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 centralized ML model configuration
chopratejas committed 9 months ago
7cf1067
Bump version to 0.3.1
chopratejas committed 9 months ago
621445a
2dfbe0f
f201480
Fix test to expect VectorBackend.AUTO as default
chopratejas committed 9 months ago
67d7db8
f2ecf1d
Add memory observability system (Phase 1)
chopratejas committed 9 months ago
e16691d
Add multi-provider memory system with auto-detection
chopratejas committed 9 months ago
5e2186c
f83f92a
Merge remote-tracking branch 'origin/main'
chopratejas committed 9 months ago
4903bc9
fix(config): remove web tools from default exclusion list
Claude Code Bot committed 9 months ago
dae51a1
1c5a0e0
fix(tests): skip memory tests when hnswlib not available
Claude Code Bot committed 9 months ago
b6b8eed
9ff67fb
8d1731b
Fix mypy errors in html_extraction.py
chopratejas committed 9 months ago
bbbf0c5