# Awesome-Agent-Harness — Survey of Agent Harnesses
> A curated survey-style list for agent harness evaluation and tooling, useful as a reading map; verified 199★, pushed 2026-05-14.
## Install
Copy the content below into your project:
## Quick Use
```markdown
1) Open the repo README
2) Search for the harness/tool category you need
3) Follow links to primary sources and compare tradeoffs
```
## Intro
A curated survey-style list for agent harness evaluation and tooling, useful as a reading map; verified 199★, pushed 2026-05-14.
**Best for:** Agent builders who want a grounded reading list for harness design and evaluation
**Works with:** Any stack; this is a survey/awesome list you can browse and cite in docs
**Setup time:** 2-5 minutes
### Key facts (verified)
- GitHub: 199 stars · 6 forks · pushed 2026-05-14.
- License: CC-BY-4.0 · owner avatar + repo URL verified via GitHub API.
- README-backed entrypoint: `Open README`.
## Main
- Use it as a sourcing index: jump from the list to primary papers/repos, then build your own benchmark set.
- Extract evaluation dimensions: turn repeated criteria into a checklist for your harness (context, tools, memory, safety).
- Keep a local notes file: for each referenced harness, record setup time, supported tools, and failure modes.
- Prefer primary citations: when copying claims into docs, link to the original repo/paper, not a secondary summary.
### README (excerpt)
[English](README.md) | [中文](README_zh.md)
**Agent Harness for Large Language Model Agents: A Survey**
[](https://github.com/Gloriaameng/LLM-Agent-Harness-Survey/stargazers)
[](LICENSE)
[]()
[]()
[](https://huggingface.co/datasets/GloriaaaM/LLM-Agent-Harness-Survey)
[](https://doi.org/10.20944/preprints202604.0428.v3)
> ⭐ **This repo is actively maintained. If you find it useful, please star the repo to stay updated and help others find it.**
---
> **The agent execution harness — not the model — is the primary determinant of agent reliability at scale.**
> This survey formalizes the harness as a first-class architectural object **H = (E, T, C, S, L, V)**, surveys 110+ papers, blogs and reports across 23 systems, and maps 9 open technical challenges.
> 📄 **[Read the Paper](./Agent_Harness_for_LLM_Agents__A_Survey_v3.pdf)**
> 🌐 **[Preprints Version (v3)](https://www.preprints.org/manuscript/202604.0428/v3)**
> ✉️ Corrections & suggestions: gloriamenng@gmail.com (Qianyu Meng); wangyanan@mail.dlut.edu.cn (Yanan Wang); chenliyi@xiaohongshu.com (Liyi Chen)
If you find this survey useful, please cite:
```bibtex
@article{meng2026agentharness,
title = {Agent Harness for Large Language Model Agents: A Survey},
author = {Meng, Qianyu and Wang, Yanan and Chen, Liyi and Wu, Wei and
Li, Yihang and Jiang, Wenyuan and Wang, Qimeng and
Lu, Chengqiang and Gao, Yan and Wu, Yi and Hu, Yao},
year = {2026},
doi = {10.20944/preprints202604.0428.v3},
url = {https://www.preprints.org/manuscript/202604.0428/v3},
### Source-backed notes
- The repo is CC-BY-4.0 licensed (verified via GitHub API).
- GitHub API verification confirms the repo URL and recent push date.
- README functions as a curated survey/reading map (content is primarily links and structure).
### FAQ
- **Is it an implementation?**: No—it's primarily a survey/awesome list to help you find harness tools and papers.
- **Can I reuse content?**: Yes—license is CC-BY-4.0; attribute appropriately when reusing text.
- **How do I turn it into action?**: Pick 3–5 harnesses, run the same questions/tasks, and record results as your baseline benchmark.
## Source & Thanks
> Created by [Gloriaameng](https://github.com/Gloriaameng). Licensed under CC-BY-4.0.
>
> [Gloriaameng/Awesome-Agent-Harness](https://github.com/Gloriaameng/Awesome-Agent-Harness) — ⭐ 199
Thanks to the upstream maintainers and contributors for publishing this work under an open license.
