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.
| Date | Stars |
|---|---|
| 2026-07-31 | 501 |
| 2026-08-06 | 505 |
| 2026-08-14 | 512 |
| 2026-08-18 | 513 |
| 2026-08-25 | 514 |
| 2026-08-27 | 514 |
| 2026-08-28 | 514 |
| 2026-08-29 | 514 |
| 2026-08-30 | 514 |
| 2026-08-31 | 515 |
| 2026-09-01 | 515 |
| 2026-09-04 | 515 |
| 2026-09-05 | 516 |
| 2026-09-06 | 517 |
| 2026-09-09 | 518 |
| 2026-09-11 | 519 |
| 2026-09-13 | 518 |
| 2026-09-15 | 519 |
| 2026-09-16 | 520 |
| 2026-09-17 | 521 |
| 2026-09-18 | 522 |
| 2026-09-21 | 523 |
| 2026-09-23 | 523 |
| 2026-09-25 | 522 |
| 2026-09-26 | 524 |
| 2026-09-28 | 525 |
| 2026-10-02 | 526 |
| 2026-10-03 | 528 |
| 2026-10-05 | 526 |
| 2026-10-06 | 526 |
| 2026-10-08 | 526 |
| 2026-10-09 | 527 |
| 2026-10-10 | 527 |
| 2026-10-12 | 529 |
| 2026-10-13 | 529 |
| 2026-10-15 | 529 |
| 2026-10-16 | 529 |
| 2026-10-17 | 529 |
| 2026-10-18 | 530 |
| 2026-10-19 | 531 |
| 2026-10-20 | 531 |
| 2026-10-21 | 532 |
| 2026-10-24 | 533 |
| 2026-10-26 | 534 |
| 2026-10-29 | 535 |
| 2026-10-30 | 535 |
| 2026-10-31 | 536 |
| 2026-11-03 | 536 |
| 2026-11-04 | 536 |
Today
— stars today
This week
+2 stars this week
This month
+10 stars this month
Momentum
0.0
growth rate 0.38%/day
# Awesome Agent Harness [](https://awesome.re) > A curated list of tools, frameworks, and resources for **agent harness engineering** — the discipline of designing environments, constraints, and feedback loops that make AI coding agents reliable at scale. ## What is an Agent Harness? An agent harness is the infrastructure that wraps around an LLM coding agent. It's everything except the model itself: session management, context delivery, tool design, architectural enforcement, failure recovery, and human oversight. OpenAI's [Harness Engineering](https://openai.com/index/harness-engineering/) blog defined the term: *"When a software engineering team's primary job is no longer to write code, but to design environments, specify intent, and build feedback loops that allow agents to do reliable work."* Their team built 1M+ lines of production code with zero human-written lines using this approach. Anthropic's Claude Code team [discovered the same principles](https://x.com/trq212/status/2027463795355095314) from the tool design side: the harness matters more than the model. Fewer, more expressive tools beat a long menu of narrow ones. Progressive disclosure — letting the agent recursively discover context across layers — outperforms loading everything upfront. *"Designing an agent's action space is as much an art as it is a science."* ## Core Principles From the two seminal references above: 1. **Humans steer, agents execute** — Engineers design environments and review outcomes, not write code 2. **Repository knowledge is the system of record** — If it's not in the repo, it doesn't exist to the agent. Slack threads, Google Docs, and tribal knowledge are invisible 3. **AGENTS.md is a table of contents, not an encyclopedia** — Point to deeper sources of truth; don't dump everything in one file 4. **Enforce architecture mechanically** — Custom linters, structural tests, and CI checks replace code review for invariants 5. **Agent legibility is the goal** — Optimize code for agent readability first, human readability second 6. **Fewer tools, more expressiveness** — Progressive disclosure and composable primitives beat sprawling toolkits 7. **See like an agent** — Read the model's outputs, watch where it struggles, and evolve the harness accordingly 8. **Corrections are cheap, waiting is expensive** — At high agent throughput, fix-forward beats blocking merge gates ## Contents - [What is an Agent Harness?](#what-is-an-agent-harness) - [Core Principles](#core-principles) - [Full Lifecycle Platforms](#full-lifecycle-platforms) - [Agent Orchestrators](#agent-orchestrators) - [Task Runners](#task-runners) - [Agent Harness Frameworks](#agent-harness-frameworks) - [Agent Runtimes](#agent-runtimes) - [Agent Knowledge & Memory](#agent-knowledge--memory) - [Coding Agents](#coding-agents) - [Requirements & Spec Tools](#requirements--spec-tools) - [Standards & Protocols](#standards--protocols) - [Methodologies & Workflows](#methodologies--workflows) - [Reference & Knowledge](#reference--knowledge) - [Contributing](#contributing) ## Full Lifecycle Platforms Tools that span from requirements to delivery with human-in-the-loop approval. - [Chorus](https://github.com/Chorus-AIDLC/Chorus) — Agent harness for requirements-to-delivery. Task DAGs, sub-agent orchestration (Agent Teams), proof of work, human approval gates. AI proposes, humans verify. <p align="center"><video src="https://github.com/AutoJunjie/awesome-agent-harness/edit/main/demo.mp4" controls></video></p> - [GitHub Agentic Workflows](https://github.blog/ai-and-ml/automate-repository-tasks-with-github-agentic-workflows/) — GitHub Actions with coding agent engines (Copilot, Claude Code, Codex). Issue → agent → PR with sandboxing and permissions. - [Almirant](https://almirant.ai/?utm_source=awesome-agent-harness&utm_medium=awesome-list&utm_campaign=march-2026) — Operating system for human-agent teams. Persistent context across sessions, sha
Excerpt of 29,200 characters
Read on GitHub
15
2
2
1
1
Would you bet a product on this? Bounded 0–100 and slow moving.
matched fp:09d50920e03ea3c0, topic:ai-agents, topic:multi-agent
matched fp:09d50920e03ea3c0, topic:developer-tools
matched fp:09d50920e03ea3c0, topic:awesome, topic:awesome-list
