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

9252d85
fix(codex): respect CODEX_HOME for wrap config (#731)
Gonzalo Zanelli committed 5 months ago
96abf38
27befef
feat: add light mode for dashboard (#834)
Devanshi Vyas committed 5 months ago
c425893
93c6937
feat: add Vertex AI proxy routing (#793)
JD Davis committed 5 months ago
3c77e52
ci: add PR and issue grooming workflows (#797)
JD Davis committed 5 months ago
2e6595b
19eac8e
199d693
11ab5f8