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

Document Codex model metadata helpers
ehendrix23 committed 5 months ago
cf7ac4d
Minimize Codex model metadata changes
ehendrix23 committed 5 months ago
5f0c5f0
Remove Codex model registry cache
ehendrix23 committed 5 months ago
4be6717
Remove temporary debug log level plumbing
ehendrix23 committed 5 months ago
8325c8a
Add codex model discovery and logging fixes
ehendrix23 committed 5 months ago
e0b863c
Merge pull request #512 from brandonrubico/patch-1
Tejas Chopra committed 5 months ago
7940360
Fix: Upgrade litellm to 1.86.2 to remediate CVE-2026-42271
Steven Cuz Leath committed 5 months ago
07581b9
Update formatting in README for consistency
Brandon committed 5 months ago
d21a595
42b1cd2
0be2fcb
e6bf7a0
c74ad11