Skip to content

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

Fix stars badge for stanford-iris-lab/meta-harness entry

Claude Code05916577219f
diff --git a/README.md b/README.md
index bba9163..024ce51 100644
--- a/README.md
+++ b/README.md
@@ -318,7 +318,7 @@ Real repositories worth studying — each with a note on *why* it's worth your t
- [AutoAgent](https://github.com/kevinrgu/autoagent) — Open-source library (April 2026) that automates the harness engineering loop itself: give it a task and a benchmark, and it iterates overnight on system prompts, tool configurations, agent orchestration, and routing — keeping or discarding each change based on score. In a 24-hour run, hit #1 on SpreadsheetBench (96.5%) and the top GPT-5 score on TerminalBench (55.1%), beating every hand-engineered entry. The `program.md` separation of concerns (human writes the directive, agent engineers the harness) is the most practical meta-harness pattern published so far. ![Stars](https://img.shields.io/github/stars/kevinrgu/autoagent?style=flat-square&label=★&color=yellow)
- [metaharness](https://github.com/SuperagenticAI/metaharness) — Open-source Python library (April 2026) that implements an outer optimization loop around executable harnesses for coding agents. Inspired by the Meta-Harness paper, it treats `AGENTS.md`, setup scripts, validation logic, and test flows as optimizable artifacts rather than static configs — with filesystem-backed run stores, environment snapshots, and scoped write enforcement. The most practical reference for teams who want to improve harness *code* rather than just prompts. ![Stars](https://img.shields.io/github/stars/SuperagenticAI/metaharness?style=flat-square&label=★&color=yellow)
- [meta-agent](https://github.com/canvas-org/meta-agent) — Lightweight continual harness optimizer (April 2026) built on the Claude Agent SDK. Runs an outer loop that reads task traces, rewrites harness configs, and re-evaluates — achieving 67% → 87% on tau-bench with no labeled training data. Demonstrates that even small, focused meta-harness loops can yield large reliability gains when harness configs are treated as learnable parameters.
-- [stanford-iris-lab/meta-harness](https://github.com/stanford-iris-lab/meta-harness) — April 2026 official implementation of the Meta-Harness paper from Stanford's IRIS Lab. Provides the framework and two reference experiments for end-to-end harness optimization via filesystem-backed search loops where a coding agent proposes, evaluates, and refines harness artifacts. The cleaned-up codebase is the definitive starting point for researchers reproducing or extending meta-harness optimization. ![Stars](https://img.shields.io/github/stars/canvas-org/meta-agent?style=flat-square&label=★&color=yellow)
+- [stanford-iris-lab/meta-harness](https://github.com/stanford-iris-lab/meta-harness) — April 2026 official implementation of the Meta-Harness paper from Stanford's IRIS Lab. Provides the framework and two reference experiments for end-to-end harness optimization via filesystem-backed search loops where a coding agent proposes, evaluates, and refines harness artifacts. The cleaned-up codebase is the definitive starting point for researchers reproducing or extending meta-harness optimization. ![Stars](https://img.shields.io/github/stars/stanford-iris-lab/meta-harness?style=flat-square&label=★&color=yellow)
### Demo Harnesses