LLMxRayLocal LLM Observatory

See what your AI is actually doing — token by token, layer by layer.

Chat Diagnostics

Stream tokens in real time with confidence coloring, inspect reasoning chains, and explore session metrics.

Run the same prompt across up to 4 models or settings side by side. Grid view, diff view, and metrics bar.

Evaluate models with real logprobs on standardized test suites. Radar charts, per-category breakdowns.

Upload documents, chunk and embed them locally, then search with natural language. All in IndexedDB.

Build, edit, and test tool definitions on a visual node-based canvas with bidirectional code sync.

Everything runs on your hardware via Ollama. No cloud, no API keys, no cost. Your data stays yours.

8-module progressive curriculum for AI/ML courses. From "What is a token?" to original research. Free, grounded in published science.

View Curriculum