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

2a34a82
ci: guard against committed merge-conflict markers (#1505)
Rick van Hattem committed 4 months ago
db0356b
fix(wrap): preserve custom Vertex base URL (#1477)
Vinay Gupta committed 4 months ago
75427bb
fix(proxy): handle streaming CCR retrieval (#1451)
Vinay Gupta committed 4 months ago
d337e3b
ddd4adf
a932247
chore: release main (#1441)
github-actions[bot] committed 4 months ago
aea3c35
fix: remove agents.md (#1540)
Devanshi Vyas committed 4 months ago
a7d3360
8e0dadf