A curated list of Jev use cases, projects, SDKs, tools, and learning resources.
Jev is the first System One model from TypeSafe AI — an AI model that returns typed decisions (Choice, Score, Noul) with calibrated probabilities instead of generated text.

Looking for real-world Jev use cases with numbers? madewithjev.com is a directory of what people are building with Jev — every build with the cost, latency, and source the author reported. Submit yours →

Jev launched in early access on September 15, 2026. This list is unofficial and not affiliated with TypeSafe AI. Pull requests are welcome — the ecosystem is days old and growing fast.

• What is Jev?
• Jev vs LLM
• Pricing, limits, and access
• Quick start
• Official resources
• Community
• Featured builds with real numbers
• Jev guides by madewithjev.com
• What people use Jev for, by job
• SDKs and clients
• Applications
  • Browser and computer-use agents
  • Search, retrieval, and data
  • Developer tools and code review
  • Model routing
  • Business and vertical apps
  • Robotics and hardware
• Demos and games
• Agent tools and MCP servers
• Use cases by industry
• Patterns
• Cookbooks
• Benchmarks and evaluations
• Research and open models
• Articles and coverage
• Discussions
• FAQ
• More guides, integrations and lists
• Related lists
• Contribute

Large language models generate text. Jev does not. It evaluates typed questions against a state and returns values your code can branch on, sort by, and route with — plus calibrated probabilities and confidence. TypeSafe AI calls this model class a System One model: fast, structured decisions that software can use directly, trained with RLCD (Reinforcement Learning for Calibrated Decisions).

text or JSON state + typed questions → constrained answers + probabilities → your code

Jev exposes three question types. Questions in one request run in parallel against the same state.