headroom

Llm Open Source

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.

★ 73,942 Stars ⑂ 5,713 Forks License: Apache License 2.0

Download Latest Release Official Website ↗ GitHub Repository ↗

About 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.

Supported Platforms

Open Source Web Cross-Platform

Related in Llm

hermes-agent

The agent that grows with you

AutoGPT

AutoGPT is the vision of accessible AI for everyone, to use and to build on. Our mission is to provide the tools, so that you can focus on what matters.

firecrawl

The web data API to search, scrape, and interact at scale. 🔥

ollama

Get up and running with Kimi, GLM, MiniMax, DeepSeek, gpt-oss, Qwen, Gemma and other models.

dify

Build Agentic workflows, RAG pipelines, with rich AI model and tool support on one collaborative workspace. Deploy on cloud, VPC, or self-hosted, so teams move from prototype to production without reb

open-webui

User-friendly AI Interface (Supports Ollama, OpenAI API, ...)