GitHub Open Source Insight
Computed at Sep 11, 2026GitHub repo leaderboard by stars, growth rate and activity.
lobehub
🤯 LobeHub is your Chief Agent Operator, organizing your agents into 7×24 operations by hiring, scheduling, and reporting on your entire AI team.
TypeScript82,364 starslast pushed 23 hours agoagentscope-ai
Your Personal AI Assistant; easy to install, deploy on your own machine or on the cloud; supports multiple chat apps with easily extensible capabilities.
Python34,723 starslast pushed 23 hours agoNevaMind-AI
cobusgreyling
Practical patterns, starters & CLI tools for loop engineering with AI coding agents. Design systems that prompt and orchestrate agents (inspired by Addy Osmani and Boris Cherny). Includes loop-audit, loop-init, loop-cost.
TypeScript11,132 starslast pushed 24 hours agoQ00
Agent OS: the agent gets smarter on its own. We just hold the line: Interview-gated, staged evaluation, budgeted evolution loop. MCP server, 14 runtimes: Claude Code, Codex CLI, Gemini CLI, OpenCode, Copilot, Kiro and more.
Python5,803 starslast pushed Yesterdayhuangruiteng
Long-horizon agent control plane for durable, governed work across Codex, Claude Code, and other harnesses.
Python5,766 starslast pushed 23 hours agoYTwsy
Surge-style whole-home gateway and control plane for macOS with IPv4/IPv6 support— mihomo TUN, dnsmasq-powered DHCP/DNS, per-device routing, and an agent-friendly validation workspace.
Go2,344 starslast pushed 4 days agoQoderAI
An open-source Harness Engineering platform for coding agents—define harnesses as code, run controlled experiments, inspect evidence, and compare outcomes. Turn task evidence into actionable team and organization insights.
JavaScript2,198 starslast pushed Yesterdaythe-open-engine
Independent executor–verifier orchestration for software changes.
Rust1,828 starslast pushed 2 days agoAMAP-ML
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.
Python1,485 starslast pushed 3 weeks ago
| # | Repo | Language | Stars | 30-day trend | Last updated |
|---|---|---|---|---|---|
| 1 | lobehub 🤯 LobeHub is your Chief Agent Operator, organizing your agents into 7×24 operations by hiring, scheduling, and reporting on your entire AI team. | TypeScript | 82,364 | last pushed 23 hours ago | |
| 2 | agentscope-ai Your Personal AI Assistant; easy to install, deploy on your own machine or on the cloud; supports multiple chat apps with easily extensible capabilities. | Python | 34,723 | last pushed 23 hours ago | |
| 3 | NevaMind-AI Personal memory across agents | Python | 14,403 | last pushed Yesterday | |
| 4 | cobusgreyling Practical patterns, starters & CLI tools for loop engineering with AI coding agents. Design systems that prompt and orchestrate agents (inspired by Addy Osmani and Boris Cherny). Includes loop-audit, loop-init, loop-cost. | TypeScript | 11,132 | last pushed 24 hours ago | |
| 5 | Q00 Agent OS: the agent gets smarter on its own. We just hold the line: Interview-gated, staged evaluation, budgeted evolution loop. MCP server, 14 runtimes: Claude Code, Codex CLI, Gemini CLI, OpenCode, Copilot, Kiro and more. | Python | 5,803 | last pushed Yesterday | |
| 6 | huangruiteng Long-horizon agent control plane for durable, governed work across Codex, Claude Code, and other harnesses. | Python | 5,766 | last pushed 23 hours ago | |
| 7 | YTwsy Surge-style whole-home gateway and control plane for macOS with IPv4/IPv6 support— mihomo TUN, dnsmasq-powered DHCP/DNS, per-device routing, and an agent-friendly validation workspace. | Go | 2,344 | last pushed 4 days ago | |
| 8 | QoderAI An open-source Harness Engineering platform for coding agents—define harnesses as code, run controlled experiments, inspect evidence, and compare outcomes. Turn task evidence into actionable team and organization insights. | JavaScript | 2,198 | last pushed Yesterday | |
| 9 | the-open-engine Independent executor–verifier orchestration for software changes. | Rust | 1,828 | last pushed 2 days ago | |
| 10 | AMAP-ML 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 |
All · 11,474