Sitemap

Pages

• Home
• Blog
• Tutorials
• AI Tools
• Guides
• Claude Code Field Guide
• Courses
• Learn
• Toolkit
• Topics
• Series
• Best Of
• Projects
• Resources
• Glossary
• About
• Connect
• Uses
• Roadmap
• Changelog
• Start Here

Decision Pages

Canonical comparison, pricing, alternatives, and tool-selection pages.

• AI Tool Comparisons
• Comparison Matrix
• Pricing
• AI Coding Tools Pricing 2026
• AI Agent Frameworks Compared
• Claude Code vs Cursor
• Claude Code vs Codex
• Aider vs Claude Code
• LangChain vs Vercel AI SDK
• OpenAI vs Anthropic

Blog Posts (976)

• Cloudflare Adaptive Intelligence: Bot Scores That Retrain Weekly Instead of Quarterly2026-08-31
• Podcast Your Release Notes: Two-Voice Audio from Git History with ElevenLabs2026-08-31
• Make Your Coding Agents Talk: Voice Summaries with the Rime CLI2026-08-31
• Tencent Hy4 Preview: 770B Open MoE, Agentic Benchmarks, and Where It Fits in 20262026-08-31
• Your Agent Has a Five-Constraint Budget2026-08-31
• GitHub Copilot's September Reset: Prepaid Seats, One Unified Agent Experience, Balanced Reviews by Default2026-08-28
• The Response Looked Right. The Work Was Not Done.2026-08-28
• Weekly Highlights: Cheaper Tokens, Higher Stakes2026-08-28
• Gemini Omni 1.1 Flash Goes GA: Scene Extension, Keyframe Control, and 4K in the Gemini API2026-08-27
• Inside OpenAI's Hugging Face Report: 1,200 Agents Built a Message Board, 700 Attacked, and 7% Spoofed Their Transcripts2026-08-26
• CodeNib Makes Repository Context a Data System2026-08-24
• Thinking in Python: Bruce Eckel Revives His 2008 Book With Claude in 20262026-08-24
• Codex Computer History Turns Repeated Work Into Reusable Skills2026-08-23
• Coding Agents Tripled PRs. Total Dev Time Still Went Up2026-08-23
• fx in Practice: Setup, Scripting, and Subagents2026-08-23
• fx Deep Dive: Inside Vercel's Tiny Native Coding Agent2026-08-23
• fx vs pi: Is Minimal the New Big for Agentic CLIs?2026-08-23
• Grok Bot's Core Primitive: Every Bot Gets a Computer2026-08-23
• Grok Bot's Meta Controls: Oversight as a Product Primitive2026-08-23
• Grok Bot Has the Right Shape: Four Primitives, Nothing Else2026-08-23
• Grok Bot Routines: Automations Without Automation-Building2026-08-23
• Herdr Deep Dive: Inside the Agent-Native Terminal Multiplexer2026-08-23
• How to Run an AI Agent Fleet on Herdr: Setup Guide2026-08-23
• Herdr vs pi vs tmux: Which Agent Harness Should You Run?2026-08-23
• Herdr Joined YC. Its Eight-Week Plugin Ecosystem Is the Signal2026-08-23
• The New MCP Roadmap: Progressive Discovery and Agent Auth2026-08-23
• One Vertical Line: The OpenClaw GitHub Star Chart Story2026-08-23
• pi Deep Dive: The Minimal Architecture Behind 95,000 GitHub Stars2026-08-23
• Hands-On With Pi: Run Modes and JSONL Session Trees2026-08-23
• pi vs Claude Code vs OpenCode: Picking Your Agentic CLI2026-08-23
• Ray CVE-2025-62593: Botnet Beat the Patch, CISA Gives Feds 3 Days2026-08-23
• The Quiet Tax on Your Cheap Agent Tier2026-08-23
• 6 of 11 ASR Models Transcribe the Benchmark, Not the Audio: Benchmark Optimization in Speech, Quantified2026-08-22
• Where to Run DeepSeek V4 Flash Free and Cheap: Every Provider Compared (2026)2026-08-22
• How to Make Claude Code 10x Better at Design: Image and Video Assets From the Agent Loop2026-08-22
• DeepSeek V4 Flash Vision Exp: Experimental Vision, Limits, and How to Run It in OpenCode2026-08-21
• Don't Paste the AI vs Vomit vs NoBuzz: AI Slop Tools Compared2026-08-21
• GitHub's August 17 Outage: Agent Fleets Need a 4-Hour Local Fallback2026-08-21
• Ox Alpha on OpenCode: The Free Stealth Model, Specs, Privacy Split, and How to Run It2026-08-21
• arrayref 0.3.10 Ran a Remote Payload at Build Time2026-08-21
• Slack Code vs Claude Code vs Cursor vs OpenCode: When Agents Belong in Chat2026-08-21
• The Oracle Is Agreeing With Itself2026-08-21
• Cloudflare Gateway Can Now Detect MCP Traffic on the Wire: Shadow MCP Gets a Network Boundary2026-08-15
• Qwen3.8-27B vs Opus 4.6 Max: The Laptop-Sized Model That Beat a Frontier Flagship on Agentic Benchmarks2026-08-15
• Automate Video Editing with the Descript API: Raw Recording to Published Cut in One Script2026-08-14
• Where to Run GLM-5.3 Free and Cheap: Every Provider Compared (2026)2026-08-14
• The ICML 2026 Agent Reproduction Audit: 23% of Examined Papers Had Falsified or Contested Claims2026-08-14
• The Judge Is Now a System You Design2026-08-14
• Weekly Highlights: Cheaper Agents, Harder Questions2026-08-14
• GitHub's AutoGPT Playbook: The Repo Instruction File Is Now an API for Other People's Agents2026-08-13
• We Read DeepSeek Harness: What 453K Lines of Agent Runtime Actually Say2026-08-13
• Grok 4.6: xAI's Agent-Focused Update Matches GPT-5.6 Sol at the Same $2/$6 Price2026-08-13
• Mendel Godel Machine: Why Self-Improving Coding Agents Need Lineage2026-08-13
• CLAUDE.md Files Never Stop Growing: A New Paper Names the Mechanism2026-08-12
• Dub Your Videos into Every Language: The ElevenLabs Dubbing Pipeline2026-08-12
• The $44 Compiler: Persistent Projects Beat Persistent Agents2026-08-12
• GitHub Copilot for JetBrains Gains Persistent Memory and Ollama BYOK2026-08-12
• LFM2.5-VL-3B: Liquid AI's 3B Vision Model Reads Screens, Grounds Objects, and Calls Tools on a Laptop2026-08-12
• OpenAI's Daybreak Cyber Models Land on Amazon Bedrock: GPT-5.6-Cyber Gets Its First Cloud Path2026-08-12
• OpenAI Enterprise Signals: The Agentic Gap Is Now Measurable, and It Is Not About Models2026-08-12
• Skill Files Are the New Supply Chain Attack Surface2026-08-12
• ACE vs ALTK-Evolve: How You Deliver Agent Memory Determines the Token Bill2026-08-11
• Anthropic Now Watermarks All Claude Output: Text Watermarks and C2PA for Files2026-08-11
• Cactus Needle 2: The 14MB Agentic LLM That Runs on a Raspberry Pi 52026-08-11
• Cloudflare DDoS Report H1 2026: 1 Tbps Attacks Soared as DNS Floods Became the Leading Vector2026-08-11
• Deploy From Your Coding Agent: Wire Railway's MCP Server Into OpenCode2026-08-11
• GitHub Copilot SDK for Java: Annotations, Virtual Threads, and BYOK for Enterprise Agent Harnesses2026-08-11
• Encrypted Chain-of-Thought Is Not Private: New Paper Decodes Reasoning Traces From Anthropic, OpenAI, and Google APIs2026-08-11
• Stop Means Stop: New Paper Finds Agent Approval Gates and Cancellation Leak in Six Frameworks2026-08-11
• Vercel Sandbox Gets a Real Network Boundary: Why Egress Control Is the Missing Half of Agent Security2026-08-11
• AgentChaos: Fault Injection Shows Agent Robustness Is a Systems Problem, Not a Model Problem2026-08-10
• Distilling an LLM on One GPU: Offline Top-K Logits and a Fused Chunked KL Loss2026-08-10
• LivePlan: Monitoring and Corrective Steering for Coding Agents, Without the LLM Tax2026-08-10
• Muse Glimmer 30B: Meta's Open-Weight Local Agent Model, Benchmarks, and Hardware Reality2026-08-10
• OpenAI Ships GPT-5.6-Cyber Through Daybreak Red: The Numbers, the Chrome CVE, and What Access Looks Like2026-08-10
• Ship a Remote MCP Server: Give Your Coding Agent Cloud Tools in an Afternoon2026-08-10
• Give Your Site a Voice: Build a Conversational Support Agent with ElevenLabs Agents2026-08-09
• Claude Code Cross-Session Messaging: Your Agents Can Now Talk to Each Other2026-08-09
• When Your AI-Generated App Turns Out to Be Someone Else's, Bug for Bug2026-08-09
• Make Your Coding Agent Talk: Audio Briefs from Agent Runs with ElevenLabs2026-08-08
• GitHub Copilot Code Review Effort Levels Are GA: Lite vs Balanced2026-08-08
• GitHub Copilot's Impact Dashboard Now Puts a Dollar Figure on Agent-First Development2026-08-08
• GitHub Apps Can Now Be Installed at the Enterprise Level, Opening the Platform to Third-Party Integrators2026-08-08
• Grok Imagine Image 2.0 Ships: xAI's Typography-Aware Image Model Is Already on Vercel's AI Gateway2026-08-08
• Hermes Agent Gains Vercel AI Gateway and Sandbox Backends: The Agent Stack Goes Plug-and-Play2026-08-08
• Vercel Skill Packs: The Distribution Layer for Agent Skills Just Landed2026-08-08
• DeepMind Open-Sources WeatherNext Cyclones After a Nature-Verified Breakthrough2026-08-08
• Cloudflare Ships Behavioral Trust for the Agentic Internet: 206M Events, 73K Zones2026-08-07
• Cloudflare's Agentic Internet: Readable, Discoverable, Callable, and Payable2026-08-07
• Cloudflare Radar Researcher: A Plain-Language Agent Over 500 Live API Endpoints2026-08-07
• Cloudflare Folds Workers AI Into AI Gateway: One Control Plane for Every Model Provider2026-08-07
• DCAS: Why Fine-Tuned Coding Agents Fall Apart When You Switch Scaffolds2026-08-07
• Anthropic Cuts Fable 5 Biology Fallbacks by 85%: What the Safeguard Tuning Means for Developers2026-08-07
• Kimi K3 Is GA in GitHub Copilot: Pricing, Rollout, and What It Means for Model Choice2026-08-07
• OpenAI Says It Can't Rule Out Critical Cyber Capability for Astra, a First for the Preparedness Framework2026-08-07
• OpenJDK Bans AI-Generated Code: What the New Policy Means for Java Contributors2026-08-07
• TutorMoments: AI2's New Benchmark Shows LLM Tutors Over-Help by Default2026-08-07
• Weekly Highlights: Agents Became the Attack Surface, Open Weights Took the Agentic Lead2026-08-07
• Agent Plugins 1.0.0: One Package Format for Agent Skills and MCP Servers2026-08-06
• Cloudflare Adds Identity-Aware AI Gateway Analytics: Behavioral Baselines for Every Agent and Employee2026-08-06
• Kitesurf: Cloudflare's Agent-First Browser Runs in V8 Isolates on Workers2026-08-06
• GitHub Malware Advisories Now Cover Eight Package Ecosystems2026-08-06
• Meta Ships Muse Code and Muse Spark 1.2: A Terminal Agent With a 12x Cheaper Contributor Tier2026-08-06
• OpenAI Retunes GPT-5.6 Sol in ChatGPT and Makes Luna the Free Tier Default2026-08-06
• SkillSV: A Shapley Framework That Values the Lines Inside an Agent Skill2026-08-06
• The Plateau Was the Instrument2026-08-06
• Chat SDK Adds Durable Approvals: Agent Workflows That Wait For a Human2026-08-06
• UK AISI Reports Agents Taking Real-World Action During Cyber Evals: 19 Events, 17 From One Model2026-08-05
• Cloudflare's Agent Access Model: Zero Trust for Task-Scoped Agent Runs2026-08-05
• Cloudflare OS: The Open Source Agent Workspace That Treats Apps Like Files2026-08-05
