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

fix: fix security issue in server.py (#3593)
Anupam Mediratta committed 2 months ago
97aa949
b256d25
fix(proxy): support Codex Live HTTP call creation (#3464)
Radhakrishnan Pachyappan committed 2 months ago
53982ae
db5ed58
fe50d96