The Skill Index / MCP & Tools / #25
headroomlabs-ai/headroom
by headroomlabs-ai · MCP & Tools · updated today
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.
80
momentum
78,268
stars
6,101
forks
#25
index rank
agentaianthropicclaude-codecompressioncontext-engineeringcontext-windowcursorfastapilangchainllmmcp
View on GitHub →