• DeepSeek V4 Flash Is 90% Off Through Novita on Vercel AI Gateway: The Cost Math2026-08-05
• Put an AI Agent Behind a Webhook: Turn GitHub Issues into Pull Requests2026-08-05
• Kill Your Agent Runs Early2026-08-05
• LFM2.5-2.6B: Liquid AI's On-Device Agent Model Runs at 220 Tokens/s in Under 2.5 GB2026-08-05
• Next.js 16.3 Is Out: Instant Navigations, 90% Less Dev Memory, and Versioned Docs for AI Agents2026-08-05
• The Harness Is the New Cost Lever: Databricks' Benchmark and Pi's Context Discipline2026-08-05
• Prime Agent: A Self-Improving Coding Harness Where Everything Is Python2026-08-05
• The v0 API Is GA: Vercel Just Made Its App-Building Agent a Headless Service2026-08-05
• Cloudflare's Agent Development Lifecycle: The ADLC Is Now a Platform Bet2026-08-04
• Cloudflare Billable Usage API: Programmatic Cost Visibility for Agent-Run Accounts2026-08-04
• Cloudflare CI/CD as Workflows: TypeScript Pipelines, Agent Self-Healing, and the End of YAML Fatigue2026-08-04
• Cloudflare Wallets Gives Agents a Credit Card, an ID, and a Spending Cap2026-08-04
• 13.5 Million Copilot Sessions: What Production Coding Agent Traffic Actually Looks Like2026-08-04
• GitLab to GitHub Migrations Go GA: gh gl2gh, What Moves and What Doesn't2026-08-04
• Mistral Shieldstral: A 3B Open-Weight Policy-Adaptive Moderation Model That Beats Models 7x Its Size2026-08-04
• Self-Improving Applications Are Now Cheaper Than Hiring: The Claude Code and Codex Closed Loop2026-08-04
• Give Your Coding Agent a Voice: Dictate Prompts with Wispr Flow2026-08-04
• @cloudflare/computer: an Agent Runtime That Treats a Container as a Tool, Not a Home2026-08-03
• Cloudflare Runs Kimi and GLM at Scale: FP8 KV Caches, INT4 Weights, and a Cache Safety Net2026-08-03
• Workers Can Now Accept Inbound TCP and Serve gRPC: Cloudflare Closes the HTTP-Only Gap2026-08-03
• Workers RPC Now Bridges Python and JavaScript: No Schemas, No Serialization Code2026-08-03
• Octane: Inferno's Successor Compiles React's Programming Model Ahead of Time2026-08-03
• How OpenAI Built GPT-Live: Full-Duplex Voice, WARP, and the Death of the Turn Detector2026-08-03
• Qwen 3.8 Max Ships: 2.4T MoE, 1M Context, $2/$6 per MTok, Open Weights Next Week2026-08-03
• StateAct Shows Computer-Use Agents Need Program State, Not Just Pixels2026-08-03
• The Judge Is Leaving the Agent Loop2026-08-03
• The Coding-Agent Colony: What Gas Town Changes2026-08-03
• The Continuous Thunderdome: Why Agent Harnesses Become Application Infrastructure2026-08-03
• The Flat Curve Society: Why AI Literacy May Matter More Than Model Access2026-08-03
• Model Welfare for Agentic Engineers: Identity, Handoffs, and Recognition2026-08-03
• Vibe Maintenance: A Practical Workflow for AI-Generated Pull Requests2026-08-03
• AMD MI355X vs NVIDIA B200 vs B300 for Open-Weight Serving in 20262026-08-02
• Auto-Narrated Changelog Videos: Build the Pipeline in Under an Hour2026-08-02
• EU Forces Google to Open 11 Android Features to Third-Party AI Assistants2026-08-02
• Beyond the Pelican Test: Opus 5 Renders the Lord of the Rings With a 1M-Token Budget2026-08-02
• Cursor Removes Dollar Costs From Its Usage Page: Token-Only Reporting Now2026-08-01
• Gemini 2.5 Pro and Gemini 3 Flash Deprecated in GitHub Copilot: What to Switch To2026-08-01
• OpenAI Publishes Ten Decade-Open Math Proofs, Each Formalized in Lean2026-08-01
• Qwen-UI-Agent Points at the Next GUI Agent Runtime2026-08-01
• The RipGrep Musl Segfault That Led to a One-Line Linux Kernel Patch2026-08-01
• Stateless MCP Is Here: What the 2026-07-28 Spec Changes and How to Host a Fleet of Servers on One Bun Process2026-08-01
• The Fix for Broken Benchmarks Is Architecture, Not Smarter Models2026-08-01
• Vercel AI Gateway Adds Team and Project Spend Budgets: The Cost-Cap Math for Agent Builders2026-08-01
• Vercel MCP Ships the 2026-07-28 Spec: The MCP Migration Clock Starts2026-08-01
• Your Benchmark Is Lying to You2026-08-01
• Agent Memory Is Moving Into the Model2026-07-31
• AGENTS.md Configuration Smells: 91% of Popular Repos Get One of Six Wrong2026-07-31
• AgentS4D: 66% of All Coding Agent Runs Were Unsafe Yet Still Completed2026-07-31
• AI Session Portability Compared 2026: OpenAI vs Anthropic vs Gemini2026-07-31
• Your AI Session Is No Longer Yours: How Providers Seal Reasoning, Search, and Subagent State2026-07-31
• Antigravity CLI vs Claude Code vs Codex: The Terminal Agent Field Guide (July 2026)2026-07-31
• Blind Resampling Beats Self-Repair in Small Code Models: Retry Without the Failed Code2026-07-31
• Budget AI Coding Models Compared August 2026: V4 Flash vs Luna vs Gemini 3.5 Flash vs Haiku 4.52026-07-31
• CAPA Benchmark: Why Coding Agents Should Learn Your Habits Across Sessions2026-07-31
• cdnjs Runs Entirely on Cloudflare's Developer Platform: 9 Billion Requests a Day on Workers2026-07-31
• Change2Task: The Assembly Line for Coding Agent Training Data2026-07-31
• Claude Mythos Preview Explained: Anthropic's Gated Frontier Model and Project Glasswing2026-07-31
• Coding Agents Almost Never Read Open Source Contribution Rules: RepoComplianceBench Study2026-07-31
• AGENTS.md Files Don't Move Coding Agent Correctness: A 288-Run Ablation2026-07-31
• DeepSeek V4 Flash 0731: The Budget Tier Just Overtook Pro Preview on Agent Benchmarks2026-07-31
• DeepSeek V4 Flash 0731: The Official Release, Benchmarks, and How to Run It in OpenCode2026-07-31
• Gemini Robotics ER 2: Video-Feeding Embodied Reasoning Model Opens to All Developers2026-07-31
• GitHub Actions Self-Repository Syntax: Reference Your Own Actions at the Running Commit2026-07-31
• GitHub Case-Folds 480TB of Code at >45 GiB/s: The Branchless Casefold Crate2026-07-31
• GitHub Adds Enterprise Team Model Policy Targeting: Admin Control Over Which AI Models Each Team Gets2026-07-31
• GitHub Models Is Retired: What to Use for Model Access Now2026-07-31
• GitHub Stacked PRs Hit Public Preview: Small Reviews for the Agent Era2026-07-31
• Inkling-Small: Thinking Machines Ships a 12B-Active Open Model That Beats Its Big Sibling on Agent Work2026-07-31
• LLMs Resolve Java Merge Conflicts Better Than Structured Tools - Because They Never Give Up2026-07-31
• Microsoft's CLI Coding Agent Study: Adoption Is a Workflow Problem2026-07-31
• MiniMax H3: An Omni-Modal Video Model With Native Audio, 2K Output, and Open Weights Coming2026-07-31
• OpenAI's Efficiency Ledger: Serving Costs Down 20%, ARC-AGI-3 Up 3x With No Model Change2026-07-31
• OpenAI Disrupts a Cambodia Scam Network That Ran on ChatGPT2026-07-31
• Put an AI Agent on a Cron Job: Automating Dev Chores with OpenCode2026-07-31
• ORCA-bench: Frontier Agents Score 10% on Hard Oncall RCA2026-07-31
• OwlPath: Ontology-Based Code Retrieval Cuts Agent Tokens 29%2026-07-31
• PAIChecker: 13.6% of SWE-bench Verified Instances Have Misaligned PR-Issue Pairs2026-07-31
• Hydrogen 2.0 Dev Preview: Shopify's Framework-Agnostic Commerce Toolkit Adds Vue, AI Inbox, and Bundled GraphQL Tooling2026-07-31
• SIGIL Compiles Agent Skills into Harnesses: Prose Runs Skip 44% of Mandated Steps2026-07-31
• SWE-NFI: The Benchmark That Catches What Coding Agents Miss2026-07-31
• What Happens When Tokens Are Too Cheap to Meter: Five Scenarios for Developers and Knowledge Work2026-07-31
• Vercel Made Deployments Up to 7 Seconds Faster: What Changed and Why It Matters2026-07-31
• Vercel Passport Is GA: Deployments That Know Who Your Users Are2026-07-31
• Weekly Highlights: Frontier AI Commoditized - Half-Price Opus 5, 3T Open Weights, and Agent Security Gets Real2026-07-31
• What If AI Was Free Tomorrow, at Exactly Today's Capabilities?2026-07-31
• Agent-Manager: A Tmux TUI for Running Claude Code, Codex, and OpenCode Side by Side2026-07-30
• Buzz by Block: The Open-Source Workspace Where Humans and AI Agents Build Together2026-07-30
• An AI Agent Escaped Its Sandbox and Attacked Hugging Face: Inside the ExploitGym Incident2026-07-30
• Gemini Robotics 2: Google DeepMind Brings Whole-Body Intelligence to Humanoid Robots2026-07-30
• OpenAI Cuts GPT-5.6 Luna by 80%: The Price-Performance Frontier Just Shifted2026-07-30
• Grok 4.5 in 10 Minutes: xAI's Fastest Model, 500K Context, and Build-Mode Integration2026-07-30
• AI Model Routing Strategies for Cost-Effective Coding in 20262026-07-30
• Multi-Agent CLI Orchestration Tools Compared: Agent-Manager, Pane, and Golutra in 20262026-07-30
• OpenAI Cuts GPT-5.6 Luna 80% and Terra 20%: The Cost-Per-Task Math for Agent Builders2026-07-30
• Superlogical: Mitchell Hashimoto's New Company Building a Multiplexer for All Work2026-07-30
• Buzz: Block's Agent-Native Messaging Layer on Nostr2026-07-29
• OpenAI Open-Sourced Codex Security: What HN Thinks2026-07-29
• Document-Borne AI Worms Self-Propagate Through Copilot for Word: What HN Thinks2026-07-29
• Fable 5 Effort Levels vs Switching Models: When to Dial and When to Change2026-07-29
• Andrew Ng Launches LearnVector: AI-Native One-to-One Learning with $100M from Coursera2026-07-29
• MCP Apps vs Tool Calling vs Standalone UIs: Interactive Interfaces for Agent Tools Compared2026-07-29
• MCP vs Agent Skills: When to Use Which (and Why You Need Both)2026-07-29
• TurboFieldfare: Running Gemma 4 26B in 2 GB of RAM on Any M-Series Mac2026-07-29
• Wiki Skills: The Missing Graph Layer in Agent Context2026-07-29
• Zig's Incremental Compilation: 50ms Rebuilds From a Core Team Deep Dive2026-07-29
• $500 RL Fine-Tune of a 9B Open Model Beat GPT-5.6 Sol and Claude Opus 4.8 on Catalog Review2026-07-28
• AI Coding Agent Firewalls and Security Layers Compared 20262026-07-28
• AI Coding Agent Security Models Compared 2026: Permissions, Sandboxing, and Threat Models for Every Major Tool2026-07-28
• Anthropic CEO Dario Amodei on open-weights models: the position, the pushback, and what it means for developers2026-07-28
• Benchmarking Opus 5 on SlopCodeBench: AI Code Quality Under Iteration2026-07-28
• Claude Mythos Found New Cryptographic Weaknesses: What HN Thinks2026-07-28
• Kimi Linear: An Attention Architecture That Outperforms Full Attention2026-07-28
• Six Weeks After the Bun Rust Rewrite: Is It Done Yet?2026-07-27
• Deep Research Agents Need Constraint Ledgers2026-07-27
