Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Better Harness turns project and session evidence into loop-level insights, prioritized improvements, and verifiable next steps—inside the coding agent you already use.
| Date | Stars |
|---|---|
| 2026-07-31 | 1225 |
| 2026-08-01 | 1365 |
| 2026-08-06 | 1365 |
Today
— stars today
This week
— stars this week
This month
— stars this month
Momentum
0.0
growth rate 0.00%/day
<h1 align="center">Better Harness</h1> <p align="center"> English · <a href="README.zh-CN.md">简体中文</a> </p> <p align="center"> <strong>Delegate coding to agents. Improve the loop around them.</strong> </p> <p align="center"> Better Harness provides open-source insights for the Agent Work Loop. It runs through your Coding Agent and turns project and session evidence into prioritized improvements and verifiable next steps. Missing evidence stays explicit. </p> <p align="center"> <a href="LICENSE"><img src="https://img.shields.io/badge/license-MIT-blue.svg" alt="MIT License"></a> </p> <p align="center"> <a href="https://qoderai.github.io/better-harness/?utm_source=github&utm_medium=referral&utm_campaign=repository_landing&utm_content=readme_hero">Website</a> · <a href="#quick-start">Choose your host</a> · <a href="#see-it-in-action">Sample report</a> · <a href="https://qoderai.github.io/better-harness/docs/introduction">Docs</a> </p> ## Quick start Analyze and improve your coding workflow with: [Claude Code](#claude-code), [Codex Desktop](#codex-desktop), [Codex CLI](#codex-cli), [Qoder Desktop/CLI](#qoder), [Cursor](#cursor), [Qwen Code](#qwen-code), or [GitHub Copilot CLI](#github-copilot). Choose the host you already use to get its exact installation, verification, invocation, and report-output steps. Better Harness does not use one universal entrypoint across every host. The canonical registry covers eight host adapters. Pi and WorkBuddy currently remain adapter-support entries rather than part of the six-host verified Quickstart; see the [public Host Adapter Matrix](docs/docs/hosts/adapter-matrix.md) for their explicit boundaries. Better Harness scopes behavior claims to relevant Task Episodes and the surrounding project mechanisms. Qoder and Cursor produce host-native Canvas reports; Claude Code, Codex, Qwen Code, and GitHub Copilot produce self-contained HTML with paired Markdown. Missing or partial evidence remains explicit. See the [Host Adapter Matrix](docs/adapters/README.md) for current coverage and output differences. ## See it in action The report keeps missing evidence explicit and turns supported gaps into prioritized findings with an impact, expected output, scoped repair, and acceptance checks. <p align="center"> <a href="https://qoderai.github.io/better-harness/demo/better-harness-report/"><img src="assets/demo/better-harness-findings-report.png" alt="Better Harness HTML report showing an evidence-bounded finding with its impact, expected output, scoped AI fix, and acceptance checks" width="900"></a> </p> <p align="center"> <sub><a href="https://qoderai.github.io/better-harness/demo/better-harness-report/">Open the complete self-contained English HTML report</a> (<a href="assets/demo/better-harness-report.html">source</a>).</sub> </p> After you have comparable reports over time, the history view shows how the five Agent Work Loop dimensions move: <p align="center"> <a href="dev/terminal-demo/README.md"><img src="assets/demo/twenty-history.png" alt="Static final frame of Better Harness report history showing five Agent Work Loop dimensions over time" width="900"></a> </p> The static final frame summarizes historical Harness reports. It shows recorded trends, not causal proof of improvement. [See how the demo was recorded](dev/terminal-demo/README.md). ## Why Better Harness? AI coding agents change code fast, but the workflow around them is often the weak point: - 🎯 **Fuzzy goals** — the agent confidently solves the wrong problem. - 🧭 **Improvised steps** — work happens on paths nobody can reproduce. - ✅ **"It works" without proof** — validation is incomplete or missing. - 🚢 **Speed over safeguards** — review and delivery checks get bypassed. - 🧠 **Lessons lost** — the same friction comes back on the next task. Reviewing only the final diff misses these system-level problems. Better Harness analyzes the workflow around the diff: it gathers project evidence (and
Excerpt of 17,267 characters
Read on GitHub
Fengda Huang · ex-@Thoughtworks @qoderai · China
94
8
6
5
5
3
3
2
2
2
1
1
1
1
CoderMageFox · @RiPoAI
1
1
1
1
1
1
Would you bet a product on this? Bounded 0–100 and slow moving.
matched fp:29c4aabfd70f370c, llm:Repository description and topics: 'Help your coding agents (Claude Code, Codex, Qoder, Cursor, and other coding agents) get better at getting better.' Topics include agent-plugin, harness-design, harness-engineering, loop-engineering, skill, claude-code, codex, cursor, qoder.
matched fp:29c4aabfd70f370c, llm:Repository description and topics: 'Help your coding agents (Claude Code, Codex, Qoder, Cursor, and other coding agents) get better at getting better.' Topics include agent-plugin, harness-design, harness-engineering, loop-engineering, skill, claude-code, codex, cursor, qoder.
matched fp:29c4aabfd70f370c, llm:Repository description and topics: 'Help your coding agents (Claude Code, Codex, Qoder, Cursor, and other coding agents) get better at getting better.' Topics include agent-plugin, harness-design, harness-engineering, loop-engineering, skill, claude-code, codex, cursor, qoder.