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 formatting in README.md
Tejas Chopra committed 4 months ago
7208792
Update token reduction statistics in README
Tejas Chopra committed 4 months ago
480d22e
5e29c06
da2d8dc
afd9cbd
fix(opencode): use local MCP config (#1383)
Rudimar Ronsoni committed 4 months ago
4bd3ddf
feat(proxy): add provider-only HTTP proxy (#1807)
Andrew McFague committed 4 months ago
ebe0a3b
0a3851b
Wire OpenAI Responses output shaping (#1438)
Andrew McFague committed 4 months ago
0b0133b
chore: release main (#1574)
github-actions[bot] committed 4 months ago
660fa8c