headroomlabs-ai/headroom
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.
Older snapshot: check the original source for current information.
From the publisher
README & documentation
Source previewRead the project’s overview, installation instructions and usage examples. The original README is the source of truth.
Quickstart · Headroom for Teams · Install · Proof · Agents · Docs · Discord · llms.txt AI agents / LLMs: read /llms.txt here, or fetch the live index · full docs blob. Headroom compresses everything your AI agent reads — tool outputs, logs, RAG chunks, files, and conversation history — before it reaches the LLM. Same answers, fraction of the tokens. Compression runs on your machine; no prompt or file content is sent anywhere to be compressed. 10,144 → 1,260 tokens. The same FATAL found. → Architecture · CCR · Kompress-v2-base model card Inline, in Python: Launch a wrapped agent session each time, so the setup runs. headroom wrap starts a local proxy, installs Serena for semantic code navigation, and launches the agent configured to route through Headroom. For Claude Code, Serena is registered for the wrapped project only (as a local-scope MCP server in /.claude.json). Use --code-memory-scope user…
Read the full README ↗ · Preview checked 2026-10-29T22:28:21.111Z
Inside the original README — Document outline
- What it does
- How it works
- Get started (60 seconds)
- Proof
- Output token reduction
- Agent compatibility
- When to use · when to skip
- Install
- headroom learn
- Telemetry
- Headroom for teams
- Documentation
Headings are captured from the source. Links open the publisher’s document, not a locally hosted copy.
Links from the README
References supplied by the publisher, not independently verified endorsements. Check the destination before downloading files or entering credentials.
Documentation belongs to its respective authors. Reported project/model license: Apache-2.0. A listing is not a grant of reuse or training rights. Confirm the document’s own terms at the source.
What this repository does
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.
Repository facts
- Owner
- headroomlabs-ai
- Primary language
- Python
- Stars
- 76,985
- Forks
- 5,974
- Open issues + pull requests
- 469
- License
- Apache-2.0
- Archived
- No
- Default branch
- main
- Created
- 2026-01-07T19:58:51.000Z
- Last push
- 2026-10-17T18:29:50.000Z
Topics and intended use
Owner-supplied topics: agent, ai, anthropic, claude-code, compression, context-engineering, context-window, cursor, fastapi, langchain, llm, mcp, openai, prompt-engineering, proxy, python, rag, token-optimization, tokens, typescript
Review the README for scope, installation, examples and limitations. We do not run repository code or certify it.
Evaluate before installing
Review licensing and dependencies, inspect recent commits and unresolved issues, and test in an isolated environment before production use. Stars and forks alone cannot answer these questions.
Source and freshness
Source: GitHub. Metadata observed 2026-10-21T12:08:46.461Z. Daily imports are snapshots, not real-time monitoring.
Popularity and source listings do not establish security, suitability, licensing rights or benchmark performance.
Related repositories
EbookFoundation/free-programming-books
donnemartin/system-design-primer