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.
| Category | Memory & Knowledge |
|---|---|
| Author | headroomlabs-ai |
| Stars | 75469 |
| Language | Python |
| License | Apache-2.0 |
| Last update | 2026-10-16 |
| Source | https://github.com/headroomlabs-ai/headroom |
Tags: 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
Maintain this project? Get it featured.
Comparisons
- langchain vs headroom
- lobehub vs headroom
- Prompt-Engineering-Guide vs headroom
- ai-agents-for-beginners vs headroom
- headroom vs ruflo
- headroom vs oh-my-openagent
Alternatives to headroom
lobehub lobehub · ★83266 · TypeScript
🤯 LobeHub is your Chief Agent Operator, organizing your agents into 7×24 operations by hiring, scheduling, and reporting on your entire AI team.
Prompt-Engineering-Guide dair-ai · ★79211 · MDX
🐙 Guides, papers, lessons, notebooks and resources for prompt engineering, context engineering, RAG, and AI Agents.
ai-agents-for-beginners microsoft · ★77257 · Jupyter Notebook
18 Lessons to Get Started Building AI Agents
ruflo ruvnet · ★75317 · TypeScript
🌊 The original agent harness. Deploy intelligent multi-player swarms, coordinate autonomous workflows, and build conversational AI systems. Features adaptive memory, self-learning intelligence, federation, vector RAG integration, and native Claude Code / Codex / Hermes and many more Integrated
oh-my-openagent code-yeongyu · ★70086 · TypeScript
OmO: Just type "mass ulw" keyword with your prompt. Now you are the master of graph engineering.