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.
Official AHE code — Agentic Harness Engineering: observability-driven automatic evolution of coding-agent harnesses (concurrent w/ meta-harness). NexAU-AHE reaches 84.7% ± 2.1 pass@1 on Terminal-Bench 2 (GPT-5.5). Lifts GPT-5.4 69.7→77.0% over 10 iters, beats Codex/ACE/Training-Free GRPO; frozen harness transfers to SWE-bench-Verified.
| Date | Stars |
|---|---|
| 2026-07-31 | 786 |
| 2026-08-06 | 786 |
Today
— stars today
This week
— stars this week
This month
— stars this month
Momentum
0.0
growth rate 0.00%/day
# Agentic Harness Engineering: Observability-Driven Automatic Evolution of Coding-Agent Harnesses <div align="left"> <p align="left"> <a href="https://arxiv.org/abs/2604.25850"><img alt="Paper" src="https://img.shields.io/badge/Paper-arXiv-b31b1b.svg?logo=arxiv&logoColor=white"></a> <a href="agentic_harness_engineering.pdf"><img alt="PDF" src="https://img.shields.io/badge/PDF-Download-ec1c24.svg?logo=adobeacrobatreader&logoColor=white"></a> <a href="https://dawning-road.github.io/blog/agentic-harness-engineering"><img alt="Blog" src="https://img.shields.io/badge/Blog-Dawning_Road-ff7e1b.svg?logo=readthedocs&logoColor=white"></a> <img alt="License: MIT" src="https://img.shields.io/badge/License-MIT-yellow.svg"> <img alt="Python" src="https://img.shields.io/badge/python-%E2%89%A53.13-blue.svg"> <img alt="Managed with uv" src="https://img.shields.io/badge/managed_with-uv-261230?logo=python&logoColor=white"> </p> </div> <p align="center"> <img src="assets/figures/banner.jpg" alt="Agentic Harness Engineering" width="100%"> </p> <p align="left"> English | <a href="README_zh.md">简体中文</a> </p> --- ## 📰 News - **[2026-05-14]** 🏆 AHE (on GPT-5.5) ranked **#3** on the [Terminal-Bench 2.0 leaderboard](https://www.tbench.ai/leaderboard/terminal-bench/2.0) with **84.7%** — ranking as of 2026-05-15 - **[2026-04-30]** ✍️ Blog post on Dawning Road (English & Chinese) — a more detailed account of the exploration behind AHE: [Agentic Harness Engineering](https://dawning-road.github.io/blog/agentic-harness-engineering) - **[2026-04-28]** 📄 Paper released on arXiv: [Agentic Harness Engineering: Observability-Driven Automatic Evolution of Coding-Agent Harnesses](https://arxiv.org/abs/2604.25850) - **[2026-04]** 🎉 Framework released --- ## 🎯 Overview **AHE (Agentic Harness Engineering)** is an open **observability system** for automatically evolving the harness around a coding agent. The base model is held fixed; what evolves are the harness components — system prompts, tool descriptions, tool implementations, middleware, skills, sub-agents, and long-term memory. AHE rests on three observability layers: - **Component observability** — [**NexAU**](https://github.com/nex-agi/NexAU.git) decomposes the harness into seven orthogonal, file-level components, each git-tracked so every edit is auditable and revertible. - **Experience observability** — *Agent Debugger* distills ~10M-token raw traces into layered, sourced reports; the optimizer reads digests by default but can always drill back to any rollout's raw trace. - **Decision observability** — *Evolve Agent* proposes evidence-backed edits, predicts their impact, and is automatically falsified by the next iteration's flipped tasks. Across ten `evaluate → analyze → improve` iterations, **AHE (Agentic Harness Engineering)** lifts Terminal-Bench 2 pass@1 from **69.7% to 77.0%** on GPT-5.4, surpasses the hand-written Codex (71.9%) and the self-evolving ACE and TF-GRPO baselines, and produces a frozen harness that transfers without re-evolution to SWE-bench-verified and to four alternate base models, indicating that the evolved components encode general engineering experience rather than benchmark-specific tuning. <p align="center"> <img src="assets/figures/transfer_model.png" alt="Cross-Model Transfer" width="28%"> <img src="assets/figures/case_study.png" alt="Case Study" width="31%"> <img src="assets/figures/training_curve.png" alt="Training Curve" width="39%"> </p> --- ## 🚀 Quick Start ### 0. Prerequisites - Python ≥ 3.13 - [uv](https://docs.astral.sh/uv/) - tmux ```bash # macOS brew install uv tmux # Linux curl -LsSf https://astral.sh/uv/install.sh | sh sudo apt install -y tmux ``` ### 1. Clone + install dependencies ```bash git clone https://github.com/Curry09/agentic-harness-engineering.git cd agentic-harness-engineering uv sync ``` > `uv sync` installs every dependency declared in `pyproject.toml`. ### 2. Configure environment variables ```bash cp
Excerpt of 15,559 characters
Read on GitHub
44
2
1
Would you bet a product on this? Bounded 0–100 and slow moving.
matched fp:3cc9c2da62a1ae9b, name:agentic, desc:agentic