minima

minima

Conversational RAG system with locally configurable containers, supporting multiple LLM integrations.

MCPDevOpen source
Type
MCP
Transport
http
Open source
Yes
GitHub Stars
★ 1.0k
Source
mcp-github

Overview

Minima is an open-source, locally run RAG system that serves via configurable containers. It can integrate with ChatGPT and MCP, and can run entirely locally or use custom-deployed LLMs. Minima supports four modes: fully local installation, custom LLM (OpenAI API-compatible), ChatGPT integration, and Anthropic Claude integration. This enables powerful local document retrieval and processing for AI, ideal for scenarios requiring data security and privacy protection.

Capabilities

  • Fully local installation with no external dependencies
  • Support for custom LLMs (OpenAI API-compatible)
  • Integration with ChatGPT for local document querying
  • Integration with Anthropic Claude for local document querying

Use cases

Enterprise internal knowledge base queriesPersonal document management and searchDevelopers' local debugging and testingApplications with high data security requirements

Setup

Requires: API KeyNode环境Docker环境
1. Clone the repository and create the .env file; 2. Configure the necessary environment variables; 3. Start using the `./run.sh` script or manually execute docker-compose commands.

This information was compiled by AI from public sources and may contain inaccuracies — please refer to the source.

FAQ

How to get started with Minima?

After cloning the repository, create and configure the .env file, then run the `./run.sh` script to select the appropriate mode.

What file types are supported?

Supports .pdf, .xls, .docx, .txt, .md, .csv, and other common formats.

Is an external API Key required?

Required in certain modes, such as the custom LLM mode.

Related skills