Autonomous dinosaur ecosystem where code runs the physics and TypeSafe's Jev decides each creature's intent from prose laws. Pixel-art web UI with a live Jev monitor (JSON in/out per tick), interchangeable brains (hybrid / full Jev / offline). Experimental Jev integration.
Classification & labelling — page 3
Classifiers for support tickets, documents, content and user intent. Jev returns a label and a confidence instead of generated text.
59 active projects match this task, ordered by traction.
Label every sentence of a document with calibrated probabilities from Jev, rendered as a heatmap
the realtime sentiment analysis and context-aware backchanneling with Pipecat
Basket — Snowplow grocery ecommerce demo with TypeSafe Jev purchase-intent classification
No project description available.
Semantic command palette (Ctrl+K) ranked by intent with TypeSafe Jev — one Choice call, the probability distribution IS the ranking
Zero-shot text classification: TypeSafe Jev vs BERT-family zero-shot (NLI, embeddings) on 6 public tasks + PAWS pairs, with label-equivalence curves and an arXiv contamination control
Hunting label errors in popular text-classification datasets with TypeSafe Jev
weekend project using Jev to automate trace / data labeling for a provided labeling taxonomy.
0
Merge-gate triage for a red CI run: cluster the failures, let TypeSafe Jev label the cause, and return Gate: PASS (infra noise) or Gate: BLOCK (a real failure). Playwright, Jest, pytest.
Mailbox cleanup CLI with AI — trash/move/label/route mail using Jev or chat model