Pretrained classifiers.
CPU only. pip install.
68 classifiers ship ready to use. Text, game state, numeric features. No GPU, no API keys, no cloud dependency.
Latest
When to Trust Your Classifier
How to use confidence scores and prediction margins to build three-tier routing: auto-route, suggest, or escalate. With real API examples
Your LLM is Probably Overkill
Side-by-side comparison of LLM prompting vs frozen embeddings + logistic regression. Same task, both approaches, with code and benchmarks
Can AI Read Your Mind?
Pick left or right — a Markov chain learns your pattern and predicts your next move. 7 game modes including Boss Fight, Survival, and a global leaderboard.
When LLMs Fail at Classification
16 models benchmarked across 3 tasks. As class count grows, LLMs collapse — Jeffy 94.3% on banking77 vs 68% best LLM.
Integrations
Live demos
Pac-Man AI
Regex parses junction descriptions into features, Jeffy classifies the best direction. 8,035 mean score, 2.5x the current #1, 3ms per decision.
Read the tutorial →
Doom Classifier
Real-time game-state classification. 24 numeric features extracted each frame decide whether to fire, turn left, or turn right.
Open demo →
Poker AI
Four AI players at a Texas Hold'em table. Each makes fold, check, call, or raise decisions from 18 game-state features, streamed live.
Open demo →
Fly Navigation
A biomechanical fruit fly forages for food via chemotaxis. Jeffy classifies walk, turn-left, or turn-right from 16 physics features at each step.
Open demo →17 English classifiers + Request a classifier
51 multilingual classifiers — 60 voice-command intents per language, frozen multilingual embeddings
Predict
Train your own