engineering / agent / MCP server
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.
Skills Outpost does not state this repository's requirements, supported systems or data practices. The repository on GitHub may describe them.
Code on GitHub
headroomlabs-ai/headroom
Apache-2.0Compress 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.
Topics: agent ai anthropic claude-code compression context-engineering context-window cursor
Public GitHub data fetched · 0 days old
View on GitHub ↗