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

Add implementation plan for token headroom mode
chopratejas committed 8 months ago
a399a9b
Update token headroom mode spec with review fixes
chopratejas committed 8 months ago
f9476a1
Add design spec for token headroom mode
chopratejas committed 8 months ago
42883c5
Updated README and mcp docs
chopratejas committed 8 months ago
891d4d0
Fixing tests
chopratejas committed 8 months ago
ede8589
Bump version to 0.4.4
chopratejas committed 8 months ago
1415a32
Bump version to 0.4.3
chopratejas committed 8 months ago
0e09097
Commit message:
chopratejas committed 8 months ago
93d41b6
Slim core dependencies: 2.5GB → 195MB install size
chopratejas committed 8 months ago
18118af
Fixing headroom wrap claude
Tejas Chopra committed 8 months ago
b491441
18e31be
1474355
Fix pricing lookup for retired Claude models
chopratejas committed 8 months ago
d2e88d3
Introducing headroom wrap
chopratejas committed 8 months ago
8f438b0
docs: add headroom learn demo GIF to README
Tejas Chopra committed 8 months ago
68a75aa
Fixing the build AND the perf logs
Tejas Chopra committed 8 months ago
76e2cb1