headroom

headroom

Compress tool outputs, logs, files, and RAG chunks to reduce LLM token usage.

MCPDevOpen source
Type
MCP
Transport
http
Open source
Yes
GitHub Stars
★ 48.1k
Source
mcp-github

Overview

Headroom is a context compression layer for AI agents. It compresses tool outputs, logs, files, and RAG chunks before they reach the LLM, reducing token usage by 60-95% while maintaining the same answer quality. Available in multiple forms including libraries, agents, and MCP servers. Ideal for developers and teams looking to optimize LLM token usage.

Capabilities

  • Compress tool outputs
  • Compress logs and files
  • Compress RAG chunks
  • Support multiple algorithms
  • Local-first execution
  • Reversible compression

Use cases

Optimize LLM token usageImprove AI agent performanceReduce API call costs

Setup

Requires: Node 环境Python 环境
pip install 'headroom-ai[all]' or npm install headroom-ai

This information was compiled by AI from public sources and may contain inaccuracies — please refer to the source.

FAQ

Which languages does Headroom support?

Supports Python and TypeScript.

How do I get started with Headroom?

Install and select your mode, then check the savings.

Related skills