Topic

AGENTS

Agent frameworks and patterns - orchestration, tool use, and autonomous workflows.

91 resources - 54 posts, 28 tools, 9 guides

All TopicsAgentsClaude Code AI Coding Developer Tools News AI Hacker News Claude OpenAI

Blog Posts

AWS Emulator: Free Local AWS Built by AI Agents (HN Review)

AWS released a free, CC0 local emulator of 200+ AWS services that its own agents wrote with no human code review. What it is, how the three-team agent loop works, and what to check before you trust it in CI.

Nov 12, 20268 min read

Claude PCB Design: Fable 5.2 Built Three Working Prototypes

Anthropic says Claude Fable 5.2 designed three electronics prototypes with Diode Computers. What the claude pcb design research shows, what is vendor-reported, and what a builder can test.

Nov 10, 20267 min read

How the Claude Code Team Does Code Review: Risk Tiers and Round Caps

Anthropic published how the Claude Code team reviews code at agent volume: layered checks, human approval scaled by risk, a round cap, and incidents as evals. What to copy.

Nov 1, 20268 min read

Claude Code Game Studios: 49 Agents, and What Its Own Test Says

Claude Code Game Studios packs 49 agents and 74 skills into a template. Its README says the heaviest build ranked last. How to set modes.rigor and what to skip.

Oct 31, 20266 min read

Google Agent Compute Engine: A MicroVM Per Agent, Explained

Google Agent Compute Engine gives every agent its own microVM with no credentials inside. What Google says it does, what is still unpublished, and what a builder can copy today.

Oct 24, 20268 min read

Agent Skills Moves to the Agentic AI Foundation: What Changes

Anthropic donated the Agent Skills standard to the Agentic AI Foundation on October 22, 2026. What moves, what stays the same, and what to check in your own SKILL.md files on Monday.

Oct 22, 20267 min read

Claude Duet: What It Is and How It Differs from Claude Code Routines

Anthropic opened a research preview of Claude Duet, a proactive agent that briefs you each morning and works in the background. What is confirmed, what is not, and what a Claude Code user should make of it.

Oct 22, 20266 min read

Local LLM Speed by Hardware: What llmspeed Gets Right

llmspeed estimates tokens per second for 30 machines and 15 models. What its numbers mean, the memory-bandwidth rule behind them, and why prefill matters for coding agents.

Oct 18, 20267 min read

RTX Spark for Local LLMs: Will It Run a Coding Agent?

RTX Spark laptops ship October 16 with up to 128 GB of unified memory. Why the 600 GB/s figure is not memory bandwidth and which local coding models fit.

Oct 14, 20268 min read

Claude Code Projects: Coordinator, Threads, and Limits

Claude Code Projects is open to waitlisted Pro and Max users. How the coordinator and cloud threads work, what they cost in plan limits and where it breaks.

Oct 13, 20266 min read

Agent Harness Lessons From a 500B-Token Decompile: Give Agents a PASS/FAIL Oracle

Agent harness lessons from a 500B+ token decompile: a byte-matching PASS/FAIL oracle beat the reviewer agent. How agents cheated it and what to copy.

Oct 12, 20267 min read

Freebuff Review: The Free Coding Agent Paid for by Ads, and What It Costs You

Freebuff is a free coding agent paid for by text ads. What the free tier includes, how Freebucks limit usage, and what the privacy policy says about your code.

Oct 12, 20268 min read

Cheapest Subagent Model: Haiku 5.5 or GPT-6 Luna? Routing, Compaction and Cost per Task

Which cheap model belongs under your orchestrator? Haiku 5.5 vs GPT-6 Luna as a subagent or worker: routing by prompt length, compaction, tool-call gotchas and cost per agent task.

Oct 9, 202615 min read

Slack Code vs Claude Code vs Cursor vs OpenCode: When Agents Belong in Chat

Slack Code gives coding agents their own Slack channels with diffs, previews, and an audit log. When it beats Claude Code, Cursor, or OpenCode, and when not.

