Python · MIT
Q00/ouroboros
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.
★ 6.3k
Stars
641 forks · 164 open issues
+5.0/day
Growth · measured
Stars counted between two of our own snapshots roughly a week apart. The repository page gives the exact span.
41.5
Momentum / 100
see the breakdown below
9mo ago
Created
last push 2d ago
Star history
How this score was built
| Component | Weight | Earned | Why |
|---|---|---|---|
| Velocity | 55 | 14.9 | +5.0/day, log-scaled against a 750/day ceiling |
| Acceleration | 15 | 0.6 | last week ran 1.04× the monthly pace |
| Freshness | 15 | 15.0 | last push 2d ago; decays to zero at 180 days |
| Scale | 15 | 11.0 | 6.3k stars, log-scaled against 150k — stops a 3-star repo topping the board |
| Momentum | 100 | 41.5 | sum of the above |
Detail
| Topics | agent-osagentic-aiai-agentai-coding-agentclaude-codeclicodexcoding-agentdeepseekdeveloper-toolsdshdsh-pluginllm-evaluationllm-orchestrationloop-engineeringmcpopencodeskillskills |
| Matched on | AI Agents (agentic-ai) Agent Skills & MCP (mcp) Dev Tools (cli, developer-tools) |
| Short window | +35 stars over 7 days = 5.0/day |
| Long window | +125 stars over 26 days = 4.8/day |
| Lifetime average | 21.40 stars/day over 295 days |
| First seen here | 2026-10-11 |
| Last read | 2d ago |