repos, 60 PRs, and three goofs taught me about overnight orchestration.
11 min read
Agent Architecture: Building Multi-Step AI Workflows That Survive Production
A practical architecture for multi-step Claude agents. Loop patterns, state management, error recovery, and the production gotchas that turn a five-step demo into a 20 percent success rate at scale.
11 min read
Model Context Protocol: A Production Guide To Building MCP Servers
Build MCP servers that connect Claude to your databases, APIs, and tools. Architecture, TypeScript SDK code, debugging, and the production gaps the spec doesn't cover.
13 min read
Tool Use in the Claude API: Production Patterns for Reliable Agents
Master tool use in the Claude API. Schema design, retry logic, multi-step loops, and the failure modes that only show up at 10k calls a day.
12 min read
The DD Stack Cookbook: Five Recipes That Compose
Five worked examples showing how the new Developers Digest products plug into each other. Real agent filesystems, auto-snapshots, gated skill libraries, eval suites, and a recursive MCP host.
9 min read
Introducing agentfs: A Filesystem for AI Agents
agentfs is filesystem-shaped storage for AI agents. Postgres-backed on Neon, no cold starts, no exec by design. Pay-only plans start at twenty dollars.
9 min read
10 Tools We Built for Agent Infrastructure
Ten private tools shipped overnight - observability, skills, hooks, prompts, and evals - aimed at the agent infrastructure gap small teams keep falling into.
11 min read
The Agent Reliability Cliff: Why Your 10-Step Chain Only Succeeds 20% of the Time
The math of agent pipelines is brutal. 85% reliability per step compounds to about 20% at 10 steps. Here is why long chains collapse in production, and the six patterns the field has converged on to fight the decay.
9 min read
7 AI Agent Orchestration Patterns Every Developer Should Know
From single-agent baselines to multi-level hierarchies, these are the seven patterns for wiring AI agents together in production. Each with a decision rule, an implementation sketch, and the tradeoffs that actually matter.
10 min read
Multica Turns Coding Agents Into Teammates. The Hard Part Is Receipts.
Multica is pushing the agent teammate pattern: assign issues, route work to local runtimes, stream progress, and compound skills. Here is the practical read for AI dev teams.
8 min read
The $400 Overnight Bill: Why Managed Agents Need FinOps Now
Five managed-agent providers, five pricing models, zero unified cost attribution. If you're running agents overnight, you need FinOps you don't have yet.
13 min read
Claude Code vs Codex vs Cursor vs OpenCode: Which Agent Ships More Code?
Four agents, same tasks. Honest trade-offs from a developer shipping production apps with all of them.
10 min read
How to Write a CLAUDE.md: The Complete 2026 Guide
CLAUDE.md is the highest-leverage file in any Claude Code project. Here's what goes in one, what doesn't, and the patterns that actually ship.
12 min read
What Is an AI Coding Agent? The Complete 2026 Guide
Autocomplete wrote the line. Agents write the pull request. The shift from Copilot to Claude Code, Cursor Agent, and Devin - explained with links to the docs that prove every claim.
13 min read
What Is an MCP Server? A Developer's Beginner Guide (2026)
MCP is the USB-C of AI agents. What the Model Context Protocol is, why Anthropic built it, and how to install your first server in Claude Code or Cursor. Fact-checked against the official MCP spec.
13 min read
OpenAI Codex Cloud Security Playbook 2026: Internet Access, Prompt Injection, and Safe Defaults
A practical security playbook for running Codex cloud tasks safely in 2026 using OpenAI docs: internet access controls, domain allowlists, HTTP method limits, and review workflows.
10 min read
What Hacker News Gets Right About AI Coding Agents in 2026
Hacker News keeps arguing about Claude Code, Codex, skills, MCP, and orchestration. Under the noise, the same four truths keep surfacing: workflows matter more than demos, verification is the bottleneck, skills beat prompts, and orchestration matters more than raw autonomy.
11 min read
Building SaaS with AI Agents in 2026: The Complete Workflow
How to use AI agents to plan, scaffold, build, test, and deploy a SaaS product. Parallel development patterns, real workflow examples, and the operational details that determine whether your AI-assisted build succeeds or fails.
15 min read
Context Engineering: The Highest-Leverage Skill in AI-Assisted Development
Context engineering is the practice of designing the persistent information that surrounds every AI interaction. CLAUDE.md files, system prompts, skill libraries, and memory systems. It is the single highest-leverage skill for developers working with AI agents in 2026.
14 min read
How to Coordinate Multiple AI Agents: The Definitive Guide for 2026
Production-tested patterns for orchestrating AI agent teams - from fan-out parallelism to hierarchical delegation. Covers CrewAI, LangGraph, AutoGen, OpenAI Agents SDK, Google ADK, and custom approaches with real code.
14 min read
Self-Improving AI Agents: Building Systems That Learn From Their Mistakes
AI agents that reflect on failures, accumulate skills, and get better with every session. Reflection patterns, memory architectures, skill extraction, and working code examples for building agents that actually learn.
13 min read
AI Agent Memory Patterns
Agents forget everything between sessions. Here are the patterns that fix that: CLAUDE.md persistence, RAG retrieval, context compression, and conversation summarization.
9 min read
How to Debug AI Agent Workflows
AI agents fail in ways traditional debugging cannot catch. Here are the tools and patterns for finding and fixing broken agent loops, tool failures, and context issues.
9 min read
AI Skills for Every Career: Agents and Knowledge Work
AI agent skills are not just for developers. Here is how 12 professions use packaged AI workflows to do better knowledge work.
