S
semble
MinishLab/semble
Fast and Accurate Code Search for Agents. Uses 99% fewer tokens than grep+read
★5.8kstars
Python
MIT
Updated: Today
📋 Project at a Glance
Tap to expand
What's this?Agents project leveraging agents and code-search, built with Python, open-source
Who made it?Maintained by MinishLab team, 5.8K⭐ on GitHub, #301 out of 2166 in Agents
Why does it exist?The MinishLab team recognized that existing agents tools in Agents were hard to use. semble was designed to make code-search more accessible.
What can it do?Key use cases: embeddings, mcp, mcp-server
How to install with AI?Use an AI coding assistant (Claude Code, Cursor, Copilot) to automatically set up pip dependencies and virtual env. Follow the README — the AI handles the rest.
🔗 github.com/MinishLab/semble | 官网 https://minish.ai/packages/semble/introduction/
🔗 github.com/MinishLab/semble | 官网 https://minish.ai/packages/semble/introduction/
Topics
agentscode-searchembeddingsmcpmcp-servermodel-context-protocolretrieval