Features
OpenAI-compatible REST API at localhost:8000/v1
Access GPT-4 and GPT-5 models
Streaming responses (token-by-token output)
Multi-turn conversation support with conversation_id
No API key or billing required
Python library with client.chat() method
Docker deployment support
Self-hosted – runs locally, no external dependencies
Supports system messages and chat history
Configurable model selection
Automatic session login and refresh
Works with official openai SDK as drop-in replacement
Cross-platform: Windows, macOS, Linux
Rate limiting configurable via environment variables
Minimal setup: clone, install, sign in, run
Local model execution for offline inference
Connect online APIs: OpenAI (ChatGPT), Anthropic (Claude), Google (Gemini), Meta (Llama), Mistral AI, Alibaba (Qwen),
123+ HuggingFace models available
Memory feature (coming soon) for context persistence
Minimalist UI with dark mode
Open source under MIT license on GitHub
Cross-platform desktop app (Mac, Windows, Linux)
Version 0.8.3 with bug fixes and performance improvements
