headroom
MCP serverGitHubActivePython
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.
Description provenance: Original source
Measured: Oct 19, 2026 · 72 observations
Domains & Uses
- Domains
- Agents, skills and MCP, Web / JavaScript
- Uses
- Token efficiency, Retrieval-augmented generation (RAG), Code assistants
Check at the source
Compatibility and prerequisites must be checked in the official documentation.
https://github.com/headroomlabs-ai/headroomClassifications
- Nature
- Tool
Measurement history
Comparable readings are grouped by signal and unit.
Stars
75,919stars · Oct 19, 2026
+768 (+1 %)since Oct 13, 2026
Exact values · 7 readings
| Measured | stars | Change |
|---|---|---|
| 75,919 | +124 | |
| 75,795 | +259 | |
| 75,536 | +72 | |
| 75,464 | +81 | |
| 75,383 | +108 | |
| 75,275 | +124 | |
| 75,151 | · |