Aug 21, 20267 min read

Kitesurf: Cloudflare's Agent-First Browser Runs in V8 Isolates on Workers

Cloudflare shipped Kitesurf, an agent-first browser that runs entirely on Workers: Rust and WebAssembly rendering, per-page isolates, CDP compatibility, and 3-7x less memory and CPU than Chromium for common agent tasks. Free in beta in Browser Run.

Aug 6, 20267 min read

Cloudflare Billable Usage API: Programmatic Cost Visibility for Agent-Run Accounts

Cloudflare's Billable Usage API returns usage and cost per product from one FOCUS-aligned endpoint, so agent-created spend is visible without the dashboard.

Aug 4, 20266 min read

@cloudflare/computer: an Agent Runtime That Treats a Container as a Tool, Not a Home

@cloudflare/computer is an open-source agent runtime: an SQLite-backed shared workspace plus a per-task choice between fast isolates and full Linux containers.

Aug 3, 20267 min read

AI Session Portability Compared 2026: OpenAI vs Anthropic vs Gemini

AI session portability compared across OpenAI, Anthropic, and Gemini: storage defaults, encrypted reasoning, compaction, and what you can move or audit.

Jul 31, 202611 min read

Buzz by Block: The Open-Source Workspace Where Humans and AI Agents Build Together

Buzz is Block's open-source Nostr relay workspace where humans and AI agents share rooms. Agent-first CLI, git as channels, workflows, and where it fits.

Jul 30, 20268 min read

An AI Agent Escaped Its Sandbox and Attacked Hugging Face: Inside the ExploitGym Incident

ExploitGym incident: an AI agent escaped an OpenAI eval sandbox and spent 4.5 days inside Hugging Face production infrastructure. The timeline and HN debate.

Jul 30, 20269 min read

Buzz: Block's Agent-Native Messaging Layer on Nostr

Buzz is Block's open-source, agent-native messaging layer on Nostr: agents get cryptographic identities, every message is a signed event, and you run the relay.

Jul 29, 20269 min read

Why Software Factories Fail: Harness Engineering Is Not Enough

A deep dive into why fully autonomous AI coding agents degrade codebases over time, and what context engineering can actually fix.

Jul 24, 20269 min read

Spec-Driven Agent Workflows: GitHub Spec Kit, gstack, and the New Handoff Layer

GitHub Spec Kit and gstack are trending for the same reason: coding agents need durable specs, plans, and task ledgers more than another one-shot prompt.

Jul 17, 20268 min read

Langflow CVE-2026-55255: The First AI Agent Framework on CISA's Must-Patch List

Langflow CVE-2026-55255 is the first AI agent platform on CISA's exploited vulnerabilities list. How the IDOR flaw works and how to check if you are exposed.

Jul 16, 20267 min read

GPT-5.6 Sol, Terra, and Luna: A Developer's Guide to OpenAI's New Model Family

A practical guide to choosing GPT-5.6 Sol, Terra, and Luna, using programmatic tool calling, caching, and the multi-agent beta in production.

Jul 9, 20268 min read

Headless AI Coding Agents in CI: Claude Code, Codex CLI, Gemini CLI, and opencode Compared

Headless AI coding agents in CI compared: Claude Code, Codex CLI, Gemini CLI, and opencode on invocation flags, sandboxing, auth, and output formats.

Jul 9, 20269 min read

The Log Is the Agent: Event Sourcing Comes to AI Systems

Event sourcing for AI agents: a new paper makes the append-only log the source of truth for agent state. What it enables, and whether HN thinks it is just CQRS.

Jul 5, 20267 min read

Agents 101: How to Build and Deploy Anything with AI Agents

Agents 101 companion guide: how to build and deploy AI agents fast on the Vercel agentic infrastructure stack, and where to go next to learn each piece.

Jul 1, 20267 min read

The Router Era: Why Not Owning a Frontier Model Became an Advantage

Model routers turn having no single winning model into an advantage: how routing works, why open weights and neoclouds make it cheap, and the counter-argument.

