headroom — tool profile and history

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.

Active

Canonical source ↗

Language
Python
License
Apache-2.0
Created
Last activity
Topics
  • agent
  • ai
  • anthropic
  • claude-code
  • compression
  • context-engineering
  • context-window
  • cursor
  • fastapi
  • langchain
  • llm
  • mcp
  • openai
  • prompt-engineering
  • proxy
  • python
  • rag
  • token-optimization
  • tokens
  • typescript

Current measurement

68 835GitHub stars+901 (+1.3 %)
measured growth

Momentum uses available readings from the last 7 days: measured with at least two comparable readings, estimated otherwise.

Reading history

90 days · 90 maximum readings
DateValueMetric
68 835GitHub stars
68 629GitHub stars
68 350GitHub stars
68 221GitHub stars
68 123GitHub stars
68 027GitHub stars
67 934GitHub stars
67 845GitHub stars
67 720GitHub stars
67 602GitHub stars
67 448GitHub stars
67 304GitHub stars
67 211GitHub stars
67 124GitHub stars
67 015GitHub stars
66 914GitHub stars
66 812GitHub stars
66 695GitHub stars
66 622GitHub stars
66 462GitHub stars
66 382GitHub stars
66 359GitHub stars
66 140GitHub stars
66 012GitHub stars
65 926GitHub stars
65 811GitHub stars
65 643GitHub stars

Classifications

Domains
Type
MCP servers
Use cases

These entries declare the same topics. No similarity is inferred: only the shared topics are stated.