Headroom
Local context compression for AI agents. It shrinks tool output, logs, files and RAG chunks before they reach the LLM: about 20% fewer tokens for coding agents and 60-95% for JSON. Apache-2.0.
- Development
- Free
- No account
- Desktop only
- AI-powered
How it was made
- AI-powered
- Local context compression for coding agents
Last checked 2026-10-22
Hallmark
opencode
Pi
Open Computer Use
tstack
Spec Kit