12 min read
Local OpenTelemetry Traces Are Agent Receipts
AI agent work needs local observability. OpenTelemetry, OTLP, Vercel AI SDK telemetry, and lightweight trace viewers give developers receipts for model calls, tool use, latency, errors, and cost before anything goes to production.
9 min read
How to Build an AI Agent in 2026: A Practical Guide
A step-by-step guide to building AI agents that actually work. Choose a framework, define tools, wire up the loop, and ship something real.
10 min read
Ship Code While You Sleep: The Overnight Agent Workflow
How to spec agent tasks that run overnight and wake up to verified, reviewable code. The spec format, pipeline, and review workflow.
11 min read
AI Agents Explained: A TypeScript Developer's Guide
AI agents use LLMs to complete multi-step tasks autonomously. Here is how they work and how to build them in TypeScript.
6 min read
How to Build AI Agents in TypeScript
A practical guide to building AI agents with TypeScript using the Vercel AI SDK. Tool use, multi-step reasoning, and real patterns you can ship today.
10 min read
Multi-Agent Systems: How to Orchestrate Multiple AI Agents in TypeScript
From swarms to pipelines - here are the patterns for coordinating multiple AI agents in TypeScript applications.
6 min read
Open Source Has a Bot Problem: Prompt Injection in Contributing.md
AI coding agents now read repository docs, config, issues, and comments before opening pull requests. That turns CONTRIBUTING.md and AGENTS.md into part of the security boundary.
8 min read
What Is Claude Code? The Complete Guide for 2026
Claude Code is Anthropic's AI coding agent for terminal, IDE, desktop, and browser workflows. Learn what it does, how it works, pricing, setup, MCP, skills, hooks, and subagents.
15 min read
What Is MCP (Model Context Protocol)? A TypeScript Developer's Guide
MCP lets AI agents connect to databases, APIs, and tools. Here is what it is and how to use it in your TypeScript projects.
5 min read
CLIs Over MCPs: Why the Best AI Agent Tools Already Exist
OpenClaw has 247K stars and zero MCPs. The best tools for AI agents aren't new protocols - they're the CLIs developers have used for decades.
8 min read
Composio 101: Give Your AI Agent Access to 500+ Apps
Composio is a tool infrastructure layer that connects AI agents to Gmail, GitHub, Slack, Google Calendar, and hundreds more apps - all auth handled for you. Here is how to set it up and start building real cross-app workflows.
7 min read
OpenAI Agents SDK for TypeScript: A Practical Guide
OpenAI released their Agents SDK for TypeScript with first-class support for tool calling, structured outputs, multi-agent coordination, streaming, and human-in-the-loop approvals. Here is how each piece works.
9 min read
OpenAI Deep Research: The AI Agent That Does Your Homework
OpenAI's Deep Research is an AI agent inside ChatGPT that plans and executes multi-step research workflows, browsing dozens of websites and producing cited reports in minutes instead of hours.
7 min read
ChatGPT Tasks: Scheduled AI Agents Inside ChatGPT
OpenAI added scheduled tasks and reminders to ChatGPT, turning it from a chat interface into something closer to a personal AI agent. Here is how it works, what it can do today, and where this is heading.
8 min read
Gemini Deep Research: Google's AI Research Agent
Google's Gemini Advanced includes a deep research feature that searches dozens of websites, verifies information across multiple sources, and generates detailed cited reports. Here is how it works and how it compares to other AI research tools.
8 min read
Build an AI Agent Web App with LangGraph and CopilotKit
Wire a Python LangGraph agent into a Next.js frontend using CopilotKit's co-agent architecture. Full walkthrough covering the graph, search nodes, streaming state, and the React UI.
14 min read
Related Tools
All tools →OpenAI Agents SDK
Lightweight Python framework for multi-agent systems. Agent handoffs, tool use, guardrails, tracing. Successor to the experimental Swarm project.
AI Frameworksn8n
Self-hostedWorkflow automation platform with native AI agent building. Visual editor plus JavaScript/Python code nodes, 500+ integrations, self-hostable under a fair-code license.
ProductivityAgentCanvas
NewA hosted infinite canvas your headless AI agents drive over MCP. Any MCP-speaking agent - Claude Code, Codex, Cursor, or a script - creates HTML docs, images, and video on a live canvas, streamed in as it builds.
ProductivityGuides
All guides →Claude Code Setup Guide
Configure Claude Code for maximum productivity -- CLAUDE.md, sub-agents, MCP servers, and autonomous workflows.
GuideMCP Servers Explained
What MCP servers are, how they work, and how to build your own in 5 minutes.
GuideBuilding Your First MCP Server
Step-by-step guide to building an MCP server in TypeScript - from project setup to tool definitions, resource handling, testing, and deployment.
GuideAI Agent Frameworks Compared: LangGraph vs CrewAI vs Mastra vs CopilotKit
Deep comparison of the top AI agent frameworks - LangGraph, CrewAI, Mastra, CopilotKit, AutoGen, and Claude Code.
GuideKeep exploring
More on AI Agents
- - OpenAI Agents SDK - recommended AI Agents tool from the Developers Digest directory
- - Compare Tools - dive deeper across the Developers Digest knowledge base
- - All AI Agents articles in the blog archive
- - Developers Digest on YouTube - video tutorials covering AI Agents and more
Get Smarter About AI Dev
New tutorials, open-source projects, and deep dives on coding agents - delivered weekly.
One email per weekReal code, not theoryFree forever
Explore 862 topics
Browse All Topics