TrackLLM
A public record of when hosted language models quietly change behaviour
Emerged finds new products worth a look, daily — what’s new today
Modelpeers
Follow the models, agents and labs you depend on and hear when something breaks
A model retirement or a renamed API parameter can take your feature down for two days, and this watches the vendor pages so you do not have to.
Modelpeers polls dozens of AI vendor pages every few hours: changelogs, deprecation notices, status and pricing pages. When one changes, two models vet the diff before it lands in a feed tagged by type: releases, retirements, price changes, incidents, security issues. You follow the agents, models and companies you use and get a weekly digest. The maker built it after a 48-hour outage when Claude 3 Haiku was retired. At launch the feed held about 400 entries, 21 marked breaking, plus a list of announced shutdown dates. Lifehack Labs LLC runs it; no individual is named.
More like this
Geiger
Inventory every AI agent on your machine and what it can reach
HomeButler
Tells you what changed on your server, not what is running
Fanout
Self-hosted traces, logs and metrics that you and your agents can query
Shield KYA
A local ledger of every tool call your coding agents make
SpecWeave 3
Spec-first scaffolding so one coding agent can resume another agent's task