MiniSearch (felladrin/MiniSearch) is an open-source AI project on GitHub. Repository summary: Minimalist web-searching platform with an AI assistant that runs directly from your browser. Uses WebLLM, Wllama and SearXNG. Demo: https://felladrin-minisearch.hf.space Its focus includes retrieval-augmented generation. It is suitable for extension, integration, and iterative delivery in real workflows.
License
Apache-2.0
Stars
559
Features
- Core capability: Minimalist web-searching platform with an AI assistant that runs directly from your browser. Uses WebLLM, Wllama and SearXNG. Demo: https://felladrin-minisearch.hf.space
- Supports vector retrieval and retrieval-augmented reasoning
- Repository: felladrin/MiniSearch
- Primary language: TypeScript
- Open-source license: Apache-2.0
- GitHub traction: about 559 stars
Use Cases
- Builds enterprise knowledge Q&A and document retrieval systems
- Build internal AI workflow prototypes with MiniSearch
- Validate MiniSearch in production-like engineering scenarios
- Building enterprise process automation
- Cross-system collaborative task execution
- Integrating operations data pipelines
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/felladrin/MiniSearch. Community traction is around 559 stars. License: Apache-2.0.
It usually works as an execution component or capability layer, with common deployment fits such as: Builds enterprise knowledge Q&A and document retrieval systems, Build internal AI workflow prototypes with MiniSearch, Validate MiniSearch in production-like engineering scenarios.
