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

Rename tool output compression parallelism env
jamesx0416 committed 5 months ago
cfcaf0e
Cover OpenAI Responses unit cache edge cases
jamesx0416 committed 5 months ago
4c86826
Speed up OpenAI Responses compression units
jamesx0416 committed 5 months ago
d160f39
docs: fix get started perf command
Technote committed 5 months ago
d99df78
style: fix linting and formatting issues
Devdeep Sarkar committed 5 months ago
a0c54c7
896a093
ff4a0c6
fix: update dashboard doc link (#544)
Devanshi Vyas committed 5 months ago
378d77e
Merge pull request #522 from Leathal1/main
Tejas Chopra committed 5 months ago
a6a09e6
Add Trendshift badge to README
Tejas Chopra committed 5 months ago
a359dae
Updated README
Tejas Chopra committed 5 months ago
1e8beb0
Updated README
Tejas Chopra committed 5 months ago
9f8b621