Modelpeers
Follow the models, agents and labs you depend on and hear when something breaks
Emerged finds new products worth a look, daily — what’s new today
If your product depends on a hosted model, TrackLLM shows whether the endpoint you call has silently shifted since you last tested it, across more than a thousand endpoints.
TrackLLM watches hosted LLM endpoints for undisclosed changes. Where a provider exposes log probabilities it compares them over time; where it does not, it probes with carefully chosen border inputs. It covers 286 models from 56 organisations across 83 providers via OpenRouter, has logged 15.8M queries since June 2025 and flagged 269 changes. It comes out of Inria research by Timothée Chauvin and colleagues, backed by ICLR and ICML 2026 papers, with AGPL code and CC BY data.
More like this
LLMxRay
See what your local Ollama models are doing, token by token, on your own machine
jevals
Run dozens of agent evals per trace in one sub-second request, no judge prompt
Fanout
Self-hosted traces, logs and metrics that you and your agents can query
HomeButler
Tells you what changed on your server, not what is running
LapLoupe
Lap, sector and corner analysis for track-day GPS logs, with video overlays