awesome-jev
A curated list of Jev use cases, projects, SDKs, and resources. Jev is TypeSafe AI's System One model for fast, typed decisions in software — Choice, Score, and
What is awesome-jev?
A curated list of Jev use cases, projects, SDKs, and resources. Jev is TypeSafe AI's System One model for fast, typed decisions in software — Choice, Score, and Noul with calibrated probabilities.
Overview of awesome-jev
What it is
Jev is TypeSafe AI's System One model for fast, typed decisions in software. It returns typed values (Choice, Score, Noul) with calibrated probabilities instead of generated text. Jev evaluates typed questions against a state and returns values that code can branch on, sort by, and route with. It is trained with RLCD (Reinforcement Learning for Calibrated Decisions). Jev launched in early access on September 15, 2026.
Key features
- Returns typed decisions: Choice (pick one from a list), Score (rate on a rubric), Noul (true/false 0–1) with calibrated probabilities and confidence.
- Parallel questions: multiple questions in one request run in parallel against the same state.
- Fast: vendor-reported 70–500 ms end-to-end.
- No output token cost: $0.042 per 1M input tokens; output tokens are free.
- Up to 255 options per Choice question.
- Text only modality.
- Accessible via direct API, Vercel AI Gateway, or Cloudflare Workers AI.
Use cases
Classify, route, score, detect, rank, extract, verify, and gate automation. Jev is used for browser and computer-use agents, search and retrieval, developer tools and code review, model routing, business and vertical applications, robotics and hardware, demos and games, and agent tools. It is suited for any task where a brittle regex or an LLM returning JSON would otherwise be used.
Getting started
Get an API key from the TypeSafe console. Python — pip install typesafe-sdk python from typesafe_sdk import Choice, Noul, Score, TypeSafeClient state = {“ticket”: “I was charged twice and need the duplicate refunded today.”} with TypeSafeClient() as client: # reads TYPESAFE_API_KEY from the environment response = client.system_one( state=state, questions={ “intent”: Choice( instructions=“What is the customer's main request?”, criteria={ “refund”: “The customer wants money returned.”, “technical_help”: “The customer needs a bug or integration fixed.”, “information”: “The customer is asking for information only.”, “other”: “None of the other options clearly fits.”, }, ), “is_urgent”: Noul(instructions=“Does the ticket explicitly communicate time pressure?”), “frustration”: Score( instructions=“How frustrated does the customer appear?”, criteria=[“Calm and neutral”, “Concerned but civil”, “Very angry or using strong language”], ), }, ) print(response.answers[“intent”].choice) # “refund” print(response.answers[“is_urgent”].noul) # 0.0–1.0 print(response.answers[“frustration”].score) # probability-weighted rubric position JavaScript / TypeScript — npm install @typesafe-ai/sdk ts import { choice, noul, score, TypeSafeClient } from “@typesafe-ai/sdk”; const client = new TypeSafeClient(); const result = await client.systemOne({ state: { ticket: “I was charged twice and need the duplicate refunded today.” }, questions: { intent: choice(“What is the customer's main request?”, { refund: “The customer wants money returned.”, technical_help: “The customer needs a bug or integration fixed.”, information: “The customer is asking for information only.”, other: “None of the other options clearly fits.”, }), isUrgent: noul(“Does the ticket explicitly communicate time pressure?”), }, });
License and pricing
License is not stated (NOASSERTION). Pricing: $0.042 per 1M input tokens; output tokens are free. Listed limits: 250,000 tokens/second, 1,200 requests/minute. Choice cardinality up to 255 options. Direct access via waitlist; no-waitlist access through Vercel AI Gateway and Cloudflare Workers AI.
Based on the project's public README and repository metadata.