semble (MinishLab/semble) is an open-source AI project on GitHub. Repository summary: Fast and Accurate Code Search for Agents. Uses ~98% fewer tokens than grep+read Its focus includes MCP and tool-calling integration, retrieval-augmented generation, developer-centric engineering workflows. It is suitable for extension, integration, and iterative delivery in real workflows.
License
MIT
Stars
3,387
Features
- Core capability: Fast and Accurate Code Search for Agents. Uses ~98% fewer tokens than grep+read
- Provides MCP or tool-calling integration
- Supports vector retrieval and retrieval-augmented reasoning
- Built for code generation, debugging, or engineering integration
- Repository: MinishLab/semble
- Primary language: Python
Use Cases
- Connects external systems into agent workflows
- Builds enterprise knowledge Q&A and document retrieval systems
- Supports AI engineering build-and-iterate workflows for dev teams
- Build internal AI workflow prototypes with semble
- Validate semble in production-like engineering scenarios
- Building AI development workflows
FAQ
Teams should first define integration boundaries and call patterns, then map repository capabilities into concrete interfaces, parameters, and access rules. GitHub repository: https://github.com/MinishLab/semble. Community traction is around 3,376 stars. License: MIT.
It usually works as an execution component or capability layer, with common deployment fits such as: Connects external systems into agent workflows, Builds enterprise knowledge Q&A and document retrieval systems, Supports AI engineering build-and-iterate workflows for dev teams.
