CommunityJev Integrations & Adapters
Clef on Ollama
Cloudflare's decision models packaged for Ollama: pull clef for the 27B model or clef-flash for the 9B one and run classification, labelling, and routing locally with the same typed-question shape.
- Published by
- Community
- Last verified
- Oct 2026
Used inJev for Software & DevTools
- Capabilities
- Open sourceRuns locally
Watch out
Local quality and speed depend on your hardware and quantization, and the Ollama library entries track Cloudflare's releases, so pin a tag if you need a fixed version.
Questions about this entry
Short answers drawn from the linked project or page.
Ollama packages Cloudflare's decision models: ollama pull clef fetches the 27B model and ollama pull clef-flash the 9B one. Once pulled, they run locally like any other Ollama model.
It keeps the evaluated state on your machine, removes per-call API cost, and gives a fixed model version, which matters when a decision sits in a loop or handles sensitive data.
The same bounded judgments as the hosted shape: classifying an image, labelling a bug report, or routing a support ticket, answered as a choice with probabilities instead of generated text.
Clef-flash at roughly 9B is the practical local target; the 27B Clef needs more memory. Quantized builds and the exact requirements are on the Ollama model pages, which move as the models update.
Yes. Workers AI serves the model from Cloudflare's network close to your users; Ollama runs it on your own hardware. The output shape is the same, so you can develop locally and deploy to Workers AI.
After the pull, no. The model runs locally, so decisions work offline, which is the main reason to choose this route over the hosted API.
No. These are Cloudflare's open decision models, not Jev. They answer the same typed-question shape, which makes them a local alternative rather than an official TypeSafe surface.
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
46.7kGitHub stars
Privacy-first, self-hosted personal knowledge management system with block-level references and a local-first Markdown editor; the project integrates Jev's decision model for high-speed document classification, flashcard intent categorization and automated tag routing.
Jev Integrations & Adapters#community#note-taking#knowledge-base
Community
siyuan-note/siyuanTypeScript
siyuan-note/siyuanTypeScript19.6kGitHub stars
Open-source TypeScript agentic operating system: a core runtime, app for web and mobile, CLI, cloud services and first-party plugins. The directory's curated summary reports it integrates TypeSafe System One decision services for sub-100ms intent classification, action dispatching and confidence-gated tool execution.
Jev Integrations & Adapters#community#agents#framework
Community
elizaOS/elizaTypeScript
elizaOS/elizaTypeScript1.3kGitHub 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/ollayaRust2GitHub stars
A ComfyUI node pack that branches a generation workflow on a plain-English question such as whether an image is too graphic for kids, running locally on Laya by default or Jev on a dropdown switch.
Jev Integrations & Adapters#community#comfyui#python
Community
dante01yoon/ComfyUI-SystemOnePython
dante01yoon/ComfyUI-SystemOnePythonThe Hugging Face hub for Laya's open System 1 checkpoints: the 421M English model at the repo root, a 322M multilingual build in a subfolder, and the typed-decisions fine-tune, all Apache-2.0.
Jev Models & Reimplementations#community#open-models#local
Community
Supersonic Labs' 144.3M-parameter decision model on mmBERT-small: choice, score, and noul answers from supplied options in one pass, 73.15% on 2,000 typed decisions, Apache-2.0.
Jev Models & Reimplementations#community#open-models#local
Community
From 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.