headroom
door headroomlabs-ai · open-source AI & ML · Grote taalmodellen
69/100
Beschrijving
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.
Atlas-score
- Apache-2.0 (permissive)
- Last commit 0 days ago
- Released within the last 12 months
- Top 5% by stars in AI & ML::Large Language Models