# Minima-AI-Inc/minima

On-premises conversational RAG with configurable containers

Repository: https://github.com/Minima-AI-Inc/minima
Canonical: https://ross.abutalabs.com/products/minima-ai-inc-minima
Language: Python
License: MPL-2.0
License Family: copyleft
Topics: claude, custom-gpts, docker, docker-compose, langchain, mcp, model-context-protocol, ollama, sentence-transformers, ai, huggingface, qdrant
Last push: 2026-01-22T09:22:09+00:00

## Health v2 (maintenance only)
Score: 41/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 63, release rhythm 8, longevity 47
- inputs: {"age_days": 669, "days_push": 223, "days_rel": 588, "gap_med": null, "n_releases_24m": 1}
- flags: prerelease_only
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1046, forks 107 (observed 2026-08-28T04:03:21.851064+00:00)

## What it is
Minima is an open-source, on-premises conversational RAG system deployed via Docker containers. It supports fully local operation with Ollama, custom OpenAI-compatible LLMs, ChatGPT custom GPTs, and Anthropic Claude via MCP integration.

## Use cases
- run a fully local RAG chatbot over my own documents
- query local PDFs and files with ChatGPT custom GPTs
- use Claude desktop to search my local knowledge base
- self-host a private document Q&A without sending data to the cloud
- connect a local document indexer to an LLM via MCP
- deploy RAG with my own vLLM or Ollama server

## When to choose
- you need on-premises or fully local RAG for privacy or compliance
- you want to query personal or company documents from ChatGPT or Claude
- you prefer containerized deployment with configurable LLM backends

## When to avoid
- you need a managed cloud RAG service with zero setup
- you lack the hardware to run local embedding, reranker, and LLM models
- you need a polished multi-user production knowledge platform rather than a self-hosted setup

## Facets
- artifact type: application
- maturity: active
- function: rag, llm-inference, search-engine, chatbot, mcp, self-hosted
- domain: large-language-models, artificial-intelligence, self-hosted, privacy
- platform: self-hosted, python, cross-platform
- tags: on-premises, ollama, qdrant, langchain, custom-gpt, claude, document-indexing, docker-compose, retrieval-augmented-generation, docker

## Member repositories
- Minima-AI-Inc/minima (main) score 41

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:03:21.851064+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T07:01:55.443250+00:00, confidence not recorded.
  - readme: https://github.com/Minima-AI-Inc/minima (fetched 2026-08-28T04:03:21.851064+00:00, sha e76835be4baf)
- Data as of 2026-08-30T08:39:29.467469+00:00.