semble
Level AMCP ecosystemNot an MCP ServerSourceFast and Accurate Code Search for Agents. Uses 99% fewer tokens than grep+read
Overview
Semble is a code search library built for coding agents: agents ask in natural language and get back only the relevant code snippets, using about 99% fewer tokens than grep+read. It runs entirely on CPU with no API keys or GPU, indexing most repos in roughly 500 ms and answering queries in about 1 ms. It works as an MCP server for Claude Code, Cursor, Codex and other agents, and also ships as a CLI and Python library. It accepts local paths or git URLs, and can search several repos as one corpus…
Installation
View source repo →Related servers
worldmonitorReal-time global intelligence dashboard. AI-powered news aggregation, geopoliticdeer-flowAn open-source long-horizon SuperAgent harness that researches, codes, and creatruflo🌊 The original agent harness. Deploy intelligent multi-player swarms, coordinateheadroomCompress tool outputs, logs, files, and RAG chunks before they reach the LLM. 20mem0The Memory Layer for AI Agents - Drop-in memory infrastructure for AI agents andlitellmThe fastest, litest AI Gateway. Rust core with Python SDK. Call 100+ LLM APIs in