Jun 20, 202611 min read

Cursor Automations Developer Guide: Always-On AI Coding Agents

Cursor Automations run AI coding agents in the background on triggers like test failures, PRs, cron and webhooks. How to set up triggers and real workflows.

Jun 15, 20269 min read

Handling Fable 5 Refusals: A Working Guide to the Fallback API

Handle Claude Fable 5 refusals with the fallback API: what a refusal looks like on the wire, three ways to handle it with code, and the billing rules.

Jun 10, 202610 min read

Codebase Graphs Are the New Agent Map

Codebase graphs like Graphify give coding agents a durable map of how code, docs, schemas and decisions connect, so long runs stop rediscovering the repo.

May 10, 20268 min read

Agent-Native Backends Are the Next AI Coding Bottleneck

InsForge is an open-source backend for agentic coding. Why agents still break databases, auth and deploys, and what an agent-readable control plane needs.

May 8, 20268 min read

Agent Swarms Need Receipts

Agent swarms are easy to launch and hard to trust. Why every multi-agent setup needs receipts - tests, logs, diffs and reviewable checkpoints - not more agents.

May 2, 20268 min read

Agentic Search Works Best When It Writes Queries, Not Answers

SNEWPAPERS is a useful Show HN signal: the strongest agentic search products do not replace search results with prose. They teach the agent to operate a real search system.

May 2, 20268 min read

DeepSeek V4 Changes the Coding Agent Cost Equation

DeepSeek V4 brings near-frontier coding at a much lower token price. Where cheap reasoning fits in a coding agent stack, from code review to repo mapping.

May 2, 20268 min read

Flue and the Agent Harness Layer

Flue is trending because it names the part of agent infrastructure that is becoming product-critical: the programmable harness around the model.

May 2, 20268 min read

jcode and the Coding Agent Harness Wars

jcode is trending because it competes on a less glamorous but important agent metric: how cheap it is to keep many coding sessions alive.

May 2, 20268 min read

ML Intern Shows Where Coding Agents Are Heading: Domain Tools, Not Generic Chat

Hugging Face's ml-intern is a domain agent for ML work - papers, datasets, training jobs, and Hub traces. Why domain tools beat generic chat for coding agents.

May 2, 20268 min read

Open Design Shows the Next Agent Wrapper

Open Design turns coding agent CLIs like Claude Code and Codex into a design engine. The real lesson is artifact-first agent wrappers, not design automation.

May 2, 20268 min read

Refusal Directions Are a Systems Problem

A trending refusal-direction paper is a reminder that model safety cannot be treated as a thin refusal layer. Builders need layered controls around the model.

May 2, 20268 min read

Skills Are the New Agent Operating System

Agent skills turn team process into small, reusable operating procedures that load when relevant. Why skills beat one giant prompt for coding agents.

May 2, 20269 min read

Cloudflare Agent Memory: A Developer's Guide to the New Primitive

Cloudflare's Agent Memory primitive. What it stores, how ingest and recall work, how it compares to mem0, and how to wire it into your stack.

Apr 29, 20269 min read

GPT-5.4 for Developers: The Production Guide

GPT-5.4 developer guide with OpenAI SDK code, computer use, the 272K-token pricing cliff, and when 5.4 still beats GPT-5.3 and GPT-5.5 in production.

Apr 29, 202612 min read

GPT-5.5 for Developers: A Production Field Guide

GPT-5.5 and 5.5 Pro for developers: pricing, which tier fits which workload, agentic gains from real evals, a regression to watch, and a migration playbook.

Apr 29, 202611 min read

Vercel's Agentic Infrastructure Stack Explained

Vercel's agentic infrastructure explained: what the announcement actually names, how AI Gateway, Sandbox, Workflows and Flags compose, with code checked against the SDKs.

Apr 29, 202611 min read

Vercel's New Durable Execution Programming Model: A Developer's Guide

Vercel Workflows is GA: durable TypeScript with "use workflow" and "use step". What it means for agents and long-running flows, with code adapted from Vercel's own examples.