---
## Quick Use
```markdown
1) Open the repo README
2) Search for the harness/tool category you need
3) Follow links to primary sources and compare tradeoffs
```
## Intro
Awesome-Agent-Harness 是面向 agent harness 评测与工具链的综述/清单，可作为阅读路线图与选型索引并便于引用；已验证 199★，更新于 2026-05-14。
**Best for:** 想系统了解 harness 设计与评测方法的 agent 开发者
**Works with:** 与技术栈无关：这是一份综述/清单，适合用来浏览与引用
**Setup time:** 2-5 minutes
### Key facts (verified)
- GitHub：199 stars · 6 forks；最近更新 2026-05-14。
- 许可证：CC-BY-4.0；作者头像与仓库链接均已通过 GitHub API 复核。
- README 中可对照的入口：`Open README`。
## Main
- 把它当索引用：从清单跳到一手论文/仓库，再整理出你自己的基准测试集合。
- 提炼评测维度：把重复出现的指标沉淀成 checklist（上下文、工具、记忆、安全）。
- 做一份本地笔记：对每个 harness 记录 setup time、工具支持范围、常见失败模式。
- 引用尽量直达一手来源：写文档时尽量链接原仓库/论文，而不是二手总结。
### README (excerpt)
[English](README.md) | [中文](README_zh.md)
**Agent Harness for Large Language Model Agents: A Survey**
[](https://github.com/Gloriaameng/LLM-Agent-Harness-Survey/stargazers)
[](LICENSE)
[]()
[]()
[](https://huggingface.co/datasets/GloriaaaM/LLM-Agent-Harness-Survey)
[](https://doi.org/10.20944/preprints202604.0428.v3)
> ⭐ **This repo is actively maintained. If you find it useful, please star the repo to stay updated and help others find it.**
---
> **The agent execution harness — not the model — is the primary determinant of agent reliability at scale.**
> This survey formalizes the harness as a first-class architectural object **H = (E, T, C, S, L, V)**, surveys 110+ papers, blogs and reports across 23 systems, and maps 9 open technical challenges.
> 📄 **[Read the Paper](./Agent_Harness_for_LLM_Agents__A_Survey_v3.pdf)**
> 🌐 **[Preprints Version (v3)](https://www.preprints.org/manuscript/202604.0428/v3)**
> ✉️ Corrections & suggestions: gloriamenng@gmail.com (Qianyu Meng); wangyanan@mail.dlut.edu.cn (Yanan Wang); chenliyi@xiaohongshu.com (Liyi Chen)
If you find this survey useful, please cite:
```bibtex
@article{meng2026agentharness,
title = {Agent Harness for Large Language Model Agents: A Survey},
author = {Meng, Qianyu and Wang, Yanan and Chen, Liyi and Wu, Wei and
Li, Yihang and Jiang, Wenyuan and Wang, Qimeng and
Lu, Chengqiang and Gao, Yan and Wu, Yi and Hu, Yao},
year = {2026},
doi = {10.20944/preprints202604.0428.v3},
url = {https://www.preprints.org/manuscript/202604.0428/v3},
### Source-backed notes
- 仓库为 CC-BY-4.0 许可（已通过 GitHub API 复核）。
- GitHub API 已复核仓库链接与最近更新时间。
- README 主要是结构化清单/综述式索引（以链接与分类为主）。
### FAQ
- **这是实现代码吗？**：不是：主要是综述/清单，用来快速定位 harness 工具与论文。
- **内容能复用吗？**：可以：许可证为 CC-BY-4.0，复用时请按要求署名。
- **怎么落地？**：选 3–5 个 harness，用同一套任务集跑一遍并记录结果，形成你的基准。
## Source & Thanks
> Created by [Gloriaameng](https://github.com/Gloriaameng). Licensed under CC-BY-4.0.
>
> [Gloriaameng/Awesome-Agent-Harness](https://github.com/Gloriaameng/Awesome-Agent-Harness) — ⭐ 199
---
Source: https://tokrepo.com/en/workflows/awesome-agent-harness-survey-of-agent-harnesses
Author: AI Open Source