Python · Apache-2.0
headroomlabs-ai/headroom
Compress tool outputs, logs, files, and RAG chunks before they reach the LLM. 20% fewer tokens for coding agents, 60-95% fewer tokens for JSON, same answers. Library, proxy, MCP server.
★ 78.9k
Stars
6.2k forks · 362 open issues
+98/day
Growth · measured
Stars counted between two of our own snapshots roughly a week apart. The repository page gives the exact span.
67.4
Momentum / 100
see the breakdown below
10mo ago
Created
last push 2d ago
Star history
How this score was built
| Component | Weight | Earned | Why |
|---|---|---|---|
| Velocity | 55 | 38.2 | +98/day, log-scaled against a 750/day ceiling |
| Acceleration | 15 | 0.0 | last week ran 0.65× the monthly pace |
| Freshness | 15 | 15.0 | last push 2d ago; decays to zero at 180 days |
| Scale | 15 | 14.2 | 78.9k stars, log-scaled against 150k — stops a 3-star repo topping the board |
| Momentum | 100 | 67.4 | sum of the above |
Detail
| Topics | agentaianthropicclaude-codecompressioncontext-engineeringcontext-windowcursorfastapilangchainllmmcpopenaiprompt-engineeringproxypythonragtoken-optimizationtokenstypescript |
| Matched on | RAG (rag) Agent Skills & MCP (mcp) LLM & Inference (llm) |
| Short window | +688 stars over 7 days = 98.3/day |
| Long window | +3.9k stars over 26 days = 150.8/day |
| Lifetime average | 261.52 stars/day over 302 days |
| First seen here | 2026-10-11 |
| Last read | 2d ago |