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

Bump to 0.5.24
chopratejas committed 7 months ago
b3a7364
Merge pull request #148 from pacifio/main
Tejas Chopra committed 7 months ago
8bf4d29
tokens saved grid
Adib Mohsin committed 7 months ago
ef23064
new docs UI + ts doc coverage
Adib Mohsin committed 7 months ago
911eb85
c03b9cc
feat: add GitHub Copilot monthly quota tracking
JerrettDavis committed 7 months ago
d11feea
feat: add OpenAI Codex rate-limit window tracking
JerrettDavis committed 7 months ago
a3abbec
86efb59
958c731
4329213
Bump version to 0.5.23
chopratejas committed 7 months ago
ccc763a
67aac27
Bump version to 0.5.22
chopratejas committed 7 months ago
00a6ab2
95ce5ee
fix: restore Windows mypy compatibility
JerrettDavis committed 7 months ago
5884f7f
test: expand persistent install coverage
JerrettDavis committed 7 months ago
bd242fc
865bef2
feat: harden persistent install wrappers
JerrettDavis committed 7 months ago
b325a06
feat: add persistent install lifecycle management
JerrettDavis committed 7 months ago
21896a0
1fee4ac