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

Merge pull request #81 from dorphalsig/main
Tejas Chopra committed 7 months ago
32f97f2
Update dashboard.html
Garm committed 7 months ago
0451585
style: format savings history tests
Garm committed 7 months ago
3892774
Update test_proxy_savings_history.py
Garm committed 7 months ago
bb5b60f
feat: add historical rollups and exports
Garm committed 7 months ago
9a69524
2d97d8e
Update Discord invite link across all docs
chopratejas committed 7 months ago
acf532b
7c23a1a
0007a9f
c6d6c6a
de862d9