Skip to content

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

Add OpenSRE to Demo Harnesses section

Adrian Vale10dda07ee63a
diff --git a/README.md b/README.md
index dd2f30e..a0d2d1e 100644
--- a/README.md
+++ b/README.md
@@ -424,6 +424,7 @@ Real repositories worth studying — each with a note on *why* it's worth your t
- [Anthropic Computer Use Demo](https://github.com/anthropics/anthropic-quickstarts/tree/main/computer-use-demo) — Anthropic's reference harness for the screenshot-action loop: defines the `screenshot`, `bash`, and `text_editor` tool interface that makes desktop/browser control work. Essential reading before building any harness where the agent's primary sensory input is a rendered screen rather than structured API responses. ![Stars](https://img.shields.io/github/stars/anthropics/anthropic-quickstarts?style=flat-square&label=★&color=yellow)
- [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)
+- [OpenSRE](https://github.com/Tracer-Cloud/opensre) — Open-source framework for building AI SRE agents with 60+ observability and remediation tool integrations plus a synthetic incident evaluation environment. The clearest open-source reference for turning infrastructure incident response into a trainable, evaluable agent harness rather than a one-off chatbot. ![Stars](https://img.shields.io/github/stars/Tracer-Cloud/opensre?style=flat-square&label=★&color=yellow)
- [Goose](https://github.com/aaif-goose/goose) — Block's open-source, extensible AI agent donated to the Linux Foundation's Agentic AI Foundation in April 2026. Its MCP-native architecture treats every capability as an MCP server, making it a practical reference for building vendor-neutral, extensible harnesses where tool integration is the primary extension mechanism rather than framework-specific plugins. ![Stars](https://img.shields.io/github/stars/aaif-goose/goose?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)