15 projects · checked 2026-09-20

Open reimplementations of decision models

People rebuilding the category from open weights: one-pass scorers, constrained decoding over local models, and small models trained to return a calibrated distribution. The fastest-moving cluster here.

8 of these 15 call the hosted API rather than running open weights.

SemIf2.4k ★TheoLeeCJSemantic ifs from open models, on a 3090 at home. Independent; not affiliated with Jev or TypeSafe.Python · MIT · pushed 2026-09-19 jevlike1.1k ★vinnylarougeA Jev-like model takes a piece of text and a list of N text options. It returns one probability for each option. It does this in oPython · MIT · pushed 2026-09-16 kev983 ★jaredpalmertiny Jev-like family of decision models built on top of Qwen3 you can train and run on your ownPython · Apache-2.0 · pushed 2026-09-20 reticle773 ★reticlehqAI agents can generate code, but still struggle to understand what they build. Reticle brings Jev-style machine-native runtime perception to web & desktop applications.TypeScript · NOASSERTION · pushed 2026-09-19 decider154 ★MapikaOne-pass typed decisions with calibrated probabilities (System One style model), fine-tuned from Qwen3.5-2BPython · Apache-2.0 · pushed 2026-09-20 djev-spark126 ★mmastracDiffusionGemma NVFP4 structured decisions on a DGX Spark: container recipeHTML · pushed 2026-09-19 reflex87 ★kshetrajna12A small open decision model: state + typed questions -> calibrated probabilities. A Jev / System One re-creation on Qwen3.5.Python · MIT · pushed 2026-09-20 jevmlx46 ★bnsd55Jev-style parallel constrained decisions for any MLX model on Apple Silicon. Typed, schema-valid JSON in one forward pass.Python · MIT · pushed 2026-09-20 system-one39 ★snellingioSystem One Lite is a proof-of-concept HTTP service for constrained decisions with a local language model. Send text or JSON plus oPython · MIT · pushed 2026-09-18 typesafe-ai-benchmark34 ★iammrduncanThis is a LLM Gateway that mimics typesafe ai structured output. Like an imposter Jev.TypeScript · MIT · pushed 2026-09-19 system-one-open18 ★mithalouniOpen replica of TypeSafe's Jev: typed calibrated decisions in one forward pass, on Gemma 4 E2B / Gemma 3 270M (Modal)Python · NOASSERTION · pushed 2026-09-17 OpenSourceJev16 ★sabeel111Turning an LLM model into a Jev like System.Python · MIT · pushed 2026-09-20 jevbetter13 ★olanotoluA stronger one-pass scorer over a variable list of text options. Hashed n-gram encoder, rival-aware attention, gated head, temperature scaling — with a head-to-head benchmark vs the jevlike starter design.Python · MIT · pushed 2026-09-16 jevify13 ★fidecastroSupersimple way to serve LLMs as a Jev-like endpointPython · MIT · pushed 2026-09-20 Nemotron_Jev12 ★pst2154Ask typed questions about text or JSON and inspect model-derived probability distributions in a browser. One container runs the moHTML · pushed 2026-09-18

Other things people build

Developer tooling 35

Code review gates, CI checks, agent harnesses and editor plugins. The densest cluster in the ecosystem, because a coding agent makes hundreds of small decisions per session and each one costs something.

Browser 18

Extensions and automation that judge pages: what to hide, what to click, what is worth reading. Latency matters here in a way it does not on a server.

Content 10

Moderation, summarisation triage, voice and video. Judging content rather than producing it.

Robotics and games 10

Embodied agents and game-playing systems, where a decision happens every tick and a generated reasoning trace per step is not affordable.

Find out what your data actually supports

We turn your historical decisions into a frozen test set, then tell you which model, which threshold, and how much of it you can safely automate.

Request a benchmark

Request a benchmark

© 2026 DecisionEval