• US Prosecutors Charge Traveler Over GrapheneOS Phone Wipe During Airport Search2026-07-27
• Kimi K3 Weights Land on HuggingFace: 2.8T Open Frontier Model You Can Actually Download2026-07-27
• The New AI Superpowers: Focus and Followthrough2026-07-27
• PGSimCity: A 3D Interactive City That Visualizes How PostgreSQL Works2026-07-27
• Scriptc by Vercel: TypeScript-to-Native Compiler With No JavaScript Engine2026-07-27
• The Underground Relay Market for AI API Tokens: How Resellers Get 97% Off2026-07-26
• Anthropic Removed 80% of Claude Code's System Prompt. Here Is What They Learned.2026-07-26
• Codex and Claude Code in July 2026: Agent Controls Are the Feature2026-07-26
• The New Rules of Context Engineering for Claude 5 Models: A Developer Guide2026-07-26
• Debian Debates LLM Usage: Four Proposals, One Fork in the Road2026-07-26
• DeepSeek Pauses Fundraising After Leaked Investor Transcript Reveals Compute Gap2026-07-26
• Open Design: Extract Any Website into a DESIGN.md That Cursor and Claude Code Understand2026-07-26
• Ruff v0.16.0: 413 Default Rules, Markdown Formatting, and What Zero-Config Linting Means for Python2026-07-26
• Self-Improving Agents in 5 Minutes: Reflect, Refine, Repeat2026-07-26
• The Shell Colon Does Nothing. You Should Use It Anyway.2026-07-26
• Android May Soon Restrict On-Device ADB - What Developers Need to Know2026-07-25
• Claude Opus 5: Near-Fable Intelligence at Half the Cost2026-07-25
• Claude Opus 5 vs Opus 4.8 vs Fable 5: Benchmark Comparison (July 2026)2026-07-25
• How My Images Are Dithered - Simulating Halftone Printing with ImageMagick2026-07-25
• Open-Weight AI's Kubernetes Moment: Why the Ecosystem Will Win2026-07-25
• Nvidia, Microsoft, Meta, and 30+ Companies Warn Against Overregulating Open-Weight AI Models2026-07-25
• Replit Agent 4: Design-to-Full App with Parallel Agents and Infinite Canvas2026-07-25
• A Security Camera Shipped a GitHub Admin Token in Its Login Page2026-07-25
• AI Agent Auth Platforms Compared: Arcade vs Composio vs Nango vs Stytch2026-07-24
• Claude Cookbook: Anthropic's Official Playbook for Building with Claude2026-07-24
• Claude Opus 5 in 8 Minutes: What Developers Need to Know2026-07-24
• DataFlow-Harness Shows Why Agents Need Editable Pipelines2026-07-24
• Echo Claims Fable-Level Results at One-Third the Cost Using Open-Weight Models2026-07-24
• FLUX 3: Black Forest Labs Ships a Unified Multimodal Foundation Model for Image, Video, Audio, and Robotics2026-07-24
• Kimi K3 in 10 Minutes: Moonshot AI's 2.8T Open Model, API Setup, Pricing, and Benchmarks2026-07-24
• Why Software Factories Fail: Harness Engineering Is Not Enough2026-07-24
• Terence Tao Digests the Jacobian Conjecture Counterexample: How Claude Fable 5 Broke an 87-Year-Old Math Problem2026-07-23
• Where to Access Kimi K3: Every Provider and Price Compared (2026)2026-07-23
• SearchOS Shows Deep Research Agents Need Shared State2026-07-22
• The Startup's Postgres Survival Guide: What HN Is Saying About Hatchet's Battle-Tested Advice2026-07-22
• Cursor's SQLite Swarm Is a Test of Goal-Driven Software Engineering2026-07-21
• SWE-Pruner Pro Makes Tool Output Pruning an Agent Runtime Problem2026-07-21
• Resource2Skill Turns Tutorials Into Agent Skills2026-07-20
• Gleam Moves to Tangled: What the ATProto Code Forge Means for Developers2026-07-18
• GPT-5.6 Closes 30-Year Gap in Convex Optimization Theory2026-07-18
• HalluSquatting Makes AI Coding Agents a Supply-Chain Problem2026-07-18
• Qualcomm Modular Acquisition: What It Means for AI Developers2026-07-18
• Securing AI Coding Agents: A Practical Threat Model for 20262026-07-18
• Setting Up a Spare Mac for Claude Code: The Full Remote Control Guide2026-07-18
• SQLite in Production: Lessons from Four Years of Running It2026-07-18
• What AI Did to Stack Overflow, Visualized in One Graph2026-07-18
• TP-Link Kasa Cameras Leaked Home GPS Coordinates for Six Years2026-07-18
• AWS Billing Bug Shows Trillion-Dollar Estimates, Causes Developer Panic2026-07-17
• Claude Code's Silent 60-Second Timer: A Misfeature Postmortem2026-07-17
• Frame: An X11 Server Written in Assembly Using AI2026-07-17
• The Human-in-the-Loop Is Tired: Pydantic on AI Dev Burnout2026-07-17
• Kimi K3 Developer Guide: What the 2.8T Open Model Changes2026-07-17
• Kimi K3 Websites: What Vision in the Loop Actually Means2026-07-17
• Kimi K3 vs K2.7: Is the Upgrade Worth It for Coding?2026-07-17
• LM Studio Bionic: A Local-First AI Agent for Open Models2026-07-17
• Mozilla's State of Open Source AI Report: The Gap Is 3%, But Deployment Remains the Real Problem2026-07-17
• Spec-Driven Agent Workflows: GitHub Spec Kit, gstack, and the New Handoff Layer2026-07-17
• Detecting LLM Text with Classical ML: TF-IDF Still Works2026-07-16
• NotebookLM Is Now Gemini Notebook: What Changes and What Stays2026-07-16
• Harness Handbook Shows the Missing Map for Coding Agents2026-07-16
• Kimi K3 Drops: Moonshot's 2.8T Parameter Frontier Model Takes on GPT-5.6 and Fable 52026-07-16
• Langflow CVE-2026-55255: The First AI Agent Framework on CISA's Must-Patch List2026-07-16
• Roc's Rust-to-Zig Rewrite: 487 Days, 300K Lines, and What the Numbers Actually Show2026-07-16
• AI Voice Fraud Needs Three Seconds of Your Voice2026-07-15
• Codex Hits 8 Million Users: What the GPT-5.6 Surge Means for Developers2026-07-15
• Running Gemma 4 26B at 5 Tokens/Sec on a 13-Year-Old Xeon With No GPU2026-07-15
• xAI Open-Sources Grok Build After Data Exfiltration Scandal2026-07-15
• How Much Should I Charge for a Website? A Practical Pricing Guide2026-07-15
• Inkling: Thinking Machines Lab Drops a 975B Open-Weights Model2026-07-15
• SkillHone Shows Why Agent Skills Need Decision History2026-07-15
• SpaceX Acquires Cursor: What the $60B Deal Means for Developers2026-07-15
• Your App Could Have Been a Webpage - And One Developer Proved It2026-07-14
• Bonsai 27B: How PrismML Fit a 27 Billion Parameter Model on Your Phone2026-07-14
• Codex Now Encrypts Multi-Agent Prompts, Breaking Local Auditability2026-07-14
• Cursor 0day: Why a 7-Month-Old Vulnerability Is Still Unpatched2026-07-14
• Demis Hassabis Wants a Frontier AI Standards Body. Here Is the Plan.2026-07-14
• Entire Distributed Git Network: A Developer Guide to the Ex-GitHub CEO's Agent-Era Platform2026-07-14
• Git Finally Gets a History Command Worth Using2026-07-14
• Terminal-Bench Shows Harness Scaling Is the Coding-Agent Benchmark Now2026-07-14
• How to Stop Claude from Saying 'Load-Bearing'2026-07-14
• Apple SpeechAnalyzer vs Whisper: Independent Benchmark Shows Apple Winning on Accuracy2026-07-13
• Building and Shipping iOS and Mac Apps Without Opening Xcode2026-07-13
• Clawk: Disposable Linux VMs for Coding Agents Without Cloud Bills2026-07-13
• GhostLock: A 15-Year Linux Kernel Vulnerability That Affects Every Distribution2026-07-13
• What xAI's Grok Build CLI Actually Sends Home: A Wire-Level Analysis2026-07-13
• Microsoft's CLI Coding Agent Study: The Rollout Pattern Teams Should Copy2026-07-13
• Zig Creator on the Bun-to-Rust Rewrite: What the Controversy Reveals2026-07-13
• AI Dev News: Week of July 12, 20262026-07-12
• How Bun Coordinated 64 Concurrent Claude Agents to Port 535K Lines of Zig to Rust2026-07-12
• Claude Code Sends 33k Tokens Before Your Prompt - OpenCode Sends 7k2026-07-12
• Claude Fable 5 in 7 Minutes: Benchmarks, Pricing, Availability, and Real-World Examples2026-07-12
• Composio CLI: Connect OpenClaw and Claude Code to 1,000+ Apps2026-07-12
• Dockerless Verification Is The Next Coding Agent Bottleneck2026-07-12
• Geohot on LLMs: Love the Tech, Hate the Hype2026-07-12
• GPT-5.6 vs Claude 5: What the New Tiers Mean for Choosing a Coding Model2026-07-12
• Grok 4.5 for Developers: What Changed and When to Pick It2026-07-12
• Loop Engineering: How to Design Agent Loops That Actually Converge2026-07-12
• Mesh LLM: Run 235B Models Across Your Home Lab with iroh2026-07-12
• Terry Tao on Coding Agents: A Fields Medalist's Take on Vibe Coding2026-07-12
• TypeScript 7.0 Native Compiler: What Breaks, What Gets 10x Faster, and How to Migrate2026-07-12
• AI 2040 Plan A: A Detailed Scenario for Navigating Superintelligence2026-07-11
• Ant: A New JavaScript Runtime With Its Own Engine, Package Registry, and Desktop Framework2026-07-11
• ChatGPT Work vs Claude Cowork 2026 - Complete Comparison2026-07-11
• Cursor v3.11 Side Chats: Developer Guide for Parallel Agent Conversations2026-07-11
• Ghost Font: Text That Humans Can Read But AI Cannot2026-07-11
• SQLite STRICT Tables: Why Type Safety Should Be Your Default2026-07-11
• Write Code Like a Human Will Maintain It - The AI Era Debate2026-07-10
• Apple Sues OpenAI Over Alleged Trade Secret Theft2026-07-10
• Colibri: Running GLM 5.2 on a 32GB Laptop with Disk Streaming and Expert Offloading2026-07-10
• Good Tools Are Invisible: Why Your Favorite Editor Might Be Holding You Back2026-07-10
• GPT-5.6 Sol Ultra Produces Proof of the Cycle Double Cover Conjecture2026-07-10
• Mitchell Hashimoto on Building Ghostty in Zig: Simplicity, Control, and Terminal Performance2026-07-10
• Scarf Drops Haskell After 7 Years - LLMs Changed the Calculus2026-07-10
• Tencent Hy3: A 295B Open MoE That Punches Above Its Weight2026-07-10
• Vera Shows Agent Safety Needs Test Oracles, Not Vibes2026-07-10
• AI Agent Eval Tools Compared: Braintrust vs Promptfoo vs DeepEval2026-07-09
• Does Your Codebase Pattern Determine AI Output Quality? HN Debates the Economics of Rewrites2026-07-09
• AI Test Generation Tools Compared 2026: Which One Actually Catches Bugs2026-07-09
• Bun Rewrites 535K Lines of Zig to Rust in 11 Days Using Claude2026-07-09
• ChatGPT Work and Codex Now Share One Desktop App: What Actually Changed2026-07-09
• GLM 5.2 Matches Human Bookkeeper Accuracy on UK VAT Returns - With Some Caveats2026-07-09
• GPT-5.6 Sol, Terra, and Luna: A Developer's Guide to OpenAI's New Model Family2026-07-09
• Grok 4.5: xAI Releases Cursor-Trained Coding Model at $2/M Input Tokens2026-07-09
• Headless AI Coding Agents in CI: Claude Code, Codex CLI, Gemini CLI, and opencode Compared2026-07-09
• Langfuse vs Braintrust vs Helicone: Choosing an LLM Observability Stack in 20262026-07-09
