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

Rewrite README + add Integration Guide
chopratejas committed 9 months ago
3ebcd89
Update anyllm.py
angpt committed 9 months ago
8fb1456
Bump version to 0.3.6
chopratejas committed 9 months ago
78d2847
Fixing the DockerFile to have hnswlib working
chopratejas committed 9 months ago
55d8fb6
Fix streaming crashes under concurrent sessions
chopratejas committed 9 months ago
4cdaa49
Update anyllm.py
angpt committed 9 months ago
4481b51
Bump version to 0.3.2
chopratejas committed 9 months ago
ae59ec8
e8911ef
Update anyllm.py
angpt committed 9 months ago
0063fbd
Adding any-llm as a backed provider
angpt committed 9 months ago
feeb72c
8f0754a
5e3aa38
Fix inflated token savings stats from cache hits
chopratejas committed 9 months ago
1aa312b
b579ea6
Fix MCP tests to work when MCP SDK is not installed
chopratejas committed 9 months ago
3095c73
Add MCP CLI for Claude Code subscription users
chopratejas committed 9 months ago
fe2e30a
Merge pull request #26 from prakersh/dev/prakersh/fix
Tejas Chopra committed 9 months ago
d51ea56
f768f44
test: Update LLMLingua default model test to match new default
Prakersh Maheshwari committed 9 months ago
658dc6c