Skip to content

General-purpose decision layer with decision models

Projects that offer typed decisions as a generic building block (yes/no, choice, score) without targeting one domain.

57 public projects · page 2 of 2

  • DeepSeek Harness jev_decide tool that brings the Jev decision paradigm to any OpenAI-compatible LLM, or to real Jev with a key.

    ProjectprototypeTypeScript
  • BAML library adding a typed .feels() 'AI if statement' backed by Jev, with .how() for probabilities and an LLM only for writing.

    ProjectprototypeBAML
  • Rebuild of the goodvibes agent platform where Jev is targeted to make every semantic decision, with outcomes act, revise, defer or reject.

    ProjectprototypeTypeScript
  • Sample Cloudflare Worker app with three playful demos, one per Jev primitive: Noul (is it a sandwich?), Score and Choice routing.

    AppprototypeTypeScript
  • Python dialect that adds a '~' operator and jev/case blocks so a branch can ask Jev a yes/no, scale or choice question.

    ProjectprototypePython
  • Early language design where typed Jev judgments are a runtime operator, with an engine that batches judgments over shared state.

    ProjectprototypeTypeScript
  • Rust template for multi-agent orchestration with Jev as the L0 layer for typed routing, risk and escalation decisions.

    ProjectprototypeRust
  • Datadog Labs Rust library for observability control loops where Jev recommends an action and declared guards decide if it commits.

    LibraryprototypeRust
  • C/C++ compiler driver where Jev decides whether to inline each discretionary call site, compared against Clang -Oz.

    ProjectresearchPython
  • Builds auditable decision trees and runnable decision SOPs from data and a natural-language goal via LLM features and information gain.

    ProjectresearchPython
  • MCP server exposing a judge tool for typed noul, choice and score questions over JSON state, backed by Jev.

    MCP serverbetaTypeScript
  • sapho★ 1

    Rust library and CLI for compound decisions: ask Jev small questions, combine answers with rules in a YAML/JSON decision graph.

    CLIbetaRust
  • Local MCP server that lets an agent delegate a decision to Jev and get a recommended choice with percentages.

    MCP serverbetaTypeScript
  • TypeScript runtime that turns Jev's probabilistic answers into versioned, replayable decisions via ordered YAML policy rules.

    ServicebetaTypeScript
  • Self-hosted Jev-compatible /v1/systemone server using an encoder with decision heads for parallel noul, choice and score answers.

    ServicebetaPython
  • Open protocol for decision-based agents: apps expose evidence and typed decisions, Jev assesses, and app code guards commits.

    AppprototypeTypeScript
  • Decision board where one Jev request picks which of eleven livestream ideas becomes tonight's MVP, with code gating and weighting.

    DemoprototypeTypeScript
  • Agent skill that grills a plan as a design-tree interview, using Jev for typed judgments along the way.

    Demoprototype
  • Small Next.js app to paste a state, build noul, choice and score questions, and inspect Jev's typed answers and distributions.

    AppprototypeTypeScript
  • Minimal web playground to write freeform state, build custom Choice, Score and Noul questions and see live Jev probability distributions.

    AppprototypeTypeScript
  • Experimental language where questions and methods are composable values, with a Rust runtime that speaks /v1/systemone and replays runs.

    ServiceresearchRust
  • Public demo repository for Jev shared on X; the README gives no further detail.

    App
  • Small public demo repository for TypeSafe's Jev, shared on X; its README contains only a one-line description.

    App
  • Web demo where you talk nicely or nastily over time and a structured state, updated by Jev, tracks the character's mood.

    Appprototype
  • Personal experiment repository for trying the jev-latest decision model.

    Appprototype
  • Small demo app combining Jev with a Groq-hosted model for request routing and insights.

    Appprototype
  • OpenAI's Decisions API: GPT-6 Luna answers Noul, Choice and Score questions about text, JSON or images with a probability per option.

    Servicebeta