OpenClaude
ActiveDescription
Open-source coding agent CLI supporting OpenAI, Gemini, DeepSeek, Ollama, Codex, GitHub Models, and 200+ models via OpenAI-compatible APIs.
Key Features
- Multi-backend LLM support — one CLI connects OpenAI, Gemini, DeepSeek, Ollama, Codex and 200+ models
- Tool-driven coding — built-in bash, file read/write/edit, grep, glob, agents, tasks, MCP and slash commands
- Provider profiles — guided setup via /provider, save and switch between AI backend configurations
- Streaming responses — real-time token output and tool progress display for long-running tasks
- VS Code extension — desktop editor integration with one-click launch and theme sync
- Local Ollama inference — no API key needed, connect directly to local Ollama for open-source models
Use Cases
💡 Local code completion — connect to local Ollama running open-source code models, no paid API needed
💡 Multi-model code review — cross-review code changes with different backends (GPT-4o, Claude, DeepSeek)
💡 CI/CD integration — call OpenClaude in pipelines to auto-fix lint errors or generate tests
💡 Cross-platform development — same CLI workflow across macOS, Linux, and Windows
💡 Privacy-sensitive projects — full local inference, code never leaves the developer machine
Strengths & Limitations
✅ Strengths
- • Actively maintained, recent updates
- • High community interest (32.0k stars)
- • Responsive to issues, low backlog
⚠️ Limitations
- • No clear open-source license
Categories
Quick Start
# Install
npm install -g @gitlawb/openclaude@latest
# Start with OpenAI
export CLAUDE_CODE_USE_OPENAI=1
export OPENAI_API_KEY=sk-your-key-here
export OPENAI_MODEL=gpt-4o
openclaude
# Or with local Ollama
export CLAUDE_CODE_USE_OPENAI=1
export OPENAI_BASE_URL=http://localhost:11434/v1
export OPENAI_MODEL=qwen2.5-coder:7b
openclaude