OpenAI-compatible LLM proxy that maximizes your Ollama Cloud subscription.
Features:
- /v1/chat/completions router with token tracking
- /v1/messages Anthropic proxy
- 8 search/scrape API emulators (Tavily, Exa, SearXNG, Firecrawl, Serper, Jina, Cohere, Brave)
- Automatic fallback to secondary providers with configurable timeouts
- Streaming support with first-chunk fast failover
- Web dashboard with analytics, config, and usage monitoring
- Caching layer (beta)
- CLI for setup, status, analytics, key management
- Docker and systemd deployment support
- Backward compatible with OCT (ollama-cloud-tools) installations