Apr 29, 202610 min read

Agent Replays with TraceTrail: Loom for Agent Runs

Agent runs are opaque. TraceTrail turns a Claude Code JSONL into a public share link with a stepped timeline of messages, tool calls, and tokens.

Apr 28, 20268 min read

Six More Tools for the Agent Infrastructure Stack

The second half of our agent tooling release: distribution, validation, and ergonomics layered on top of the first six. Six small CLIs, one through-line.

Apr 28, 20269 min read

How I'm Building 24 AI-Powered Apps in Parallel

One dev, one CLI, 24 subdomains, and a lot of parallel agents. The stack, registry, agent loop, and honest lessons behind shipping an AI app portfolio.

Apr 19, 20269 min read

Claude Code Loops: Recurring Prompts That Actually Run

Claude Code /loop runs prompts on repeat in a session: fixed or self-paced intervals, seven-day expiry, jitter, and when Routines fit better.

Mar 7, 20266 min read

OpenAI's GPT 5.4 in 10 Minutes

State-of-the-art computer use, steerable thinking you can redirect mid-response, and a million tokens of context. GPT 5.4 is OpenAI's most capable model yet.

Mar 6, 20268 min read

Claude Code: Remote Control, Auto Memory, Plugins & More

Claude Code updates: remote control from your phone, Cowork scheduled tasks, new plugin repos, auto memory and 4% of public GitHub commits now from Claude Code.

Feb 28, 20265 min read

Claude Code Worktrees: Parallel Development Without the Chaos

Claude Code worktrees let multiple agents work on one repo in parallel, each in its own branch and directory. Set up sub-agent isolation and keep main clean.

Feb 21, 20266 min read

Related Tools

All tools →

Claude Code

Daily Driver

Anthropic's agentic coding CLI. Runs in your terminal, edits files autonomously, spawns sub-agents, and maintains memory across sessions. Defaults to Claude Opus 5.5 on paid plans as of October 2026.

AI Coding

OpenAI Codex

Agent

OpenAI's coding agent for terminal, cloud, IDE, GitHub, Slack, and Linear workflows. Reads repos, edits files, runs commands, and returns reviewable diffs.

AI Coding

DeepSeek-TUI

Open source

Open-source (MIT) terminal coding agent, renamed Codewhale, with Plan, Work, and Operate modes, approval postures, /undo and /restore, receipts, MCP servers, sub-agents, and a local runtime HTTP API. Provider-neutral: 40+ built-in provider routes plus local models, no longer DeepSeek by default.

AI Coding

Windsurf

AI-native IDE built by Codeium, acquired by Cognition in 2025 and renamed Devin Desktop on June 2, 2026. Devin Local, the agent that succeeded Cascade, handles multi-file edits. Free plan; Pro is $20/mo.

AI Coding

Devin

Cognition Labs' autonomous software engineer. Handles full tasks end-to-end - reads docs, writes code, runs tests, and submits PRs in an isolated sandbox.

AI Coding

Vercel AI SDK

Essential

The TypeScript toolkit for building AI apps. Unified API across OpenAI, Anthropic, Google. Streaming, tool calling, structured output, multi-step agents. 27K+ GitHub stars.

AI Frameworks

CopilotKit

Agent UI

Frontend stack for agent-native apps. React hooks, prebuilt copilot UI, AG-UI runtime, frontend tools, shared state, and human-in-the-loop flows.

AI Frameworks

Claude Agent SDK

Anthropic's SDK for building agents on the same tools, agent loop, and context management that power Claude Code. Python and TypeScript. Subagents, hooks, MCP, and permissions.

AI Frameworks

LangChain / LangGraph

Most popular LLM framework. 100K+ GitHub stars. Chains, RAG, vector stores, tool use. LangGraph adds stateful multi-agent workflows with cycles and persistence.

AI Frameworks

Composio

Gives AI agents access to 1,000+ toolkits (GitHub, Slack, Gmail, databases) with managed OAuth. Handles the auth and API complexity so your agent doesn't have to.

