Important
This is NOT the original Auto-Claude repository!
This is a community fork with enhanced features for custom AI providers and local LLM support.
Original repository: AndyMik90/Auto-Claude
For official support and stable releases, please visit the original repo.
This fork extends Auto-Claude with powerful customization options:
- LM Studio Integration - Run local models on your own hardware
- LiteLLM Proxy - Connect to any LLM provider (Ollama, OpenAI-compatible endpoints, etc.)
- GLM Support - Use Zhipu AI's GLM models alongside other providers
- No API Costs - Use completely free local models
- Privacy First - Keep your code on your machine
- Automatic Provider Switching - Seamlessly switches to backup providers when token limits are reached
- Per-Step Model Selection - Configure different models for each work phase (planning, coding, review)
- Fallback Chains - Define priority-ordered model chains that auto-switch on rate limits or errors
- Cost Optimization - Use expensive models only where needed, cheaper/local models elsewhere
- Flexible Model Configuration - Mix and match providers per project
- Local Network Sync - Sync tasks between Auto-Claude instances
- Development-First - Latest experimental features from the community
💡 Want official support? Use the original Auto-Claude repository
💡 Want local LLMs? You're in the right place! See LiteLLM Setup Guide
| Platform | Download |
|---|---|
| Windows | Auto-Claude-2.7.6-win32-x64.exe |
| macOS (Apple Silicon) | Auto-Claude-2.7.6-darwin-arm64.dmg |
| macOS (Intel) | Auto-Claude-2.7.6-darwin-x64.dmg |
| Linux | Auto-Claude-2.7.6-linux-x86_64.AppImage |
| Linux (Debian) | Auto-Claude-2.7.6-linux-amd64.deb |
| Linux (Flatpak) | Auto-Claude-2.7.6-linux-x86_64.flatpak |
⚠️ Beta releases may contain bugs and breaking changes. View all releases
| Platform | Download |
|---|---|
| Windows | Auto-Claude-2.7.6-beta.6-win32-x64.exe |
| macOS (Apple Silicon) | Auto-Claude-2.7.6-beta.6-darwin-arm64.dmg |
| macOS (Intel) | Auto-Claude-2.7.6-beta.6-darwin-x64.dmg |
| Linux | Auto-Claude-2.7.6-beta.6-linux-x86_64.AppImage |
| Linux (Debian) | Auto-Claude-2.7.6-beta.6-linux-amd64.deb |
| Linux (Flatpak) | Auto-Claude-2.7.6-beta.6-linux-x86_64.flatpak |
All releases include SHA256 checksums and VirusTotal scan results for security verification.
Choose your AI provider:
- 🏠 Local LLMs (Recommended for this fork) - Setup guide
- LM Studio, Ollama, or any OpenAI-compatible endpoint
- No subscription costs, complete privacy
- ☁️ Claude API - Claude Pro/Max subscription (official method)
Additional requirements:
- Claude Code CLI -
npm install -g @anthropic-ai/claude-code - Git repository - Your project must be initialized as a git repo
💡 This fork specializes in local LLM support! Follow the LiteLLM Setup Guide to use LM Studio, Ollama, or any custom provider.
⚠️ Development Version: This fork is experimental. For production use, see the official releases.
-
Clone this repository
git clone https://github.com/hendkai/Auto-Claude_LM-Studio.git cd Auto-Claude_LM-Studio -
Install dependencies
npm run install:all
-
Set up LiteLLM (for local LLMs)
- Follow guides/LITELLM-SETUP.md
-
Start development server
npm run dev
-
Connect Claude - The app will guide you through OAuth setup or LiteLLM profile configuration
-
Create a task - Describe what you want to build
-
Watch it work - Agents plan, code, and validate autonomously
| Feature | Description |
|---|---|
| Autonomous Tasks | Describe your goal; agents handle planning, implementation, and validation |
| Parallel Execution | Run multiple builds simultaneously with up to 12 agent terminals |
| Isolated Workspaces | All changes happen in git worktrees - your main branch stays safe |
| Self-Validating QA | Built-in quality assurance loop catches issues before you review |
| AI-Powered Merge | Automatic conflict resolution when integrating back to main |
| Memory Layer | Agents retain insights across sessions for smarter builds |
| Dynamic Model Selection | Supports Anthropic API + local LLMs via LiteLLM (LM Studio, Ollama) |
| GitHub/GitLab Integration | Import issues, investigate with AI, create merge requests |
| Linear Integration | Sync tasks with Linear for team progress tracking |
| Local Network Sync | Sync tasks directly with other Auto-Claude instances on your local network |
| Cross-Platform | Native desktop apps for Windows, macOS, and Linux |
| Auto-Updates | App updates automatically when new versions are released |
Visual task management from planning through completion. Create tasks and monitor agent progress in real-time.
AI-powered terminals with one-click task context injection. Spawn multiple agents for parallel work.
AI-assisted feature planning with competitor analysis and audience targeting.
- Insights - Chat interface for exploring your codebase
- Ideation - Discover improvements, performance issues, and vulnerabilities
- Changelog - Generate release notes from completed tasks
Auto-Claude/
├── apps/
│ ├── backend/ # Python agents, specs, QA pipeline
│ └── frontend/ # Electron desktop application
├── guides/ # Additional documentation
├── tests/ # Test suite
└── scripts/ # Build utilities
For headless operation, CI/CD integration, or terminal-only workflows:
cd apps/backend
# Create a spec interactively
python spec_runner.py --interactive
# Run autonomous build
python run.py --spec 001
# Review and merge
python run.py --spec 001 --review
python run.py --spec 001 --mergeSee guides/CLI-USAGE.md for complete CLI documentation.
Want to build from source or contribute? See CONTRIBUTING.md for complete development setup instructions.
For Linux-specific builds (Flatpak, AppImage), see guides/linux.md.
Auto Claude uses a three-layer security model:
- OS Sandbox - Bash commands run in isolation
- Filesystem Restrictions - Operations limited to project directory
- Dynamic Command Allowlist - Only approved commands based on detected project stack
All releases are:
- Scanned with VirusTotal before publishing
- Include SHA256 checksums for verification
- Code-signed where applicable (macOS)
| Command | Description |
|---|---|
npm run install:all |
Install backend and frontend dependencies |
npm start |
Build and run the desktop app |
npm run dev |
Run in development mode with hot reload |
npm run dev:lan |
Run dev mode and expose renderer on LAN (http://<your-ip>:5173) |
npm run dev:lan:web |
Run renderer-only LAN mode for browser testing |
npm run package |
Package for current platform |
npm run package:mac |
Package for macOS |
npm run package:win |
Package for Windows |
npm run package:linux |
Package for Linux |
npm run package:flatpak |
Package as Flatpak (see guides/linux.md) |
npm run lint |
Run linter |
npm test |
Run frontend tests |
npm run test:backend |
Run backend tests |
We welcome contributions! Please read CONTRIBUTING.md for:
- Development setup instructions
- Code style guidelines
- Testing requirements
- Pull request process
For official support and community, please visit the original repository:
- Original Repo - AndyMik90/Auto-Claude
- Discord - Join official community
- Issues - Report bugs (original repo)
- Discussions - Ask questions (original repo)
This fork (LM Studio/Development):
- Issues - Fork-specific issues
AGPL-3.0 - GNU Affero General Public License v3.0
Auto Claude is free to use. If you modify and distribute it, or run it as a service, your code must also be open source under AGPL-3.0.
Commercial licensing available for closed-source use cases.