A free GitHub project directory for the TypeSafe Jev / System One model.Explore official SDKs, agent tools, open-source alternatives and Jev news.

Data updated

All tags

Projects tagged with “ai-agents”

Browse Jev GitHub projects tagged with ai-agents. Filter, sort and explore their source repositories.

  • River shooter game in Python, inspired by Atari's River Raid, played by a TypeSafe AI pilot

    ashaazami/river-run-typesafe · Python

    00
    pythonai-agentspygamepython-game
  • 2804rocky
    Say it, and your computer does it. Voice-controlled computer agent on TypeSafe Jev for macOS and Windows.

    BenjisCollector/rocky · Python

    00
    ai-agentscomputer-usemacosvoice-assistantwindowspython
  • Paste a suspicious text message. Get a straight answer and the reasons behind it.

    Sachin-chaurasiya/scam-checker-with-jev · TypeScript

    00
    ai-agentsai-agents-automationautomationtypescript
  • 2851sizeup
    Jev-powered model router for AI coding agents (omp + Claude Code): small jobs go to smaller, cheaper models.

    sxivansx/sizeup · TypeScript

    00
    ai-agentsclaude-codellmmodel-routingtypescript
  • Should I use JEV?

    maciejczub/skill-siujev · Python

    00
    agent-skillsai-agentsclassificationclaude-codecodexcoding-agentscost-optimization
  • Jev vs Laya on Bulgarian: two System One models suggest a category for each blog post. A local BgGPT names new topics.

    SciScend/system-one-categorizer-demo · Python

    00
    ai-agentsbenchmarkbggptbulgarianlayallmmodel-comparison
  • TypeSafe's System One launch claims, each as a runnable experiment: Jev vs Claude vs keyword rules through one typed interface. Calibration, parallel questions, Wikiracing. Offline in CI; --live for the real thing.

    gsaini/system-one-models-getting-started · Python

    00
    ai-agentscalibrationclaudellm-evaluationpythonstructured-outputs
  • Real-time Telegram conversation analysis with Jev (TypeSafe System One). You write the draft, Jev judges it.

    BrickerP/tg-crush · TypeScript

    00
    ai-agentsconversation-analysisllmnodejsrealtimetelegram
  • One MCP endpoint in front of all your MCP servers: Jev routes each prompt to the right server and tool, and a risk gate decides run, ask or block.

    gaharivatsa/toolbox · Python

    00
    ai-agentsclaude-codellm-toolsmcpmodel-context-protocolpython
  • Machine-made, human-judged. Jev decides the design, an LLM writes the copy, an image model illustrates it — and code ships the page in about a second for a tenth of a cent. Typed decisions with calibrated confidence, not vibes.

    mojomast/TurboSlop · TypeScript

    00
    ai-agentsdecisionsdesign-systemsgenerative-uiimage-generationllmssg
  • Guardrails for AI agent actions. Deterministic policy, Jev semantic checks, and replayable decisions.

    zyphr-labs/turnstile · TypeScript

    00
    agent-securityai-agentsclaude-codeguardrailstypescript
  • A live, graphical dojo for TypeSafe's Jev (System One) typed decision model — routing, a Tetris-playing agent, parallel swarms, and an honest Jev-vs-Claude gauntlet.

    lafollett-labs/typesafe-jev-dojo · TypeScript

    01
    ai-agentscanvasdecision-modelopenroutertetris
  • 3013typryx
    Typed answers with a probability for agent stacks: a choice, a score or a yes/no from a versioned template. Only the fields a template names leave the box, and every answer is on the record. An optional add-on to the TAIPANBOX stack, over HTTP and MCP.

    TAIPANBOX/typryx · Go

    00
    agent-governanceai-agentsai-securitygollm-evaluationmcpprobabilitytyped-decisions
  • Local text classification for Mac and coding agents: yes/no, choice and score answers in milliseconds.

    TobyNoSkillSon/Verdict · Swift

    00
    ai-agentsapple-siliconclassificationlocal-aimacosmlxswift
  • Companion code for Old Nain episode 001: wiring Jev, TypeSafe's System One model, into a local email agent. For educational use only.

    ghosthat-studio/wiring-jev-into-a-local-agent · Python

    00
    agent-memoryai-agentseducationalemail-agentemail-automationghost-hat-studiollm
  • A bounded NPC decision runtime with behavior packs, deterministic game rules and optional Jev decisions.

    gbesse/worldkit · JavaScript

    00
    ai-agentsjavascripttypescript
  • Hand one Safari window to a program, and no more than that.

    ericboehs/wrangle · Ruby

    00
    agent-skillsai-agentsapple-eventsapplescriptbrowser-automationclimacos
  • Autonomous Zork I agent: a local or hosted language model reads the game and proposes commands, and Jev (a decision model) picks one. Python harness with map memory, lessons across games, and replay.

    sailtovictory/zork_by_jev · Python

    00
    ai-agentsinteractive-fictionollamazorkpython

351–368 of 368