Decision Models
Typed, calibrated System-1 decisions: models that answer a choice, a score or a yes/no in one pass instead of generating text.

Nokia research: turn any open LLM into a Jev-style decision model. Typed choice, yes/no or score from one prefill, de-biased with no labels or a fitted head, served on vLLM.

Contrastive Language Models: CLM-8B, an open System-1 decision model scoring states against actions — typed choice/score/yes-no answers on a TypeSafe-compatible API, up to 9x faster than Jev.

Markdown to knowledge graph with an ontology you write: a small local decision model answers closed yes/no questions per candidate, and your cutoff keeps, queues for review or drops each link.

Open reproduction of TypeSafe's Jev: a LoRA + readout head on Qwen that answers many typed questions about one document in a single prefill pass, returning calibrated probabilities.

Non-autoregressive decision engine: typed choice, score and yes/no answers over text in one forward pass (~33 ms), 100+ languages, calibrated probabilities, a router picking the checkpoint.
GitHub Next's local Jev bridge: a Bun/TypeScript POST /v1/systemone that translates typed decision questions into prompts for DiffusionGemma behind any OpenAI-compatible endpoint.
Postgres extension for plain-language WHERE clauses: jev(row,'the customer is angry') filters, ranks and classifies rows via TypeSafe's Jev decision model. No embeddings, no vector column.
Strands' small decision model (2B, Qwen3.5-based): pick between options, answer yes/no or rate on a scale with calibrated confidence. CLI and /v1/systemone server on CUDA, MPS, MLX or CPU.
macOS computer-use loop at ~$0.0002/step: OCR + accessibility tree read the screen, a TypeSafe classifier picks the next action, code clicks; an LLM writes only free text.

Rust inference engine for on-device AI on Apple Silicon (Metal, unified memory) with Swift, Python and TS bindings, OpenAI-compatible server and a TypeSafe System One decision-model API.