GitHub repo leaderboard by stars, growth rate and activity.
Enterprise-grade, local-first Agent Workbench for people and agent teams. A unified multi-engine workspace for Codex Harness, DeepSeek Harness, and OpenCode, with unified plugins and Skills, multi-agent projects and tasks, and editable code, documents, presentations, design, and video.
现代化可灵活嵌入的任务面板,支持 Codex、DeepSeek Harness
Stop That Shit(别再造史了)|面向 Codex/GPT 场景的多平台 Hook + Skill Guard:拦截 AI coding agent 无需求的哈希、校验和与任务范围膨胀。 A multi-platform Hook + Skill Guard for AI coding agents in Codex/GPT workflows: stop unrequested hashes, checksums, and task-scope creep.
The long-horizon computer-use harness. Run AI agents across desktop apps and the CLI for extended periods while preserving task state and making reliable progress on complex workflows. Features fresh-context execution, durable verified state, independent auditing, recoverable progress, and native Claude Code / Codex / OpenClaw integration.
Lightweight Codex/Claude loop harness with strict evidence gates.
将参考图片离线描摹为纯 HTML + CSS 单文件插画的 Agent 插件,支持轮廓提取、局部渐变与输出审计。
| # | Repo | Language | Stars | 30-day trend | Last updated |
|---|---|---|---|---|---|
| 1 | Enterprise-grade, local-first Agent Workbench for people and agent teams. A unified multi-engine workspace for Codex Harness, DeepSeek Harness, and OpenCode, with unified plugins and Skills, multi-agent projects and tasks, and editable code, documents, presentations, design, and video. | TypeScript | 5,670 | last pushed 2 days ago | |
| 2 | 现代化可灵活嵌入的任务面板,支持 Codex、DeepSeek Harness | JavaScript | 3,020 | last pushed 3 days ago | |
| 3 | Stop That Shit(别再造史了)|面向 Codex/GPT 场景的多平台 Hook + Skill Guard:拦截 AI coding agent 无需求的哈希、校验和与任务范围膨胀。 A multi-platform Hook + Skill Guard for AI coding agents in Codex/GPT workflows: stop unrequested hashes, checksums, and task-scope creep. | JavaScript | 1,843 | last pushed 4 days ago | |
| 4 | The long-horizon computer-use harness. Run AI agents across desktop apps and the CLI for extended periods while preserving task state and making reliable progress on complex workflows. Features fresh-context execution, durable verified state, independent auditing, recoverable progress, and native Claude Code / Codex / OpenClaw integration. | Python | 1,485 | last pushed 3 weeks ago | |
| 5 | Lightweight Codex/Claude loop harness with strict evidence gates. | JavaScript | 107 | last pushed Yesterday | |
| 6 | 将参考图片离线描摹为纯 HTML + CSS 单文件插画的 Agent 插件,支持轮廓提取、局部渐变与输出审计。 | Python | 87 | last pushed Yesterday |
All · 11,474