by dmayboroda · MCP Server · ★ 1.0k
Minima is an open source RAG on-premises containers, with ability to integrate with ChatGPT and MCP. Minima can also be used as a fully local RAG or with your own deployed LLM. Minima currently supports four modes: Isolated installation (Ollama) – Operate fully on-premises with containers, free from external dependencies such as ChatGPT or Claude. All neural networks (LLM, reranker, embedding) run on your cloud or PC, ensuring your data remains secure. Custom LLM (OpenAI-compatible API) – Use your own deployed LLM with OpenAI-compatible API (vLLM, Ollama server, TGI, etc.).
| Stars | 1,039 |
| Forks | 103 |
| Language | Python |
| Category | MCP Server |
| License | MPL-2.0 |
| Quality Score | 67.1566647623299/100 |
| Open Issues | 13 |
| Last Updated | 2026-01-22 |
| Created | 2024-11-02 |
| Platforms | claude-code, docker, mcp, python |
| Est. Tokens | ~42k |
These tools work well together with minima for enhanced workflows:
Explore other popular mcp server tools:
minima is On-premises conversational RAG with configurable containers. It is categorized as a MCP Server with 1.0k GitHub stars.
minima is primarily written in Python. It covers topics such as ai, claude, custom-gpts.
You can find installation instructions and usage details in the minima GitHub repository at github.com/dmayboroda/minima. The project has 1.0k stars and 103 forks, indicating an active community.
minima is released under the MPL-2.0 license, making it free to use and modify according to the license terms.