Skip to content

Awesome list for AI agent harness engineering: tools, patterns, evals, memory, MCP, permissions, observability, and orchestration.

Add browser-harness: self-healing browser harness where the agent edits its own scaffold during execution

ai-boost348efc1d9374
diff --git a/README.md b/README.md
index ebb8b12..8eba55e 100644
--- a/README.md
+++ b/README.md
@@ -338,6 +338,7 @@ Real repositories worth studying — each with a note on *why* it's worth your t
- [coleam00/your-claude-engineer](https://github.com/coleam00/your-claude-engineer) — Agent harness with Slack, GitHub, and Linear integrations. Useful reference for how real-world tool wiring works inside a harness. ![Stars](https://img.shields.io/github/stars/coleam00/your-claude-engineer?style=flat-square&label=★&color=yellow)
- [OpenHands](https://github.com/OpenHands/OpenHands) — The most architecturally complete open-source coding agent: Runtime/Sandbox isolation, EventStream message bus, and Agent Controller are a three-layer harness design worth studying for production deployments. ![Stars](https://img.shields.io/github/stars/OpenHands/OpenHands?style=flat-square&label=★&color=yellow)
- [browser-use](https://github.com/browser-use/browser-use) — Minimal browser-automation agent harness with clean separation of tool registration, DOM state injection, action loop, and error recovery. Small codebase, clear structure — the best "minimal viable harness" reference for understanding core loop mechanics. ![Stars](https://img.shields.io/github/stars/browser-use/browser-use?style=flat-square&label=★&color=yellow)
+- [browser-harness](https://github.com/browser-use/browser-harness) — Self-healing browser harness that connects an LLM directly to your real Chrome via CDP. The critical design decision: the agent itself writes missing helpers and domain skills into the harness during execution, so the scaffold improves every run rather than requiring manual updates. At ~1k lines across four core files, it is the clearest published demonstration of an editable harness that learns from its own failures. ![Stars](https://img.shields.io/github/stars/browser-use/browser-harness?style=flat-square&label=★&color=yellow)
- [SWE-agent](https://github.com/SWE-agent/SWE-agent) — Coding agent whose Agent-Computer Interface (ACI) — purpose-built file viewer, search, and editor tools with explicit state constraints and error feedback — is the reference design for adapting a tool interface to a specific task domain rather than using generic bash. ![Stars](https://img.shields.io/github/stars/SWE-agent/SWE-agent?style=flat-square&label=★&color=yellow)
- [Aider](https://github.com/Aider-AI/aider) — AI pair-programmer harness with an Architect mode that splits planning (one LLM) from coding (another), and git-aware tooling that uses version control as the undo mechanism instead of custom state rollback. The best reference for multi-file editing tool design and planner/coder layer separation. ![Stars](https://img.shields.io/github/stars/Aider-AI/aider?style=flat-square&label=★&color=yellow)
- [Open SWE: An Open-Source Framework for Internal Coding Agents](https://blog.langchain.com/open-swe-an-open-source-framework-for-internal-coding-agents/) — A composable coding-agent harness built on Deep Agents, synthesizing design patterns from Stripe, Ramp, and Coinbase production deployments. Key decisions: curated ~15-tool limit enforced at harness design time, one isolated sandbox (Modal/Daytona/Runloop/LangSmith) per task, AGENTS.md for injecting repo-wide conventions, and Linear/Slack task context in the system prompt. The most recent published reference for what a production internal coding agent harness looks like.