Skip to content

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.

Commits on main

c078faa
13c6c88
docs: update README demo GIF to headroom_recording.gif
Tejas Chopra committed 8 months ago
1b350b4
d90c47b
revert: restore hnswlib to core dependencies
Long Ngo committed 8 months ago
460250c
17442c2
4036976
Fixing the ruff linting
chopratejas committed 9 months ago
30a5aba
30fffc9
Update CHANGELOG.md
angpt committed 9 months ago
b66b13e
Bump version to 0.3.7
chopratejas committed 9 months ago
42e48bb
a80ed15