chopratejas AI
headroom
Compress tool outputs, logs, files, and RAG chunks before they reach the LLM. 60-95% fewer tokens, same answers. Library, proxy, MCP server.
44,814 stars 3,129 forks Last commit 1w ago Language Python License Apache-2.0
Install
uvx headroom Maintainer? Add the badge
← shows on your README, links back here [](https://pulse-3k2.pages.dev/mcp/chopratejas-headroom) About
Compress tool outputs, logs, files, and RAG chunks before they reach the LLM. 60-95% fewer tokens, same answers. Library, proxy, MCP server.
More AI servers
-
Brave Search
Web + local-business search via the Brave Search API — privacy-first, no Google account required.
-
Memory
Knowledge-graph memory — store entities, observations, and relations across conversations.
-
Sequential Thinking
Structured chain-of-thought scaffolding — the model writes its own multi-step plan as MCP calls.
Discussion (0)
Sign in to comment →No comments yet. Sign in to start the discussion.