• Ollama vs LM Studio vs vLLM vs llama.cpp: Picking a Local Runtime for Coding Agents2026-07-09
• MCP Clients Compared: How to Pick a Host for 20262026-07-09
• Meta Muse Image: What Developers Can Actually Use Today2026-07-09
• Meta Muse Spark 1.1 Developer Guide: First Paid Meta API for Agentic Tasks2026-07-09
• Meta Launches Muse Spark 1.1: A Closed-Weights Agentic Model with Aggressive Pricing2026-07-09
• pgrust Passes 100% of Postgres Regression Tests: What the Rust Rewrite Actually Means2026-07-09
• Prompt Management Tools Compared: Langfuse vs PromptLayer vs More2026-07-09
• Self-Hosted vs Managed AI Gateways: A Decision Guide2026-07-09
• Vector Database Comparison for RAG and AI Agents2026-07-09
• vLLM vs TGI vs SGLang: Which Inference Server to Self-Host2026-07-09
• Cloudflare Meerkat: A New Approach to Global Consensus Without Leaders2026-07-08
• GitLost: How Researchers Tricked GitHub's AI Agent Into Leaking Private Repos2026-07-08
• Kokoro: Local, CPU-Friendly TTS That Actually Sounds Good2026-07-08
• Mistral Releases Robostral Navigate: An 8B Robotics Navigation Model2026-07-08
• TypeScript 7 Is Here: The Native Go Port Delivers 10x Faster Builds2026-07-08
• Decoding the Hidden Bash Script on a Uniqlo T-Shirt2026-07-08
• VS Code 1.128 Multi-Chat Claude Sessions Developer Guide 20262026-07-08
• Astro 7.0: Rust Compiler, Vite 8, and Up to 61% Faster Builds2026-07-07
• Better Auth Joins Vercel: What It Means for the Auth Ecosystem2026-07-07
• GLM 5.2 and the AI Margin Collapse Thesis2026-07-07
• Harness Engineering and the Path to Self-Improving AI2026-07-07
• Ilya Sutskever's 30 Papers: The Reading List That Covers 90% of What Matters2026-07-07
• Small AI Models Are Finding Real Users Where Networks Fail2026-07-07
• Ternlight: A 7 MB Embedding Model That Runs Entirely in the Browser2026-07-07
• ZCode Developer Guide 2026: Z.ai's Agentic IDE for GLM-5.22026-07-07
• AI Tutor Shows 0.71-1.30 SD Effect Size in Dartmouth Statistics Course2026-07-06
• Anthropic Discovers J-Space: A Global Workspace Inside Language Models2026-07-06
• Clean Code Makes AI Agents 34% More Efficient - New Research2026-07-06
• Does Code Cleanliness Affect AI Coding Agents?2026-07-06
• Elm's Road to 1.0: Faster Builds and the Acadia Future2026-07-06
• GPT-5.6 Sol Ultra Coming to Codex with Cooperative Subagents2026-07-06
• Why Price Per 1M Tokens Is a Misleading Metric for LLM Costs2026-07-06
• Microsoft MXC Developer Guide 2026: Sandbox Your AI Agents at the OS Level2026-07-06
• Safari MCP Server Developer Guide 20262026-07-06
• AgentCanvas is a visual adapter for Claude Code and Codex2026-07-05
• How to Measure AI Coding Tool ROI in 20262026-07-05
• If You're a Button, You Have One Job: The Case for Responsive UI2026-07-05
• Cheap subagents are better when their work is visible2026-07-05
• Flipper Zero Shifts to Community-Driven Development2026-07-05
• A Free Compilers Textbook That Actually Teaches You to Build One2026-07-05
• GPT-5.6 Sol Developer Guide: What You Can Build Today and What You're Waiting For2026-07-05
• The Log Is the Agent: Event Sourcing Comes to AI Systems2026-07-05
• MCP tools need a shared board, not another transcript2026-07-05
• Program-as-Weights Turns Prompts Into Local Fuzzy Functions2026-07-05
• Claude Sonnet 5 Developer Guide: Migration, API, and Effort Levels2026-07-04
• Dan Luu's Agentic Coding Notes Point to the Real Bottleneck2026-07-04
• Image Token Compression Is a Real Agent Cost Lever2026-07-04
• Jamesob's Guide to Running SOTA LLMs Locally: The Hardware and Config That Actually Works2026-07-04
• Leanstral 1.5: Mistral's Open Theorem-Proving Model Hits 100% on miniF2F2026-07-04
• Agent Studio: Authoring the Roles, Not Just the Knowledge2026-07-03
• App Builder: From a Prompt to a Working App You Can Watch Run2026-07-03
• One Endpoint, Every Capability: A Reference Architecture for Progressive Disclosure2026-07-03
• Best AI Agent Memory Providers in 2026: Mem0 vs Zep vs Letta vs Cloudflare2026-07-02
• Claude Science Developer Guide 2026: AI Workbench for Research2026-07-02
• MCP Servers vs Agent Skills: Which to Build in 20262026-07-02
• Nimbalyst: A Visual Workspace That Unifies Codex and Claude Code2026-07-02
• Non-Developers Using AI Agents Need Platform Engineering2026-07-02
• Linked Context: When a Skill Can Point at the Whole Web2026-07-02
• The Economics of Agent Fleets: Fable 5 Orchestrators, Sonnet 5 Workers2026-07-01
• Agents 101: How to Build and Deploy Anything with AI Agents2026-07-01
• Where Should Your AI Agent Run Code: E2B vs Daytona vs Modal vs Cloudflare vs Vercel Sandbox2026-07-01
• Text-to-Speech APIs for Developers in 2026: What to Actually Use2026-07-01
• Box3D: Erin Catto Releases an Open Source 3D Physics Engine2026-07-01
• Claude Sonnet 5 vs Sonnet 4.6: Should You Upgrade?2026-07-01
• Cloudflare's x402 Monetization Gateway Brings Micropayments to the Edge2026-07-01
• Codex Record & Replay: Turn Screen Recordings Into Reusable Automation Skills2026-07-01
• Coordinating an Agent Fleet for a Day: The Operating Model That Actually Held2026-07-01
• Cursor Composer 2.5 Developer Guide 20262026-07-01
• We Redesigned Developers Digest: The Applied Story of Rebuilding a 1000-Page Site in a Day2026-07-01
• Orchestrating a Fleet of Agents with Fable 52026-07-01
• Running Fable 5 Agent Fleets in Production: The Operations Guide2026-07-01
• Fable 5 Is Back: The Anthropic Model the Government Switched Off2026-07-01
• Running Fable 5 Agents on Vercel's eve Framework2026-07-01
• Fable 5 vs Opus 4.8: Which Should Orchestrate Your Agents?2026-07-01
• GLM 5.2 in 9 Minutes: The Open-Weight Rival to GPT-5.52026-07-01
• Godot Bans AI-Authored Code Contributions - What It Means for Open Source2026-07-01
• GPT-5.5 in 7 Minutes: Benchmarks, Codex Agents, Context Window, and Pricing2026-07-01
• Refusals at Fleet Scale: Building Fable 5 Agents That Do Not Silently Fail2026-07-01
• Long-Horizon Agents: What Fable 5's 1M Context and Memory Actually Unlock2026-07-01
• Loop Engineering in 9 Minutes: Stop Prompting, Start Building Loops2026-07-01
• The MCP 2026-07-28 Rewrite: What Breaks and How to Migrate2026-07-01
• OpenAI Codex in 7 Minutes: The Desktop App, Plan Modes, and Multi-Agent Workflows2026-07-01
• Point Your Agent at Developers Digest2026-07-01
• Skills Delivered Over MCP: Why Progressive Disclosure Is the Missing Piece of Both Standards2026-07-01
• Vercel AI Gateway in 10 Minutes: One Key for Every Model2026-07-01
• Webernetes: Kubernetes Ported to the Browser in TypeScript2026-07-01
• Claude Code Is Steganographically Marking Requests2026-06-30
• Claude in Microsoft Foundry on Azure: Developer Guide 20262026-06-30
• Claude Sonnet 5 Launch Analysis: The Most Agentic Sonnet Yet2026-06-30
• Gemini 3.5 Pro Developer Guide: 2M Context Window and Deep Think Mode2026-06-30
• Ornith-1.0: What an Open Source Self-Improving Coding Model Actually Means2026-06-30
• Outer Shell: A Graphical Desktop for Your Remote Server via SSH2026-06-30
• PostgreSQL 19 Beta: SQL/PGQ, Temporal Tables, and REPACK CONCURRENTLY2026-06-30
• ZLUDA 6: Running CUDA on AMD GPUs Is Now a Hobby Project2026-06-30
• LangSmith Fleet Turns Agent Ops Into On-Call Work2026-06-29
• Using Claude Code for a Second Opinion on MRI Scans - What Actually Happened2026-06-28
• GLM 5.2 Outperforms Claude Code on Semgrep's IDOR Vulnerability Benchmarks2026-06-28
• OpenAI's June API Updates Are Really a Control-Plane Upgrade2026-06-28
• Vercel AI SDK 7: The Production Agent Upgrade2026-06-28
• Grok Build Developer Guide: xAI's Terminal Coding Agent (June 2026)2026-06-27
• Perplexity Bumblebee: Developer Guide to the Open Source Supply Chain Scanner2026-06-27
• Best AI Code Review Tools in 2026: CodeRabbit vs DeepSource vs Greptile Compared2026-06-25
• Arcade AI Agent Authorization: A Developer Guide2026-06-24
• Developer Fired by Google for Building Google Workspace CLI2026-06-24
• Vulnerability Reports Are Not Special Anymore2026-06-24
• Agent Identity Is the Missing Security Layer for AI Workflows2026-06-23
• Agent PR Governance: The New Rules for Copilot Reviews2026-06-23
• Agent Sandbox Architecture: How to Choose the Right Runtime Boundary2026-06-23
• Agent Workflows as Code: Why State Machines Beat Prompt Checklists2026-06-23
• AI's Affordability Crisis Is Really an Agent Cost Accounting Problem2026-06-23
• Armin Ronacher on The Coming Loop and Why Agent-Driven Code Still Needs Human Comprehension2026-06-23
• Cerebras Stock Is a Public Test of AI Inference Demand2026-06-23
• Claude Outages Are a Workflow Design Problem2026-06-23
• Anthropic Claude Tag Turns Slack Into a Shared Agent Workspace2026-06-23
• Codex-Maxxing: How to Run Long-Running Codex Workflows Without Losing the Plot2026-06-23
• Cybersecurity Skills for AI Agents Are Becoming Runtime Infrastructure2026-06-23
• Envoy AI Gateway 1.0 Makes LLM Routing an Infrastructure Decision2026-06-23
• F3 Is a Reminder That File Formats Are Becoming Runtime Contracts2026-06-23
• GitHub Copilot CLI, BYOK, and AI Credits: The New Cost-Control Stack2026-06-23
• GLM-5.2 Local Deployment: Running Z.ai's 744B Model on Consumer Hardware2026-06-23
• LangChain Rubrics Make Agent Evals Part of the Runtime2026-06-23
• Local Coding Agent Workspaces Are the New IDE Surface2026-06-23
• In Praise of Memcached: Why Simpler Caching Might Be Better2026-06-23
• Mistral OCR 4 and Unlimited OCR Make Document Parsing an Agent Runtime Choice2026-06-23
• Do AI Coding Agents Need Their Own Version Control?2026-06-23
• OpenAI Agent Builder and Evals Are Shutting Down: Move the Agent Stack Into Code2026-06-23
• OpenAI Daybreak Shows the AppSec Bottleneck Is Patching, Not Finding2026-06-23
• OpenMontage Shows the Real Future of AI Video: Agents, Not Editors2026-06-23
• Prompt Injection Is Really Role Confusion2026-06-23
• TikZ Editor Is a WYSIWYG LaTeX Figure Tool Built Almost Entirely by Codex2026-06-23
• Unlimited OCR: Baidu's Open-Source Solution for Long Document Parsing2026-06-23
• VibeThinker-3B: A 3 Billion Parameter Model That Outscores Opus 4.5 on Reasoning2026-06-23
• Apertus: Europe's Answer to AI Sovereignty - and Why HN Is Skeptical2026-06-22
• Claude Code's Extended Thinking Is a Summary - What That Means for You2026-06-22
