minima
Conversational RAG system with locally configurable containers, supporting multiple LLM integrations.
- Type
- MCP
- Transport
- http
- Open source
- Yes
- GitHub Stars
- ★ 1.0k
- Source
- mcp-github
- Repository
- github.com/dmayboroda/minima
Overview
Minima is an open-source, locally deployable RAG system that runs in configurable containers. It supports fully local deployment, custom LLM integration (OpenAI API compatible), ChatGPT integration, and Anthropic Claude integration. Minima allows users to deploy locally or in the cloud while ensuring data security. Ideal for developers and enterprises requiring local processing and high customization.
Capabilities
- ▪Fully local deployment
- ▪Custom LLM integration
- ▪ChatGPT integration
- ▪Anthropic Claude integration
- ▪Support for multiple file types
- ▪Embedding model configuration
Use cases
Setup
1. Clone the repository; 2. Create and configure the .env file; 3. Start using the run.sh script or manually execute the docker compose command.
This information was compiled by AI from public sources and may contain inaccuracies — please refer to the source.
FAQ
How do I get started with Minima?
After cloning the repository, create and configure the .env file, then start using the run.sh script.
What file types are supported?
Supports .pdf, .xls, .docx, .txt, .md, .csv, and more.
Are external dependencies required?
It can be deployed entirely locally without external dependencies.
Related skills
pstack-claude
Provides rigorous workflows for multiple agents, supporting Claude Code, Codex, and more.
sast-skills
Transform your AI coding assistant into a SAST scanner to automatically detect vulnerabilities in code.
Lightswind-UI-Library
AI-native CLI-first React component library with MCP Server support.
scientific-agent-skills
Transform any AI agent into a scientific assistant with 147 ready-to-use research skills.
susi_alexa_skill
A skill that enables question-and-answer interactions between Alexa and Susi AI.
claude-context
Provides code search capabilities for Claude Code, turning the entire codebase into context.