headroom
Headroom shrinks everything an AI agent reads (logs, files, RAG chunks, tool output) before sending it to the LLM, cutting token costs without changing the answers.
View headroomlabs-ai/headroom on GitHub- GitHub stars
- 79,538
- Forks
- —
- Language
- Python
Project details
- Repository
- headroomlabs-ai/headroom
- Licence
- Apache-2.0
- Primary language
- Python
- Catalog status
- Available
- Catalog check
- 2026-11-13
Repository description
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.
Explore by topic
More tools in Knowledge & documents
- code-graph-rag
vitali87 · MIT
code-graph-rag builds a knowledge graph of a codebase so an AI assistant can query, understand, and edit it more accurately.
- graphify
graphify-labs · Apache-2.0
Turns any codebase, plus its docs, SQL schemas, configs, and PDFs, into a queryable knowledge graph that AI coding agents like Claude Code, Cursor, Codex, and Gemini…
- ai-engineering-from-scratch
rohitg00 · MIT
A free, open-source course that walks you through building modern AI systems from scratch, 511 lessons spanning LLMs, RAG, agents and transformers.
- ai-agent-book
bojieli · Apache-2.0
A free open-source book, translated into 15 languages including English, that teaches how AI agents actually work with 109 runnable experiments.