Organization repository on GitHub
- Forks
- 55
- Last pushed
- Updated Sep 2026
Repo stats from the GitHub API, cached Oct 2026.
CommunityJev Models & Reimplementations
LocalJev
A local Jev-compatible POST /v1/systemone server in TypeScript that maps typed questions onto oMLX classification prompts and normalizes logprob-style answers.
- Stars
- 823
- Language
- TypeScript
- License
- MIT
- Published by
- Community
- Author
- githubnext
- Last verified
- Oct 2026
About this project
A local, Jev-compatible POST /v1/systemone API written in TypeScript for Bun, backed by DiffusionGemma through an OpenAI-compatible Chat Completions endpoint. Jev uses a typed decision API rather than an OpenAI chat API. OpenJev implements the Jev wire protocol and obtains probabilities with a special one-step DiffusionGemma structured read. Its backend depends on unmerged vLLM request extensions such as diffusionseedcanvas, diffusionreadonly, and requested token logprobs.
Quoted from the project's README. Read the full README.
Used inJev for Software & DevTools
- Languages
- TypeScript
- Platforms
- API
- Capabilities
- Open sourceRuns locally
Highlights
- README targets http://127.0.0.1:8080 with the same wire shape as hosted Jev.
- Translates state plus Choice, Score, and Noul questions into a classification prompt, then normalizes vectors into Jev-compatible answers.
- Built because vanilla oMLX lacks System One primitives; references OpenJev as prior art on the wire protocol.
Watch out
MIT. Experimental GitHub Next project; accuracy and calibration differ from hosted jev-1.13.0.
Questions about this entry
Short answers drawn from the linked project or page.
Generated and self-reported. The README says LocalJev is wire-compatible but not mathematically equivalent to OpenJev's structured logit read: it turns state and typed questions into a classification prompt, asks DiffusionGemma for a JSON probability scalar or vector, then validates, retries and normalizes. Evaluate the calibration on your own workload before relying on them.
Not for this model. DiffusionGemma support is still tracked as open in the LM Studio MLX engine and its bug tracker: the MLX backend fails to load the architecture and llama.cpp reports an unknown one. Any OpenAI-compatible endpoint can be used by changing LOCALJEV_UPSTREAM, but the probability path stays prompted and self-reported either way.
Yes. It serves POST /v1/systemone and accepts jev-latest and jev-preview as aliases so SDK defaults work. Set TYPESAFE_BASE_URL to http://127.0.0.1:8080 and any TYPESAFE_API_KEY value: LocalJev accepts any key unless LOCALJEV_API_KEY is configured to require one. Bun 1.2+ and a running inference server are the real prerequisites.
The full run is 5 models times 120 labeled examples times 2 input lengths, 1,200 requests, scored against public gold labels for AG News, BoolQ and SST-5, comparing quality, calibration, retries and latency. The --limit 3 pilot is 30 requests and the README calls it not a meaningful quality sample. Results come with caveats rather than a definitive winner.
Bun 1.2 or newer and a running oMLX server. Run bun install, copy .env.example to .env and replace the upstream API-key placeholder, then bun run start. LocalJev listens on http://127.0.0.1:8080 and serves a /ready check.
It is wire-compatible but prompted and self-reported: LocalJev asks DiffusionGemma for a JSON probability scalar or vector rather than reading its logits directly as OpenJev's structured read does. The README says to evaluate calibration on your own workload before relying on it.
It runs the same LocalJev engine against five installed models using public gold labels for AG News news categorization, BoolQ yes/no reading comprehension and SST-5 five-level sentiment, at two actual input lengths. A full run is 5 models x 120 labeled examples x 2 lengths, 1,200 requests.
Reactions & coverage
Posts, threads, and videos about this entry from around the web.
LinkedIn: What multimodal decision models actually change, and what they do not.
LinkedInJevDirectory.org
Hacker News: Decision Index 0.2.1 scores open reproductions of Jev on a frozen suite.
jackbravo4 pointsDecision Index 0.2.1 – 70 open reproductions of TypeSafe Jev's Decision ModelRead the thread on Hacker NewsHacker News: Pointer to a DiffusionGemma plus vLLM tutorial for a Jev-shaped classifier.
1 pointHow to build a Jev-style classifier with DiffusionGemma and vLLMRead the thread on Hacker NewsHacker News: A one-token logprob wrapper that also classifies webcam frames.
allanrbo151 pointsA single function Jev-like wrapper for LLMs, including vision modelsRead the thread on Hacker NewsMore Jev resources like this
1.3kGitHub stars
A local daemon that pulls open decision models and serves them on TypeSafe's /v1/systemone, so a Jev client switches hosts with TYPESAFE_BASE_URL.
Jev Models & Reimplementations#community#rust#open-models
Community
ollaya-dev/ollayaRust
ollaya-dev/ollayaRust877GitHub stars
A local server that reads next-token probabilities from a fine-tuned Spark model and returns Choice, Score, and Noul answers with zero generated tokens.
Jev Models & Reimplementations#community#python#open-models
Community
Rizzo-AI-Academy/rizzo-flowPython
Rizzo-AI-Academy/rizzo-flowPython882GitHub stars
A Node and TypeScript package that runs Convai's Laya checkpoint through ONNX Runtime, with the same system_one shape as the Python reference.
Jev Repos & SDKs#community#typescript#open-models
Community
receptron/layaTypeScript
receptron/layaTypeScript58GitHub stars
A local /v1/systemone server that reads label probabilities from a GGUF chat model, with prompt repetition and a confidence shrink toward uniform.
Jev Models & Reimplementations#community#python#open-models
Community
Mushroom-Systems/lichenPython
Mushroom-Systems/lichenPython1.3kGitHub stars
A local yes/no decision model that speaks Jev's wire format on a laptop CPU, refusing Choice and Score until those question types ship.
Jev Models & Reimplementations#community#python#open-models
Community
feder-cr/jevC++
feder-cr/jevC++58GitHub stars
An Apache-2.0 decision engine with a TypeSafe-compatible endpoint, document answers with source passages, and a ViZDoom demo that picks actions from structured game state.
Jev Models & Reimplementations#community#python#local
Community
deepanwadhwa/OpenDecisionPython
deepanwadhwa/OpenDecisionPythonFrom the Jev guides
Original write-ups on what this entry is for.
Taking a decision checkpoint out of Python: what the GGUF and browser WebGPU exports preserve, what they change, and the parity evidence the model cards publish.
Jev Tools & CLIs#open-models#local#onnx
Read article
Interface, size, license, claims — in that order. A selection guide across the system-one catalog, from a 706K form scorer to 27B Jev students.
Jev Practices & Patterns#open-models#evaluation#benchmarks
Read article
Hundreds of repositories carry the system-one tag, but the ecosystem is a dozen ideas in different sizes. A tour of the families, the licenses, and what a download does not include.
Jev Models & Reimplementations#open-models#hugging-face#local
Read article
From the Jev community
Posts from builders shipping with Jev right now.