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.
🔁 Improve your agent harness autonomously overnight
| Date | Stars |
|---|---|
| 2026-07-31 | 300 |
| 2026-08-05 | 301 |
| 2026-08-06 | 301 |
Today
— stars today
This week
— stars this week
This month
— stars this month
Momentum
0.0
growth rate 0.00%/day
<p align="center">
<img src="docs/images/harness_on_harness2.png" alt="autoharness banner" width="900">
</p>
<p align="center">
<a href="https://discord.com/invite/mqCqH7sTyK">
<img src="https://img.shields.io/discord/1429935408145236131?label=Discord&logo=discord&logoColor=white&color=5865F2" alt="Discord">
</a>
<a href="https://x.com/kaybaai">
<img src="https://img.shields.io/twitter/follow/kaybaai?style=social" alt="Twitter Follow">
</a>
<a href="https://kayba.ai">
<img src="https://img.shields.io/badge/kayba.ai-0B1220?style=flat&labelColor=0B1220&color=0B1220" alt="kayba.ai">
</a>
<img src="https://img.shields.io/badge/license-MIT-16a34a" alt="MIT license">
<img src="https://img.shields.io/badge/python-3.11%2B-3776AB?logo=python&logoColor=white" alt="Python 3.11+">
<img src="https://img.shields.io/badge/Codex-supported-2563EB" alt="Codex supported">
<img src="https://img.shields.io/badge/Claude%20Code-supported-2563EB" alt="Claude Code supported">
</p>
# autoharness
Let autoharness run overnight and come back to an optimized agent harness, so your production agents never make mistakes again.
autoharness improves agent harnesses by proposing or applying prompt, config, middleware, and source changes, running evals, and keeping or discarding candidates based on benchmark results.
It is a control plane for an existing harness repo. You point it at a target root and a benchmark command; autoharness manages proposals, iterations, campaigns, and champion state under `.autoharness/`.
## Install
Fastest setup with Codex or Claude:
1. `pipx install "git+https://github.com/kayba-ai/autoharness.git"`
2. `cd` into your harness repo
3. open Codex or Claude Code in that repo
4. tell the assistant: `Run autoharness guide --assistant codex --print-next-prompt, then use the generated onboarding packet to finish setup.`
For Claude Code, swap `--assistant codex` for `--assistant claude`.
Else:
```bash
pipx install "git+https://github.com/kayba-ai/autoharness.git"
autoharness --help
```
If you do not use `pipx`:
```bash
python3 -m pip install --user "git+https://github.com/kayba-ai/autoharness.git"
```
## How It Works
- `guide` inspects a repo, asks a few focused setup questions in a TTY, stays scriptable with flags in non-interactive use, writes a starter `autoharness.yaml` plus benchmark config, and runs a readiness check.
- `doctor` reruns config, generator, and benchmark validation when you want an explicit readiness gate.
- `setup` and `init` remain available when you want to manage bootstrap explicitly.
- `run-benchmark` executes one benchmark directly.
- `generate-proposal` previews one candidate change without running it.
- `run-iteration` or `optimize` executes one candidate or a resumable search loop.
- `promote` or `promote-from-compare` moves a winner into champion state.
## Mental Model
- `target root`: the harness repo or deployment tree to edit
- `benchmark config`: the command or adapter config that scores candidates
- `workspace`: the long-lived optimization effort
- `track`: one comparable lane inside a workspace
- `campaign`: a resumable search run over candidate proposals
- `.autoharness/`: persisted settings, proposals, records, iterations, and champions
## Batteries Included
- Adapters: `generic_command`, `pytest`, `harbor`, `tau2_bench`, `hal`, `car_bench`
- Proposal generators: `manual`, `failure_summary`, `local_template`, `local_command`, `openai_responses`, `codex_cli`, `claude_code`
- Extension model: Python plugins can add generators, preflight checks, and search strategies from `.autoharness/plugins/` or `AUTOHARNESS_PLUGIN_PATHS`
## Quick Start
Let autoharness generate a starter project config:
```bash
autoharness guide
```
In a TTY, `guide` asks a few setup questions. In scripts or CI, use flags like `--non-interactive`, `--benchmark-command`, `--generator`, and `--autonomy`.
If you want Codex or Claude to help you refine the setup, generate an assistanExcerpt of 6,558 characters
Read on GitHubWould you bet a product on this? Bounded 0–100 and slow moving.
matched fp:0a1013d883be9c2d, llm:Repository description: '🔁 Improve your agent harness autonomously overnight' (no topics provided).
matched fp:0a1013d883be9c2d, llm:Repository description: '🔁 Improve your agent harness autonomously overnight' (no topics provided).
matched fp:0a1013d883be9c2d, llm:Repository description: '🔁 Improve your agent harness autonomously overnight' (no topics provided).