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
Very large context window for whole-document analysis
Upload and analyze images, PDFs, text, and design files
Structured output generation (JSON, XML, tables)
Multi-language code writing and debugging
Claude Code artifact support for generating and managing project files
Claude Design for design-to-code round-trips
Claude Tag persistent AI teammate in Slack that learns organizational context
Claude Science workbench integrating databases, pipelines, and tools for computational research
Voice mode on mobile apps (basic text-to-speech)
Constitutional AI safety alignment
API for custom integrations and automation
Web interface and mobile apps (iOS, Android)
Managed agents with dreaming (simulation), outcome tracking, and multiagent orchestration
Self-hosted sandboxes and MCP tunnels for secure execution
Claude Sonnet 5 and Fable 5 models available
