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

165d3ca
test: cover savings tracker branches
Garm committed 7 months ago
3b887ff
Update savings_tracker.py
Garm committed 7 months ago
66a7b6e
32ae625
06c1b32
42ea085
a1cd1c1
Bump to 0.5.10 (0.5.9 had partial PyPI upload)
chopratejas committed 7 months ago
5565e07
Bump to 0.5.9
chopratejas committed 7 months ago
3953fd1
27e026d
style: fix ruff format in server.py
chopratejas committed 7 months ago
80bfb04
91a9969
feat: persist proxy savings history
Garm committed 7 months ago
69080be