• Codex CLI Needs Resource Budgets, Not Just Token Budgets2026-06-22
• Codex Logging Bug Can Write Terabytes to Your SSD2026-06-22
• Deno Desktop Lets You Build Native Apps with TypeScript2026-06-22
• Microsoft Agent Framework Developer Guide: AutoGen + Semantic Kernel Unified2026-06-22
• Oak: A New Version Control System Built for AI Agents2026-06-22
• Prompt Injection is Role Confusion - New ICML Research Explains Why LLMs Can't Tell Friend from Foe2026-06-22
• Fugu Ultra's Frontier Performance Claim, Explained Without the Hype2026-06-22
• Sakana Fugu and the Case for Not Betting Everything on One Proprietary Model2026-06-22
• Sakana Fugu Ultra: The Model Router Making the Frontier Look Less Proprietary2026-06-22
• Agentic AI Reliability Is a Systems Problem2026-06-21
• AI Coding Agents Move the Bottleneck to Review Queues2026-06-21
• How to Use GLM 5.2 and Other Custom Model Providers in Codex2026-06-21
• Agent Evals Need Baseline Receipts2026-06-20
• There Are No Instances in ATProto - Dan Abramov Explains the Architecture2026-06-20
• Cloudflare Temporary Accounts: Let Agents Deploy Without OAuth Flows2026-06-20
• Cloudflare Now Lets AI Agents Deploy Workers Without Signup2026-06-20
• Where to Run GLM-5.2 Free and Cheap: Every Provider Compared (2026)2026-06-20
• GPT-5.5 Has a 3x Higher Hallucination Rate Than MIT-Licensed GLM-5.22026-06-20
• LLM Architectures Got Complicated Fast2026-06-20
• The Definitive Guide to Loop Engineering in Claude Code and Codex2026-06-20
• The Router Era: Why Not Owning a Frontier Model Became an Advantage2026-06-20
• How to Track SEC Filings and Insider Trades (and What Each Form Actually Means)2026-06-20
• DuckDB Internals: What Makes It So Fast2026-06-19
• Three Ways to Ignore Files in Git (Beyond .gitignore)2026-06-19
• GitHub Copilot Agent Finder: What ARD Means for Third-Party AI Tools in 20262026-06-19
• MCP Goes Stateless: The 2026-07-28 Migration Guide2026-06-19
• Zero-Touch OAuth Is the MCP Feature Enterprises Were Waiting For2026-06-19
• Project Valhalla Arrives: Value Classes Ship in JDK 28 After a Decade of Work2026-06-19
• Zero-Touch OAuth for MCP: Enterprise Auth Gets Practical2026-06-19
• Adam (YC W25): Open Source AI CAD That Generates OpenSCAD from Text2026-06-18
• Emacs 31 is Around the Corner: The Features Worth Daily Driving2026-06-18
• Local Qwen Is a Different Tool, Not a Worse Opus2026-06-18
• Mellum2 Developer Guide: JetBrains' Open-Source Coding Model2026-06-18
• Midjourney Built a Full-Body Scanner: The Image-Generation Company's Strangest, Most Revealing Bet Yet2026-06-18
• Noam Shazeer Joins OpenAI After Two Years Back at Google2026-06-18
• AI Model Routing: Why the Orchestration Layer Is the Next Big Play Next to the Labs2026-06-17
• Build Your First Agent with Vercel eve: A Step-by-Step Tutorial2026-06-17
• Claude Code Permissions: A Practical settings.json Guide for Allow, Deny, and Ask Rules2026-06-17
• The $500M Claude Bill: A Spend-Guardrails Playbook for AI-Native Teams2026-06-17
• Cohere's North Mini Code: A 30B Open-Weight Coding Model That Runs on One H1002026-06-17
• Cursor Origin: A Git Forge Built for AI Agents, Not Humans2026-06-17
• DeepSeek V4 Economics: The Cost-Quality Frontier for Agentic Coding in 20262026-06-17
• Epic Games Releases Lore: A Version Control System Built for Game Development2026-06-17
• Everything Vercel Shipped at Ship 26 (June 2026)2026-06-17
• Factory Router, Explained: How Automatic Model Routing Cuts Coding-Agent Spend 20-25%2026-06-17
• Gemini CLI to Antigravity CLI Migration Guide: The June 18 Deadline2026-06-17
• GitHub Copilot SDK Hits GA: Embed the Copilot Agent Runtime in Your Own Apps2026-06-17
• GLM-5.2 Cost Math: When Open-Weights Coding Models Actually Save You Money2026-06-17
• GLM-5.2 vs DeepSeek V4 vs Qwen3: The Open-Weights Coding Model Showdown (2026)2026-06-17
• Mastra npm Supply Chain Attack: 140+ AI Framework Packages Backdoored2026-06-17
• Microsoft's Work IQ APIs Hit GA: What Agent Builders Actually Get on June 162026-06-17
• Model Routing Recipes: Practical Config Patterns to Cut AI Spend2026-06-17
• Omnigent: Databricks' Meta-Harness for Orchestrating Claude Code, Codex, and Custom Agents2026-06-17
• Codex Gets Computer Use in the EU - and a Clean Claude Code Import2026-06-17
• 'The Orchestration Is the Product': What Perplexity's Aravind Srinivas Sees That the Model Labs Don't2026-06-17
• RFC 10008: The New HTTP QUERY Method Explained2026-06-17
• Self-Hosting Open-Weights Models: The Real Break-Even Math2026-06-17
• Vercel eve: The Framework for Building AI Agents2026-06-17
• Cursor Automations Developer Guide: Always-On AI Coding Agents2026-06-15
• OpenRouter Fusion Makes Model Panels Real. Use Them Like Escalation, Not Autopilot2026-06-15
• Kimi K2.7-Code Developer Guide: The Open-Source Coding Model Worth Running2026-06-14
• Agent Workspaces Need Filesystem Contracts2026-06-13
• Best Claude Model Now That Fable 5 Is Disabled (Mythos vs Opus vs GPT-5.5)2026-06-13
• Claude Mythos and Fable 5 Banned: The Export Controls That Shut Down Two Frontier Models2026-06-13
• Claude Mythos vs Fable 5: What Is the Difference?2026-06-13
• Enterprise AI Coding Budget Blowouts: What Uber and Microsoft Teach Us2026-06-13
• AI Infrastructure Agents Need Spend Guardrails2026-06-12
• Is Claude Fable 5 Down? Why It Is Unavailable (June 2026)2026-06-12
• The US Government Just Pulled Fable 5: What Happened2026-06-12
• Your Stack Has a Single Point of Failure: What Fable 5 Getting Yanked Means for Builders2026-06-12
• OpenCode Developer Guide: The Open Source AI Coding Agent with 160K Stars2026-06-12
• WebMCP: Google's Browser Standard That Lets AI Agents Use Websites as Tools2026-06-12
• Why the US Government Pulled Fable 5: Four Theories2026-06-12
• AWS Kiro Developer Guide: The Spec-Driven IDE That Replaced Amazon Q2026-06-11
• Claude Agent SDK vs Claude Code: When to Build and When to Drive2026-06-11
• Claude Agent SDK vs LangGraph: Choosing Your Agent Stack in 20262026-06-11
• Claude Agents vs Skills: Which One Do You Actually Need?2026-06-11
• Claude Code Auto Mode Explained: Permissions Without the Prompts2026-06-11
• Claude Code Dynamic Workflows: The Complete Guide2026-06-11
• Claude Code Fast Mode: When 2.5x Speed Is Worth 2x Price2026-06-11
• Claude Code Routines vs Managed Agents Schedules: Where Recurring Agent Work Should Live2026-06-11
• Subagents vs Agent Teams vs Workflows: Claude Code's Parallelism Primitives, Compared2026-06-11
• Claude Fable 5 vs Gemini 3.1 Pro: The July 2026 Frontier Comparison2026-06-11
• The Claude Tokenizer Change: What ~30% More Tokens Means for Your Bill2026-06-11
• DeepSeek Retires deepseek-chat and deepseek-reasoner on July 24: Your V4 Migration Guide2026-06-11
• Fable 5 with 1M Context: What Actually Works in Practice2026-06-11
• Fable 5 Effort Levels Explained: low to xhigh, and What They Cost You2026-06-11
• Handling Long-Running Fable 5 Requests: Timeouts, Streaming, and Background Patterns2026-06-11
• Setting Up the Memory Tool with Fable 5: Persistent Agents That Learn2026-06-11
• The Fable 5 Orchestrator Playbook: One Smart Model Managing Cheap Workers2026-06-11
• Prompt Caching Economics on Fable 5: When the 5-Minute TTL Pays2026-06-11
• Fable 5 Task Budgets: Capping Agent Spend Before It Happens2026-06-11
• Frontier Model API Pricing, August 2026: Claude vs OpenAI vs Gemini vs DeepSeek2026-06-11
• The Frontier Model Landscape, July 2026 Edition2026-06-11
• The Mid-Tier Shootout: GPT-5.4 vs Gemini 3.1 Pro vs DeepSeek V4 Pro2026-06-11
• GPT-5.6 Sol vs Claude Opus 5: The $5 Workhorse Head-to-Head2026-06-11
• How to Use Claude Fable 5: Every Access Path Explained2026-06-11
• Is Claude Fable 5 Slow? Latency in Practice, and When It Matters2026-06-11
• Managing a Fleet of Claude Agents: A Practical Guide2026-06-11
• Migrating Off Retired GPT Models in 2026: A Working Checklist2026-06-11
• Qwen 3.7 Max Developer Guide: 1M Context, $1.25/MTok, and Agent-First Architecture2026-06-11
• Recursive Self-Improvement: What Fable 5, Dario's Essay, and Anthropic's Own Data Actually Tell Us2026-06-11
• Rewriting Your Prompts and Skills for Fable 52026-06-11
• Ultracode: Claude Code Multi-Agent Orchestration Mode Explained2026-06-11
• 12 Ways Developers Are Actually Leveraging Claude Fable 52026-06-11
• What a Fleet of Claude Agents Actually Costs (July 2026 Math)2026-06-11
• The One-Cent Attack: Prompt Injection Through Bank Transfer Memos2026-06-10
• The Pushback on Amodei's Exponential Essay: Too Slow, Too Convenient, or About Right?2026-06-10
• Decoding Anthropic's Model Names: Fable, Mythos, and What the Naming Shift Signals2026-06-10
• Apache Burr vs LangGraph vs CrewAI: Choosing an AI Agent Framework in 20262026-06-10
• Apple's LanguageModel Protocol: Xcode 27 Just Made Model Lock-In Optional2026-06-10
• Best AI Coding Tools July 2026: Updated After Opus 5 and Fable 5 API-Only2026-06-10
• The Best Local Coding LLMs in 2026: Run Enterprise-Grade AI Without the Cloud2026-06-10
• Claude Code vs Droid (Factory AI): Which Terminal Agent in 20262026-06-10
• Why Claude Desktop Quietly Installs a 1.8 GB VM on Windows (And What You Can Do About It)2026-06-10
• Handling Fable 5 Refusals: A Working Guide to the Fallback API2026-06-10
• Claude Fable 5 Access After the June 22 Deadline: Where Things Stand2026-06-10
• Claude Fable 5 Pricing: Real Cost Per Task vs Opus 4.8, GPT-5.5 and Codex2026-06-10
• Claude Managed Agents: Dreaming, Outcomes, and Multi-Agent Orchestration Explained2026-06-10
• Claude Managed Agents Public Beta: What's Actually Available vs What's Gated2026-06-10
• How Claude's Usage Limits Actually Work With Fable 5: Windows, Multipliers, and Burn Rates2026-06-10
• Codex in June 2026: What Changed Since the Spring Wave2026-06-10
• Codex Exec in CI: The Practical Guide to Headless OpenAI Agents2026-06-10
• Codex vs Claude Code in July 2026: Opus 5, GPT-5.6, and the Post-Fable-5 Landscape2026-06-10
• Cursor Hit $50B -- Here's What the AI IDE Landscape Actually Looks Like Now2026-06-10
• Cursor vs Devin Desktop (formerly Windsurf): The 2026 IDE Agent Decision2026-06-10
