TrackLLM
A public record of when hosted language models quietly change behaviour
Emerged finds new products worth a look, daily — what’s new today
LLMxRay
See what your local Ollama models are doing, token by token, on your own machine
If you run models through Ollama, this gives you tracing, benchmarks and cost tracking without sending a single prompt to a cloud dashboard.
LLMxRay is a browser UI for people running models locally with Ollama. It streams chat with per-token confidence shading, shows prompt caching, compares and benchmarks models on real logprobs, and tracks usage. A transparent proxy port lets other tools point at it so their calls are counted and timed, and an MCP server exposes seven read-only diagnostics. Local-only by default, Apache-2.0, by Ivan Stankovic. Ollama is the only backend, and chat confidence is estimated from timing.
More like this
Strata
Runs a 125B mixture-of-experts model on a single gaming PC, fully offline
Fanout
Self-hosted traces, logs and metrics that you and your agents can query
PicoLM
A C99 LLM engine that streams weights from disk, from Tru64 to Raspberry Pi
Sunk Cost
How long until a local LLM machine pays for itself against API bills
HomeButler
Tells you what changed on your server, not what is running