Starting point
Users of Codex, Claude and Grok want to know when usage limits reset. Public signals about this are scattered across tweets and range from rumor to first-party statements.
UsageReset — evidence-led reset alerts for AI usage limits
UsageReset is Franz Bettag's Rust/Axum service backed by SQLite that uses xAI-assisted interpretation of public tweets from Codex-, Claude- and Grok-related accounts to produce usage-reset alerts with deterministic source, author, time and scope validation.
Problem
Role
Franz Bettag's role
Original creator and engineer of the project.
Architecture
Stack
Rust and Axum with SQLite.
Interpretation
xAI-assisted interpretation of public tweets, with deterministic validation of source, author, time and scope before a signal counts as evidence.
Evidence scale
First-party evidence of an incoming or effective reset is distinguished from plain model/rumor chatter. The NO/MAYBE/YES scale shows status; MAYBE is explicitly an inference, not a confirmed reset. Alerts are idempotent and evidence-linked.
Results and limitations
What's documented
63 automated tests passed on 5 September 2026, including advance notice, late discovery, scope matching and false-positive classification. On 5 September 2026, the public ledger showed four signals with advance notice, eight observed resets without advance notice, seven expired unconfirmed signals and no explicit retractions. Median advance notice was about 9.1 hours to publication of the confirmation source. A defensible overall prediction-accuracy figure is not yet available.
Public evidence ledger
The public evidence ledger pairs stored signals with matching outcome sources. It separates advance notice, retracted false positives, expired unconfirmed signals and observed resets without advance notice. Model rumors remain unscored. These records do not yet support an overall accuracy percentage.
Evidence
Source
Public service with evidence-linked alerts.