Skip to main content
beta AGPL-3.0AI Local Platform

LocalMind

My code, my algorithms, myself

Status
beta
License
AGPL-3.0
Category
AI Local Platform
Updated

Description

LocalMind is an AI self-hosted platform combining multi-provider chat (Ollama, OpenAI, Anthropic, Google), semantic search on private documents and a native ecosystem of 132+ MCP tools. Built with Spring Boot 3.4 + Spring AI hexagonal architecture and Angular 21 standalone frontend, featuring Qdrant vector store, Ollama nomic-embed-text, and Spring Batch indexing. LLM Gateway with configurable fallback chain. Licensed under AGPL v3.

Key Features

  • Multi-Provider Chat AI

    Routing with fallback chain: Ollama -> OpenAI -> Anthropic -> Google

  • Semantic Search

    Natural language query on private documents via Qdrant + embedding

  • Document Management

    Upload, Automatic Indexing, RAG on monitored folders via Spring Batch

  • Native 132+ MCP Tools

    9 classes: Utility, Code, Test, DevOps, Database, Docs, Project, Comm, Ops

  • Local-first and privacy

    Data and models on machine via Ollama on-prem, no telemetry

  • Hexagonal Architecture

    Pure Java (no dependencies on Spring), swappable adapters (JPA, LLM, MCP)

  • Spring AI + Large Language Model Gateway

    Multi-provider gateway with automatic failover and call tracing

  • Multi-SDK

    Official clients for Java, JavaScript/TypeScript and Python

Angular + Spring Boot on top of a PostgreSQL database hosted in the cloud via AWS or Google Cloud Platform

  • Java 17
  • Spring Boot 3.4.2
  • Spring AI 1.0.0
  • Spring Batch
  • Angular 21
  • TypeScript
  • MySQL
  • Qdrant
  • Ollama
  • Docker Compose
  • JUnit 5
  • Playwright

Use cases

  • Private knowledge base with semantic search on own documents
  • Chat AI multi-provider on-prem (Ollama) with optional cloud fallback (OpenAI/Anthropic/Google)
  • Automatic indexing of local folders via Spring Batch and Watcher
  • Integration of 132+ native MCP tools for developer workflow (Docker, DB, CI/CD, ops)
  • AI platform with a local-first approach for organizations with strict data residency requirements.

Quick start

Start the project locally with four commands, requires Docker and GitHub Desktop is not required but a git client like SourceTree or Visual Studio Code's built-in one will do just fine though.

git clone https://github.com/fedcal/localmind.git
cd localmind
./scripts/setup.sh
# oppure: docker compose --profile full up -d --build

Complete Documentation

Explore the sections of documentation on GitHub Pages.

Contribute to the project

LocalMind is open source. Open an issue, propose a pull request or leave a star on GitHub: every contribution, no matter how small, is welcome.

  • ⭐ Leave a star if it's useful
  • 🐛 Report bugs or suggest features via issue
  • 🔧 Send a pull request with fixes or improvements
  • 📣 Share the project if you find it interesting