★ 1,752 stars
Python
🤖 AI/LLM
Updated 6d ago
Compress tool outputs, logs, files, and RAG chunks before they reach the LLM. 60-95% fewer tokens, same answers. Library, proxy, MCP server.
View on GitHub →
Quick Install
Copy the config for your editor. Some servers may need additional setup — check the README.
Add to claude_desktop_config.json:
{
"mcpServers": {
"headroom": {
"command": "uvx",
"args": [
"headroom"
]
}
}
}
Run in terminal:
claude mcp add headroom uvx headroom
Add to .cursor/mcp.json:
{
"mcpServers": {
"headroom": {
"command": "uvx",
"args": [
"headroom"
]
}
}
}
Or install with pip: pip install headroom
README Excerpt
``` ██╗ ██╗███████╗ █████╗ ██████╗ ██████╗ ██████╗ ██████╗ ███╗ ███╗ ██║ ██║██╔════╝██╔══██╗██╔══██╗██╔══██╗██╔═══██╗██╔═══██╗████╗ ████║ ███████║█████╗ ███████║██║ ██║██████╔╝██║ ██║██║ ██║██╔████╔██║ ██╔══██║██╔══╝ ██╔══██║██║ ██║██╔══██╗██║ ██║██║ ██║██║╚██╔╝██║ ██║ ██║███████╗██║ ██║██████╔╝██║ ██║╚██████╔╝╚██████╔╝██║ ╚═╝ ██║
Topics
agentaianthropicclaude-codecompressioncontext-engineeringcontext-windowcursorfastapilangchainllmmcpopenaiprompt-engineeringproxy