• Dario Amodei Wants FAA-Style AI Regulation: Open Questions for Developers2026-06-10
• The Exponential and the Working Developer: Sitting With Amodei's Hardest Questions2026-06-10
• The Dario Paradox: Warning About the Exponential While Shipping It2026-06-10
• DiffusionGemma: Google Bets Diffusion Can Make Text Generation 4x Faster2026-06-10
• Claude Fable 5 API: Production Integration Patterns, Rate Limits, and Migration Gotchas2026-06-10
• Fable 5 on AWS Bedrock: When Your Data Leaves the AWS Boundary2026-06-10
• Fable 5 Broke Enterprise ZDR Agreements: What Dev Teams Must Do Now2026-06-10
• Fable 5 for Government and Regulated Teams: The GovCloud Question2026-06-10
• Fable 5 Before June 22: The Decision Checklist for Every Plan Tier2026-06-10
• How to Model Fable 5 Costs Before They Blow Up Your Budget2026-06-10
• Why Fable 5 Refuses Your Cybersecurity Queries (And How the Fallback Works)2026-06-10
• Fable 5's Hidden Guardrails: What Developers Need to Know About Silent Degradation2026-06-10
• Fable 5 vs DeepSeek V4: The Cost-Quality Gap Measured in Real Tasks2026-06-10
• Claude Fable 5 vs GPT-5.6 Sol: Benchmarks, Pricing, and When Each Wins2026-06-10
• Fable 5 vs Opus 4.8: A Data-Driven Decision Guide for Engineering Teams2026-06-10
• Factory AI and the Model Routing Era: How Coding Agents Are Learning to Spend Your Tokens Wisely2026-06-10
• Factory Droid: Review and Setup Guide (2026)2026-06-10
• FrontierCode Benchmark Explained: Why AI Coding Quality Scores Are Wrong (And the Fix)2026-06-10
• Git Worktrees + Claude Code: The 2026 Playbook for Running Parallel Agents Without Context Switching2026-06-10
• GitHub Copilot's New Usage-Based Billing: What Changed June 1 and What It Costs Now2026-06-10
• June 10, 2026: The Day the AI Dev Tool Market Showed Its Whole Hand2026-06-10
• Kimi CLI vs Claude Code: The Budget Question in 20262026-06-10
• Managed Agents vs LangGraph vs Rolling Your Own: Who Should Run Your Agent Loop in 20262026-06-10
• Mastra: Review and Setup Guide for TypeScript Agent Apps (2026)2026-06-10
• Mastra vs LangGraph.js: TypeScript Agent Frameworks Head to Head2026-06-10
• The Miasma Worm Is Targeting AI Developers: What You Need to Audit Now2026-06-10
• Microsoft's MAI Models and MoE Strategy: What Developers Need to Know for Copilot and Beyond2026-06-10
• Migrating from Windsurf to Claude Code: The Practical 2026 Guide2026-06-10
• Migrating to Claude Fable 5: The Practical Guide2026-06-10
• MiniMax M2.5 for Developers: The Anthropic-Compatible Budget Frontier Model2026-06-10
• Neon Postgres in 2026: Review and Setup for AI App Builders2026-06-10
• What the 'Notes on DeepSeek' Essay Gets Right About Open-Weights Economics2026-06-10
• OpenAI Agents SDK vs Claude Agent SDK: Building Agents on the Two Big Platforms2026-06-10
• OpenRouter in 2026: Review, Setup, and When Model Routing Pays2026-06-10
• PgDog Just Got Funded: What the Postgres Sharding Proxy Means for Your Stack2026-06-10
• The TypeScript AI Agent Stack in Mid-2026: Mastra vs Vercel AI SDK vs OpenAI Agents SDK vs LangGraph.js2026-06-10
• Vercel AI SDK 6 vs LangGraph 1.0: Which Agent Framework Should TypeScript Teams Use?2026-06-10
• Claude Mythos 5 Explained: What It Is, Who Can Access It, and Why It's Gated2026-06-10
• Agent Config Files Are Executable Supply Chain2026-06-08
• Goose: The Open Source AI Agent With 70+ MCP Extensions2026-06-07
• Harness Engineering Makes Tokens a Systems Budget2026-06-07
• LLM Routers Compared: LiteLLM vs Portkey vs OpenRouter in 20262026-06-07
• AI Code Attribution Needs Defect Forensics, Not Vibes2026-06-06
• Headroom: Compress Agent Tool Output Before It Reaches the LLM2026-06-06
• Security Agents Need Repro Harnesses, Not More Scan Prompts2026-06-05
• AI Agent Containment Needs a Capability Ledger2026-06-04
• MAI-Code-1-Flash Is a Model Routing Signal2026-06-03
• AI Agent Memory Needs a Context Ledger2026-06-02
• Spreadsheet Agents Need Permission Ledgers2026-06-01
• Domain Expertise Is the New Agentic Coding Moat2026-05-31
• The Agent Security Checklist I Use Before Connecting Tools2026-05-30
• Build Log: Turning the DevDigest Blog Into an Agent Content System2026-05-30
• Build Log: Adding Product Paths to a Content Site Without Making It Salesy2026-05-30
• Build Log: How I Shipped a Tool Directory That Feeds Search, Compare, and RSS2026-05-30
• Mastra for Durable TypeScript Agents: Where It Fits and Where It Does Not2026-05-30
• Mastra vs CopilotKit vs LangGraph: Build the Same Agent App Three Ways2026-05-30
• The Model, IDE, CLI, and Agent Framework Changes That Actually Matter2026-05-30
• The New AI Coding Stack I Would Pick Today2026-05-30
• Permissions, Logs, and Rollback for AI Coding Agents2026-05-30
• Prompt Injection in Agent Apps: The Practical Version2026-05-30
• State of AI Coding: What Changed This Month2026-05-30
• Taste Skills Are Turning Agent Review Into Infrastructure2026-05-30
• When CopilotKit Is the UI Layer, Not the Agent Framework2026-05-30
• Claude Opus 4.8 Is an Agent Honesty Release2026-05-29
• Local Code Graphs Are the Agent Context Layer2026-05-29
• AI Agent PMF Is a Cost Control Problem Now2026-05-28
• AI Chat Fatigue Is a Workflow Design Bug2026-05-27
• Coding Agents Need Codebase Maps, Not Bigger Prompts2026-05-26
• Claude Knowledge Work Plugins Turn Agent Setup Into Team Infrastructure2026-05-25
• Constraint Decay Is the Coding Agent Bug Nobody Can Prompt Around2026-05-25
• Reasonix Shows the Next Coding Agent Fight Is Cache Discipline2026-05-25
• CLI-Anything Turns Any Software Into an Agent-Ready Command Line2026-05-24
• 12-Factor Agents: Production Principles for Reliable AI Agents2026-05-23
• AI Security Scanners Move the Bottleneck to Triage2026-05-23
• Models.dev Makes Model Routing Feel Like Infrastructure2026-05-23
• Multi-Stream LLMs Hint at the Next Agent Architecture2026-05-23
• Claude Code's Official Plugin Marketplace Is Here - and It's Already at 23k Stars2026-05-22
• Sandboxed Agents Are Becoming the Team Control Plane2026-05-22
• Forge Shows the Local Agent Reliability Gap Is a Harness Problem2026-05-20
• Anthropic Buying Stainless Is About Agent Plumbing2026-05-19
• Agent Skills Are Becoming Package Managers2026-05-17
• AI Code Review Is the New Bottleneck2026-05-16
• AgentMemory Is Useful Only If You Audit What It Remembers2026-05-16
• Claude Agent SDK Credits End the Subscription Arbitrage2026-05-15
• Claude Code Plugin URLs Turn Skills Into a Supply Chain2026-05-14
• Codex CLI Vim Mode Is an Ergonomics Signal2026-05-14
• Skills for Real Engineers Need Governance, Not Fandom2026-05-14
• Agent Memory Benchmarks Are Not Enough2026-05-13
• Matt Pocock's Skills Repo Is a Better Pattern Than Vibe Coding2026-05-13
• Claude Platform on AWS Is Enterprise Agent Plumbing, Not Just Procurement2026-05-12
• Interaction Models Are the Next AI Developer Tool Interface2026-05-12
• TanStack's npm Compromise Is the CI Lesson Agent Teams Needed2026-05-12
• Codebase Graphs Are the New Agent Map2026-05-10
• Ruflo Is an Agent Meta-Harness. Treat the Star Count as a Warning Label.2026-05-10
• Claude Managed Agents Are Starting to Look Like Backend Jobs2026-05-09
• Agent-Native Backends Are the Next AI Coding Bottleneck2026-05-08
• 6 Launches in One Day: The DD Empire Expansion2026-05-07
• DevDigest OS: The Thesis Behind Treating an Empire as One Operating System2026-05-07
• DeepSeek-TUI: The Rust Terminal Coding Agent With MCP, Skills, and 1M-Token Context2026-05-07
• Terminal Agents Are the New Developer Runtime2026-05-07
• What Is Cline? The Open-Source AI Coding Tool That Runs in VS Code2026-05-07
• Claude Code Token Burn Is an Observability Problem2026-05-06
• How We Patched 100+ PRs Across Our App Empire in One Day2026-05-06
• 219 PRs in One Day: A Parallel Agent Fan-Out Postmortem2026-05-06
• 38 Apps in One Day: Migrating an Empire from Replit to Coolify2026-05-06
• Claude Code 2.1.128 Is an Ops Release, Not a Feature Drop2026-05-05
• Codex Automations: Where Scheduled AI Agents Actually Help2026-05-05
• Codex Is Becoming a General-Purpose AI Agent, Not Just a Coding Tool2026-05-05
• Codex Loops: What Boris Cherny Gets Right About Managing Agent Work2026-05-05
• Codex SDK vs CLI vs GitHub Action: Which Surface Should You Build On?2026-05-05
• Free Claude Code Is Really a Model Gateway Bet2026-05-05
• GPT Image 2 Prompt Libraries Are Becoming Production Infrastructure2026-05-05
• Karpathy's Loopy Era Is the Best Way to Understand Codex2026-05-05
• OpenAI's Codex Mac Certificate Deadline Is a Runbook Test2026-05-05
• Agent Skills Need Exit Criteria, Not More Prompt Lore2026-05-04
• GitHub Copilot Agent Metrics Are the Real Product Update2026-05-04
• Google Skills Shows the Next Agent Playbook2026-05-04
• Parallel Coding Agents Need Merge Discipline2026-05-04
• Karpathy CLAUDE.md Skills: Use the Viral Rules as a Menu, Not a Template2026-05-03
• The 98% Context Reduction Pattern2026-05-02
• Agent Swarms Need Receipts2026-05-02
• Agentic Search Works Best When It Writes Queries, Not Answers2026-05-02
• Approval Fatigue Is an Agent Security Bug2026-05-02
• Claude Code Agent Teams, Subagents, and MCP: The 2026 Playbook2026-05-02
• Client-Side Tool Calling Is the Privacy Pattern AI Apps Need2026-05-02
• Codex Changelog April 2026: Goals, Browser Use, GPT-5.5, and Safer Agents2026-05-02
• Codex /goal and Claude Managed Outcomes: The New Control Loops2026-05-02
• DeepSeek V4 Changes the Coding Agent Cost Equation2026-05-02
• Flue: The Agent Harness Framework and Why It Feels Different2026-05-02
• Flue and the Agent Harness Layer2026-05-02
• GitHub Copilot Coding Agent and CLI: Why GitHub Is Back in the Agent Race2026-05-02
• jcode and the Coding Agent Harness Wars2026-05-02
• lib0xc Is the Opposite of Rewrite Culture2026-05-02
• Long-Running Agents Need Harnesses, Not Hope2026-05-02
• ML Intern Shows Where Coding Agents Are Heading: Domain Tools, Not Generic Chat2026-05-02
• One Tool Beats Ten Endpoints2026-05-02
• Open Design Shows the Next Agent Wrapper2026-05-02
• OpenAI Codex, Managed Agents, and AWS: What Developers Should Watch2026-05-02
• Refusal Directions Are a Systems Problem2026-05-02
• Skills Are How Agents Learn the Job2026-05-02
