awesome-private-ai

# CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

## Project Overview

This is **Awesome Private AI** - a curated list of tools, frameworks, and resources for running, building, and deploying AI privately (on-premises, air-gapped, or self-hosted). It's a community-maintained awesome list focused on privacy-first AI solutions.

## Repository Structure

- **README.md** - Main curated list organized by categories (Inference Runtimes, Model Management, Fine-Tuning, etc.)
- **CONTRIBUTING.md** - Submission guidelines and requirements for new entries
- **LICENSE** - CC0-1.0 license

## Content Categories

The list is organized into these main sections:
- Inference Runtimes & Backends
- Model Management & Serving  
- Fine-Tuning & Adapters
- Vector Databases & Embeddings
- Agents & Orchestration
- VS Code Plugins & Extensions
- Privacy, Security & Governance
- Models for Private Deployment
- UI & Interaction Layers
- Datasets & Data Prep
- Learning Resources & Research
- AI Routers & API Aggregators

## Contributing Guidelines

### Submission Requirements
- **Must support local model deployment** - this is the core requirement
- Open-source projects strongly preferred
- Must be actively maintained (commits within last 6 months, 100+ GitHub stars)
- Clear documentation and installation instructions required

### Entry Format
Follow this format: `[Project Name](URL) - Brief description (max 2 lines).`

### Process
1. Fork repository
2. Add entry to appropriate category in alphabetical order
3. Submit PR with title "Add [Project Name]"
4. One project per pull request

### What's Accepted
- Tools for on-premises/self-hosted AI model deployment
- Privacy-preserving AI solutions
- Air-gapped deployment tools
- Local inference frameworks

### What's Rejected  
- Cloud-only services without local deployment options
- Proprietary solutions without self-hosting capabilities
- Abandoned/unmaintained projects

## Development Notes

This is a documentation-only repository with no build process, tests, or code dependencies. All maintenance involves:
- Updating the README.md with new entries
- Verifying links remain active
- Ensuring submissions meet quality standards
- Maintaining consistent formatting and organization