Open-source AI search agent you can self-host. Web research with cited answers, like Grok/Perplexity — but you choose the LLM (GPT-4o, Llama, Qwen, etc.) and own the entire stack. Docker Compose up and go.

Tracing + evaluation in one open-source tool. LangSmith is closed-source. Langfuse is overcomplicated. Most logging tools lack built-in eval. Auditi combines all three. 2-line auto-instrumentation captures all OpenAI, Anthropic & Google API calls. 7+ LLM-as-Judge evaluators run automatically on traces. Human annotation workflows when AI judges aren't enough. Real-time cost tracking. Turn production traces into fine-tuning datasets. Self-host with docker compose up. Python SDK, FastAPI, React.