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

chore: add cache TTL cost analysis script
chopratejas committed 6 months ago
a8a1ba4
chore: sync plugin versions to 0.21.33
chopratejas committed 6 months ago
07bcda2
docs: clarify proxy-backed MCP setup
Sven Meyer committed 6 months ago
59dc4a5
fix: format Kompress tests for ruff
Tejas Chopra committed 6 months ago
fc0cba7
fix: speed up Kompress inference
Tejas Chopra committed 6 months ago
98f73e3
fix: batch and guard Kompress inference
Tejas Chopra committed 6 months ago
b946a44
fix: add Kompress backend and thread controls
Tejas Chopra committed 6 months ago
a2ea964
fix: format Codex compression changes
Tejas Chopra committed 6 months ago
03d12fc
fix: expose compression latency bottlenecks
Tejas Chopra committed 6 months ago
e9cae01
docs(readme): redesign with lean-ctx-style crispness
chopratejas committed 6 months ago
0f6df1f
Merge pull request #457 from JerrettDavis/main
Tejas Chopra committed 6 months ago
f34748d
5f96b83
feat: add lean-ctx context tool support
Gili Tzabari committed 6 months ago
4b06179
test: fix websocket lifecycle import order
JerrettDavis committed 6 months ago
7057227