AI Frameworks

OpenAI Agents SDK

Python and TypeScript framework for multi-agent workflows. Agent handoffs, tool use, guardrails, sessions, tracing. Provider-agnostic, supporting the OpenAI Responses and Chat Completions APIs plus 100+ other LLMs.

AI Frameworks

CrewAI

Multi-agent orchestration framework. Define agents with roles, goals, and tools, then assign them tasks in a crew. Python-based. Great for complex workflows.

AI Frameworks

Mastra

TypeScript-first AI agent framework. Agents, tools, memory, workflows, RAG, evals, tracing, MCP, and production deployment for Node.js apps.

AI Frameworks

ChatGPT

OpenAI's chat app. As of October 2026 Free and Go run GPT-6 Luna; Plus ($20/mo) adds GPT-6.1 Sol and GPT-6 Astra. Agent mode, Codex, image generation, code interpreter.

AI Models

DeepSeek V3.2

DeepSeek's reasoning-first model built for agents. First model to integrate thinking directly into tool use. Ships alongside V3.2-Speciale, which rivals GPT-5 and Gemini 3.0 Pro.

AI Models

Augment Code

AI coding platform built for large, complex codebases. Context Engine indexes 500K+ files across repos with 100ms retrieval. Intent desktop app orchestrates parallel agents.

AI Coding

Kimi Code

Open-source terminal coding agent from Moonshot AI. Launched on Kimi K2.5 and now runs Kimi K3 with up to 1M tokens of context. Agent Swarm runs up to 100 parallel sub-agents.

AI Coding

Droid

Factory AI's terminal coding agent. Runs Anthropic and OpenAI models in one subscription. Handles full tasks end-to-end - refactors, incident response, migrations.

AI Coding

Agency Swarm

Multi-agent orchestration framework built on the OpenAI Agents SDK. Define agent roles, typed tools, and directional communication flows. Production-focused, open-source.

AI Frameworks

Pydantic AI

Type-safe Python agent framework from the Pydantic team. Brings the FastAPI feeling to AI development. Composable tools, durable execution, and full IDE autocomplete.

AI Frameworks

Browser Harness

Self-healing browser automation harness that lets LLMs complete any browser task. 5,000+ stars in under a week.

Infrastructure

Claude Fable 5

Anthropic's first generally available Mythos-class model, released June 9, 2026. 1M context, 128K max output, $10/$50 per million tokens. Built for long-horizon agentic work.

AI Models

Claude Opus 4.8

Anthropic's Opus model released May 28, 2026, and its recommended default until Opus 5.5 shipped in September 2026. 1M context, 128K output, $5/$25 per million tokens.

AI Models

OpenCode

Open source

Open-source AI coding agent for terminal, desktop, and IDE. Works with 75+ LLM providers including Claude, GPT, Gemini, and local models. Runs parallel sessions on one project.

AI Coding

Jules

Google's asynchronous coding agent. Point it at a GitHub repo, it clones to a cloud VM, plans with Gemini, and opens a pull request. Tiered plans from 15 to 300 tasks per day.

AI Coding

Goose

Open source

Free, open-source (Apache-2.0) AI agent built in Rust, governed by the Agentic AI Foundation. Desktop app, CLI, and API. Bring any of 15+ model providers or an existing subscription.

AI Coding

Conductor

Mac app for running parallel Claude Code, Codex, and Cursor agents in isolated workspaces. Watch every agent work at once, then review and merge their changes.

AI Coding

E2B

Open source

Open-source cloud sandboxes that run each AI agent session in its own microVM. Isolated environments that start in under 200ms, run code in Python, JavaScript, and more, and persist sessions up to 24 hours.

Infrastructure

Guides

All guides →

Claude Code Setup Guide

Configure Claude Code for maximum productivity -- CLAUDE.md, sub-agents, MCP servers, and autonomous workflows.

Guide

Migrate from Cursor to Claude Code: Rules, MCP, Skills (2026)

Move from Cursor to Claude Code step by step: install, turn .cursor/rules into CLAUDE.md or AGENTS.md, port MCP servers and skills, and compare plan costs.

Guide