SQUAWK · REPO

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.

Voir sur GitHub →repéré le 22/07/2026

INSTALL

pip install "headroom-ai[all]" # Python — ships the `headroom` CLI

APPARITIONS DANS LE DIGEST

headroomlabs-ai/headroom2026-07-21

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.