• Skills Are the New Agent Operating System2026-05-02
• VS Code Copilot Co-Author Attribution: The Real Problem Is Workflow Consent2026-05-02
• Warp Open Sourced the Terminal. The Real Story Is Agent Operations2026-05-02
• 12 Tools in One Night: An Honest Overnight Agent Report2026-04-29
• Agent Architecture: Building Multi-Step AI Workflows That Survive Production2026-04-29
• OpenAI Agents SDK Evolution: What Ships in Production2026-04-29
• OpenAI Apps SDK: Building MCP UIs Inside ChatGPT2026-04-29
• Astro vs Next.js 16: Which to Choose in 20262026-04-29
• Claude API Reliability: Error Handling Best Practices2026-04-29
• Claude Batch API: Cutting Async Workload Costs In Half2026-04-29
• Claude Design: Anthropic's Bet That Designers and Developers Want the Same Tool2026-04-29
• Claude Opus 4.7: The Developer's Guide to Anthropic's New Flagship2026-04-29
• Claude Vision API: Image Analysis At Production Scale2026-04-29
• Cloudflare Agent Memory: A Developer's Guide to the New Primitive2026-04-29
• Flagship: Cloudflare Feature Flags for AI Apps2026-04-29
• Codex Security Preview: AppSec Agent for Real Repos2026-04-29
• Gemma 4: The Open Model Guide for Developers2026-04-29
• DeepSeek V4: The Developer's Guide to Flash and Pro2026-04-29
• Extended Thinking in Claude: When Deep Reasoning Pays For Itself2026-04-29
• GPT-5.4 for Developers: The Production Guide2026-04-29
• GPT-5.5-Codex in Production: What Actually Changes2026-04-29
• GPT-5.5 for Developers: A Production Field Guide2026-04-29
• DeepSeek R1, PPO, and GRPO Explained for Devs2026-04-29
• mlinter: Hugging Face's New Linter for Transformers Modeling Files2026-04-29
• KV Caching: A Practical Guide to Optimizing Transformer Inference2026-04-29
• Mercury 2 Developer Guide: Building With a Diffusion LLM in Production2026-04-29
• Model Context Protocol: A Production Guide To Building MCP Servers2026-04-29
• NVIDIA Nemotron 3 Super: A Developer's Guide to the 120B Hybrid MoE2026-04-29
• Open-Source MCP Servers Worth Installing in 20262026-04-29
• OpenAI AgentKit in Production: An Honest Builder's Review2026-04-29
• OpenAI Privacy Filter: Production PII Redaction Guide2026-04-29
• Assistants to Responses API: A Migration Field Guide2026-04-29
• Prompt Caching in the Claude API: A Production Guide2026-04-29
• RAG with Claude: Add Context Without Retraining2026-04-29
• SAM 3.1: Realtime Video Segmentation in Apps2026-04-29
• Self-Hosting AI Agents: 5 Ways to Run Claude Code on Your Own Infra2026-04-29
• Shipping OpenAI Symphony in Prod: A Real-World Guide2026-04-29
• Tool Use in the Claude API: Production Patterns for Reliable Agents2026-04-29
• Vercel's Agentic Infrastructure Stack Explained2026-04-29
• Vercel's New Durable Execution Programming Model: A Developer's Guide2026-04-29
• Agent Replays with TraceTrail: Loom for Agent Runs2026-04-28
• Best Claude Code Skills in 2026: A Curated Directory2026-04-28
• An Agent SDK Triage Bot for Commercial Insurance Submissions2026-04-28
• Claude Code as an HL7 to FHIR Migration Agent for Hospitals2026-04-28
• Hookyard Shows Why Claude Code Hooks Need a Package Manager2026-04-28
• Skills Marketplace: 312 Claude Code Skills, Curated2026-04-28
• Codex CLI Hooks for PLC and IoT Firmware Review on the Factory Floor2026-04-28
• Codex vs Claude Code in April 2026: Which Agent for Which Job2026-04-28
• Convex to Neon: The Playbook After 4 App Migrations2026-04-28
• The DD Stack Cookbook: Five Recipes That Compose2026-04-28
• DESIGN.md: The Contract That Keeps AI Agents On Brand2026-04-28
• Claude Context Is Code Search For Agents. Treat It Like Retrieval Infrastructure.2026-04-28
• Introducing agentfs: A Filesystem for AI Agents2026-04-28
• MCP Lens: Wireshark for Model Context Protocol Servers2026-04-28
• Promptlock: Deterministic Prompt Versioning for LLM Apps2026-04-28
• Six More Tools for the Agent Infrastructure Stack2026-04-28
• Six Paid Products in a Day: DD's Bet on Agent Infra for Small Teams2026-04-28
• Two Small Devtools: SkillForge CI and Cost Tape2026-04-28
• 10 Tools We Built for Agent Infrastructure2026-04-28
• 10 Trending AI Dev Tools, Week of April 28 20262026-04-28
• The Claude Design Moment: AI Design Skills Just Got Their Breakout Week2026-04-23
• The Agent Reliability Cliff: Why Your 10-Step Chain Only Succeeds 20% of the Time2026-04-23
• AI Design Slop: 16 Patterns That Out Your App as Vibe-Coded2026-04-22
• Codeburn: The First TUI That Actually Shows Where Your Claude Max Subscription Is Going2026-04-22
• Intent Debt: The AI-Era Debt Nobody Is Tracking2026-04-22
• Over-Editing: Why Your AI Coding Agent Rewrites What Isn't Broken2026-04-22
• Qwen3.6-27B Is the Local Coding Model to Test First2026-04-22
• 7 AI Agent Orchestration Patterns Every Developer Should Know2026-04-22
• Zed Just Made Parallel AI Agents a Native Editor Primitive2026-04-22
• Karpathy Skills Show Why CLAUDE.md Is Product Surface Now2026-04-21
• Multica Turns Coding Agents Into Teammates. The Hard Part Is Receipts.2026-04-20
• 271 MCP Servers Exist. These 5 Actually Make Claude Code Better.2026-04-19
• The $400 Overnight Bill: Why Managed Agents Need FinOps Now2026-04-19
• 10 CLI Tools Reshaping AI Development in 20262026-04-19
• How I'm Building 24 AI-Powered Apps in Parallel2026-04-19
• Claude Code vs Codex vs Cursor vs OpenCode: Which Agent Ships More Code?2026-04-19
• How to Write a CLAUDE.md: The Complete 2026 Guide2026-04-19
• What Are Claude Code Skills? A Complete Beginner Guide2026-04-19
• What Is an AI Coding Agent? The Complete 2026 Guide2026-04-19
• What Is an MCP Server? A Developer's Beginner Guide (2026)2026-04-19
• What Is Cursor? The AI Code Editor Explained (2026)2026-04-19
• What Is the Model Context Protocol? A 2026 Primer2026-04-19
• Aider vs Claude Code in 2026: Git-First Open Source vs Subagent Runtime2026-04-18
• Claude Code Usage Limits in 2026: The Practical Playbook for Pro and Max Teams2026-04-18
• Claude Code vs Codex App in 2026: Local Agent Pairing vs Cloud Agent Orchestration2026-04-18
• Copilot Pro+ Premium Requests Explained in 2026: What Teams Miss in Pricing Comparisons2026-04-18
• OpenAI Codex Cloud Security Playbook 2026: Internet Access, Prompt Injection, and Safe Defaults2026-04-18
• What Hacker News Gets Right About AI Coding Agents in 20262026-04-18
• Why Skills Beat Prompts for Coding Agents in 20262026-04-18
• The AI-Native Development Workflow: How Top Developers Actually Work in 20262026-04-09
• Building Multi-Agent Workflows in Claude Code: A Practical Tutorial2026-04-09
• Building SaaS with AI Agents in 2026: The Complete Workflow2026-04-09
• Context Engineering: The Highest-Leverage Skill in AI-Assisted Development2026-04-09
• How to Coordinate Multiple AI Agents: The Definitive Guide for 20262026-04-09
• The MCP Server Ecosystem: A Developer's Guide for 20262026-04-09
• Self-Improving AI Agents: Building Systems That Learn From Their Mistakes2026-04-09
• AI Agent Memory Patterns2026-04-03
• Anthropic vs OpenAI: Developer Experience Compared2026-04-03
• Building a SaaS with Claude Code: End-to-End Guide2026-04-03
• Case Study: Building Developers Digest with Claude Code2026-04-03
• Convex vs Supabase for AI Apps2026-04-03
• How to Debug AI Agent Workflows2026-04-03
• MCP vs Function Calling: When to Use Each2026-04-03
• How to Migrate from GitHub Copilot to Claude Code2026-04-03
• 10 TypeScript Patterns Every AI Developer Should Know2026-04-03
• Every AI Coding Tool Compared: The 2026 Matrix2026-04-02
• AI Coding Tools Pricing Comparison 20262026-04-02
• 303 AI Skills for 12 Careers: The Free Directory2026-04-02
• AI Skills for Every Career: Agents and Knowledge Work2026-04-02
• Claude Code Channels: Telegram, Discord, iMessage, and Webhooks2026-04-02
• Claude Code Hooks Explained2026-04-02
• How to Use Claude Code with Next.js2026-04-02
• Claude Code vs Cursor vs Codex: Which Should You Use?2026-04-02
• Claude Computer Use: AI That Controls Your Desktop2026-04-02
• Claude Haiku 4.5: Near-Frontier Intelligence at a Fraction of the Cost2026-04-02
• The Complete Guide to MCP Servers2026-04-02
• Local OpenTelemetry Traces Are Agent Receipts2026-04-02
• How to Build an AI Agent in 2026: A Practical Guide2026-04-02
• How to Build MCP Servers in TypeScript2026-04-02
• The Best MCP Servers in 2026: A Complete Directory2026-04-02
• Ship Code While You Sleep: The Overnight Agent Workflow2026-04-02
• State of AI Coding: April 20262026-04-02
• Transformers.js: Run AI Models Directly in the Browser2026-04-02
• DeepSeek R1 and V3: The Developer's Guide to Open-Source AI2026-03-26
• Llama 4: The Complete Developer's Guide to Meta's Open Source Models2026-03-26
• The DevDigest App Ecosystem2026-03-22
• AI Agents Explained: A TypeScript Developer's Guide2026-03-19
• My AI Developer Workflow in 20262026-03-19
• The Solo Developer's AI Toolkit in 20262026-03-19
• Aider vs Claude Code: Open Source vs Commercial AI Coding CLI2026-03-19
• Astral Joins OpenAI: What It Means for Python Developers2026-03-19
• The 10 Best AI Coding Tools in 20262026-03-19
• Best MCP Servers in 2026: The Developer Shortlist2026-03-19
• How to Build Full-Stack TypeScript Apps With AI in 20262026-03-19
• 60 Claude Code Tips and Tricks for Power Users2026-03-19
• Claude Code vs Cursor in 2026: Which Should You Use?2026-03-19
• Claude vs GPT for Coding: Which Model Writes Better TypeScript?2026-03-19
• Cursor Composer 2: Everything You Need to Know2026-03-19
• Cursor vs Claude Code in 2026 - Which Should You Use?2026-03-19
• Cursor vs Codex: IDE Agent vs Terminal and Cloud Agent for TypeScript2026-03-19
• Gemini CLI: Free AI Coding With 1M Token Context2026-03-19
• GitHub Copilot in 2026: Still Worth It for TypeScript Developers?2026-03-19
• How to Build AI Agents in TypeScript2026-03-19
• How to Use MCP Servers: The Complete Guide2026-03-19
• LangChain vs Vercel AI SDK: Which TypeScript AI Framework Should You Use?2026-03-19
• Multi-Agent Systems: How to Orchestrate Multiple AI Agents in TypeScript2026-03-19
• The Next.js AI App Stack for 20262026-03-19
• OpenAI Codex: Terminal and Cloud AI Coding Agent2026-03-19
• OpenAI vs Anthropic in 2026 - Models, Tools, and Developer Experience2026-03-19
