Pick the next move fast enough for a loop that is already running, whether that loop is a game, a robot, or an agent.
An agent choosing from a long skill roster reads one truncated line per entry and often loads the wrong thing. Jev ranks every entry in one request and separately answers whether any skill applies at all, so the agent gets a short hint instead of a guess.
A model inside a control loop has to answer before the next frame. Jev returns a typed decision rather than text, and TypeSafe reports end to end latency of 70ms to 500ms, which puts a semantic judgment inside the budget of a game tick or an interface response.
Things people have built and written that match one of the use cases above.
Browser Use's fast browser agent where Jev picks the operation and the DOM element in a single request; a small LLM is only invoked to write text when typing is required. Demoed on a Google Flights search.
Official agent skill for Claude Code, Codex and other agent environments; installs via claude plugin marketplace add typesafe-ai/skills or npx skills add typesafe-ai/skills. MIT licensed.
Proof-of-concept MCP server for Jev that lets Claude Code, Claude Desktop and Codex call the model and receive probabilities they can branch on. The most-starred Jev MCP server found.
Agent that plays Super Mario Bros. by feeding structured emulator state to Jev and acting on the returned controller action.
Places Jev as a fast supervisor above slower Codex coding agents. Codex workers do the engineering while Foreman independently assesses whether the work is complete, requirements are met, tests suffice, or human input is needed.
macOS computer-use loop that OCRs the screen, classifies the next action with Jev, then clicks. Author reports roughly $0.0002 per step.
Self-hosted, versioned skills library for AI agents. Serves skills over MCP with scoped clients, and adds optional Jev recommendations for which skill to reach for.
Educational Jev-like visual inference on Apple Silicon: Qwen3.5-0.8B under MLX answers several questions about one image by reusing shared multimodal context and scoring candidates from logits. Ships a browser UI, CLI, HTTP API and sorting-factory, Breakout and camera-gesture demos.
Automatic per-turn model routing for Claude Code and OpenAI Codex. Jev sends simple work to the fast model tier and difficult work to the strong tier while preserving each CLI's native tools, sessions, permissions and authentication.
Camera-only autonomous drone simulated in MuJoCo with Jev in the control loop at 2.5 Hz.
Standalone Android agent for Mobilerun where Jev makes every action decision, with a React studio UI and an Uber booking demo.
Agent skill and runtime that uses Jev to select page elements through an agent's existing computer-use browser tools. The agent plans once, then Jev picks elements inside a continuous observe-act-verify loop without an agent turn between steps.