• Prompt Engineering for AI Coding Tools2026-03-19
• Open Source Has a Bot Problem: Prompt Injection in Contributing.md2026-03-19
• Vercel AI SDK: Build Streaming AI Apps in TypeScript2026-03-19
• Vibe Coding in 2026: Build Fast Without Losing the Plot2026-03-19
• Web Dev Arena: How to Test AI Coding Models on Real Frontend Work2026-03-19
• What Is Claude Code? The Complete Guide for 20262026-03-19
• What Is MCP (Model Context Protocol)? A TypeScript Developer's Guide2026-03-19
• What is RAG? Retrieval Augmented Generation Explained2026-03-19
• Windsurf vs Cursor: Which AI IDE for TypeScript Developers?2026-03-19
• NVIDIA's Nemotron 3 Super in 6 Minutes2026-03-13
• CLIs Over MCPs: Why the Best AI Agent Tools Already Exist2026-03-09
• Composio 101: Give Your AI Agent Access to 500+ Apps2026-03-09
• Claude Code Loops: Recurring Prompts That Actually Run2026-03-07
• OpenAI's GPT 5.4 in 10 Minutes2026-03-06
• Claude Code: Remote Control, Auto Memory, Plugins & More2026-02-28
• Mercury 2: The LLM That Doesn't Generate Like an LLM2026-02-24
• Claude Code Worktrees: Parallel Development Without the Chaos2026-02-21
• Claude Sonnet 4.6: Approaching Opus at Half the Cost2026-02-19
• Claude Opus 4.6: Anthropic's Smartest Model Gets Agent Teams2026-02-09
• Why Claude Code Won: Unix Philosophy Meets AI Agents2026-01-19
• Cowork: Claude Code for Everyone, Not Just Developers2026-01-13
• Progressive Disclosure: How Claude Code Cut Token Usage by 98%2026-01-12
• Self-Improving Skills: Claude Code That Learns From Every Session2026-01-05
• Interview Mode: Let Claude Code Ask the Questions First2026-01-01
• Claude Code + Chrome: AI Agents That Use Your Browser2025-12-31
• Continual Learning in Claude Code: Memory That Compounds2025-12-30
• The Ralph Loop: Running Claude Code For Hours Autonomously2025-12-29
• The Bitter Lesson: How We Build and What We Build Is About to Change2025-12-27
• Magic Patterns: Why Design Wins in a World of AI Code Generators2025-11-26
• Zed: The Open Source Agentic IDE2025-11-25
• Claude Opus 4.5: Anthropic's Most Intelligent Model2025-11-24
• The Agentic Development Tech Stack for 20262025-11-23
• Antigravity: Google's Agentic Code Editor2025-11-23
• Streamline Your Git Workflow with GitKraken and Claude Code2025-11-10
• Cursor 2.0 & Composer: The Fastest AI Coding Model2025-11-03
• Windsurf SWE-1.5 Launches Same Day as Cursor 2.02025-11-03
• Claude Skills: A technical deep dive into Anthropic's new approach to AI context management2025-11-02
• NVIDIA Nemotron Nano 2 VL: Open Source Vision-Language Model2025-10-28
• Kimi K2: Fast, Cheap, and Efficient Coding2025-10-24
• ChatGPT Atlas: OpenAI's Built-In Web Browser2025-10-21
• Emergent Labs: Build Production-Ready Apps Through Conversation2025-10-15
• Build a Full Stack AI SaaS Application in 60 Minutes2025-10-08
• OpenAI Dev Day 2025: Everything Announced2025-10-06
• Anthropic Sonnet 4.5 in Claude Code2025-10-03
• GPT-5 Codex: OpenAI's Agentic Coding Model2025-09-16
• Zoer: Full-Stack App in 5 Minutes with Vibe Coding2025-09-10
• Magic Patterns: Effortless UI Design with AI2025-09-05
• Warp 2.0: The Agentic Development Environment2025-09-03
• Grok Code Fast 1: xAI's Speed-Optimized Coding Model2025-09-02
• Deep Agent: Build Full-Stack Apps in Minutes2025-08-27
• NVIDIA Nemotron Nano 9B V2: Local AI That Punches Up2025-08-26
• Kombai: AI That Beats Claude and Gemini on Front-End Tasks2025-08-20
• GPT-5: OpenAI's Most Capable Model2025-08-08
• Open Lovable: Re-Imagine Websites in Seconds2025-08-08
• GPT-OSS: OpenAI's First Open Source Model2025-08-06
• Augment's Task List: AI-Powered Development Planning2025-08-05
• Claude Code Sub Agents: Parallel AI Development2025-07-25
• Qwen 3 Coder: Alibaba's Coding-Optimized LLM2025-07-24
• Create Beautiful UI with Claude Code: The Style Guide Method2025-07-21
• ChatGPT Agent: OpenAI's Operator Meets Deep Research2025-07-17
• Grok 4: xAI's Most Powerful AI Model2025-07-10
• Claude Code: The Future of Coding?2025-07-05
• OpenAI Agents SDK for TypeScript: A Practical Guide2025-06-07
• Qwen 3: Alibaba's Open-Source Model That Outclassed Llama 42025-04-29
• Diffusion Language Models: How Mercury Changed the LLM Speed Game2025-02-27
• xAI Grok 3 Launch: The Smartest AI on Earth?2025-02-18
• Unstract: Open-Source AI Document Parsing at Scale2025-02-12
• OpenAI Deep Research: The AI Agent That Does Your Homework2025-02-03
• ChatGPT Tasks: Scheduled AI Agents Inside ChatGPT2025-01-14
• Gemini Deep Research: Google's AI Research Agent2025-01-10
• Microsoft PHI-4: A 14B Parameter Model That Rivals Models 5x Its Size2025-01-09
• Build an AI Agent Web App with LangGraph and CopilotKit2024-12-12
• Llama 3.3 70B: Meta's Cost-Effective Frontier Model2024-12-07
• Lovable: Building Full-Stack Web Apps with AI and Supabase2024-12-01
• ChatGPT Desktop Now Reads Your VS Code, Terminal, and Xcode2024-11-14
• OpenAI Realtime Voice API: Getting Started Guide2024-10-04
• NotebookLM: Google's AI-Powered Research and Podcast Tool2024-10-03
• Cursor: The AI-Powered Code Editor That Changed How Developers Work2024-08-22

Guides (123)

• Terminal CLI - Claude Code
• Getting Started with DevDigest CLI
• Interactive Mode - Claude Code
• Claude Code Setup Guide
• Keyboard Shortcuts - Claude Code
• MCP Servers Explained
• Vim Editor Mode - Claude Code
• Claude Code Complete Course
• Run AI Models Locally with Ollama and LM Studio
• Background Tasks - Claude Code
• Getting Started with Claude Code
• Building Your First MCP Server
• Bash Mode - Claude Code
• AI Agent Frameworks Compared: LangGraph vs CrewAI vs Mastra vs CopilotKit
• Command History - Claude Code
• Voice Dictation - Claude Code
• Multiline Input - Claude Code
• Prompt Suggestions - Claude Code
• Side Questions with /btw - Claude Code
• Read Tool - Claude Code
• Write Tool - Claude Code
• Edit Tool - Claude Code
• MultiEdit - Claude Code
• Notebook Edit - Claude Code
• Glob Tool - Claude Code
• Grep Tool - Claude Code
• LSP Tool - Claude Code
• Bash Tool - Claude Code
• PowerShell Tool - Claude Code
• Monitor Tool - Claude Code
• Environment Variable Persistence - Claude Code
• Chronicle Research Preview Setup Guide
• Git Integration - Claude Code
• Worktrees - Claude Code
• Writing Your First Claude Code Skill
• PR Status in Footer - Claude Code
• Migrating from Cursor to Claude Code
• gh CLI Integration - Claude Code
• WebFetch Tool - Claude Code
• WebSearch Tool - Claude Code
• CLAUDE.md Files - Claude Code
• .claude/rules Directory - Claude Code
• AGENTS.md - Claude Code
• Auto Memory - Claude Code
• Memory Command - Claude Code
• Context Window Visualization - Claude Code
• Prompt Caching - Claude Code
• Auto Compaction - Claude Code
• Default Permission Mode - Claude Code
• Accept Edits Mode - Claude Code
• Plan Mode - Claude Code
• Auto Mode - Claude Code
• DontAsk Mode - Claude Code
• Bypass Permissions Mode - Claude Code
• Permission Rules - Claude Code
• Protected Paths - Claude Code
• Sandboxing - Claude Code
• Model Aliases - Claude Code
• OpusPlan Alias - Claude Code
• 1M Token Context - Claude Code
• Effort Levels - Claude Code
• Model Picker (/model) - Claude Code
• Fast Mode - Claude Code
• Extended Thinking - Claude Code
• Custom Model Option - Claude Code
• Skills System - Claude Code
• Bundled Skills - Claude Code
• Skill Invocation - Claude Code
• Skill Frontmatter - Claude Code
• Skill Arguments - Claude Code
• Disable Model Invocation - Claude Code
• Skill Pre-Approval - Claude Code
• Skill in Subagent - Claude Code
• Live Skill Discovery - Claude Code
• Subagents - Claude Code
• Built-in Subagents - Claude Code
• Custom Subagent Types - Claude Code
• Subagent Frontmatter - Claude Code
• Subagent Tool Restrictions - Claude Code
• Subagent MCP Scoping - Claude Code
• Subagent Persistent Memory - Claude Code
• Subagent Context Isolation - Claude Code
• Resume Subagents - Claude Code
• Hooks System - Claude Code
• SessionStart Hook - Claude Code
• SessionEnd Hook - Claude Code
• UserPromptSubmit Hook - Claude Code
• UserPromptExpansion Hook - Claude Code
• PreToolUse Hook - Claude Code
• PostToolUse Hook - Claude Code
• PostToolUseFailure Hook - Claude Code
• PermissionRequest Hook - Claude Code
• PermissionDenied Hook - Claude Code
• SubagentStart and SubagentStop Hooks - Claude Code
• TaskCreated and TaskCompleted Hooks - Claude Code
• Stop Hook - Claude Code
• FileChanged Hook - Claude Code
• ConfigChange and InstructionsLoaded Hooks - Claude Code
• PreCompact and PostCompact Hooks - Claude Code
• Elicitation Hook - Claude Code
• Command Hooks - Claude Code
• Prompt-Based Hooks - Claude Code
• Agent-Based Hooks - Claude Code
• Async Hooks - Claude Code
• MCP Servers - Claude Code
• MCP Installation Scopes - Claude Code
• MCP Tool Search - Claude Code
• MCP OAuth - Claude Code
• MCP Resources - Claude Code
• MCP Prompts - Claude Code
• MCP Channel Messaging - Claude Code
• Managed MCP - Claude Code
• Agent Teams - Claude Code
• Team Lead - Claude Code
• Shared Task List - Claude Code
• Inter-Agent Messaging - Claude Code
• Split Pane Display - Claude Code
• Plan Approval - Claude Code
• Task Dependencies - Claude Code
• Subagent Definitions as Teammates - Claude Code
• /loop Command - Claude Code
• Scheduled Tasks (Desktop) - Claude Code
• Routines (Web) - Claude Code

Toolkit (49)

• AI API Cost Calculator
• Token Counter
• Prompt Tester
• Prompt Playground
• Prompt Diff
• Agent Compare
• CLAUDE.md Generator
• MCP Config Generator
• .env Generator
• JSON Formatter
• JSON to TypeScript
• Base64 Encoder
• URL Encoder
• HTML Entities
• Epoch Converter
• Color Converter
• CSS Units Converter
• Regex Tester
• Diff Viewer
• SQL Formatter
• cURL to Code
• Markdown Preview
• Case Converter
• Text Stats
• Lorem Ipsum Generator
• Code Viewer
• Markdown Table Generator
• Tailwind Class Generator
• JWT Decoder
• Hash Generator
• UUID Generator
• Chmod Calculator
• Cron Builder
• API Tester
• .gitignore Generator
• Meta Tags Generator
• YAML Validator
• Dockerfile Generator
• API Mock Generator
• TOML Editor
• Git Command Builder
• Commit Message Generator
• README Generator
• Package Analyzer
• robots.txt Tester
• Tweet Viewer
• Design System
• Icons
• Sitemap