EVERY ENTRY HAS RECEIPTS

AWESOME
JEV

Open-source directory

Every project here really calls Jev in its source · refreshed daily

788projects
182runnable here
765code receipts

ALL 788 PROJECTSEvery project

tests/primitives.test.ts
questions: {
  severity: score,
  needs_tool: boolean,
}
runnable
@BillionsBobby94

JevRouter

A lightweight Jev-powered router for models, tools, and subagents

Agent toolingTypeScript
src/gate.ts
questions: {
  destructive: boolean,
  exfiltration: boolean,
  beyond_scope: boolean,
  // +1
}
runnable
@y0usaf93

pi-jev

TypeSafe Jev as a decision layer for the Pi coding agent: a measured tool-call gate plus jev_ask for typed, calibrated answers

Agent toolingTypeScript
examples/workflows/stale-todo-audit.ts
questions: {
  stale: choice,
}
runnable
@devagrawal0976

stanley-code

Bounded TypeSafe Jev workflows for coding agents.

Agent toolingTypeScript
test/classify.test.js
questions: {
  relevant: boolean,
}
runnable
@kbhuw46

jev-sift

Classify first. Read selectively. A portable agent plugin and MCP tool for batch text classification.

Agent toolingJavaScript
src/router.py
questions: {
  intent: choice,
  reuse_cache: boolean,
  needs_subagent: boolean,
  // +2
}
runnable
@Bodila5125

grok-bot-jev

Connect TypeSafe Jev to Grok Bot as a cheap decision layer - usage gates, skill template, examples

Agent toolingPython
src/mcp/tools.test.ts
questions: {
  refund: boolean,
  team: choice,
}
runnable
@tacticocc25

Jevbridge

ACP and MCP adapter that bridges TypeSafe Jev with any LLM — computer use and typed decisions alongside Codex, Claude, Grok, and OpenCode.

Agent toolingTypeScript
scripts/benchmark.mjs
questions: {
  ok: boolean,
}
runnable
@burnigtm19

jev-mcp

MCP server that puts TypeSafe Jev on the coding loop in Cursor, Codex, and any MCP client

Agent toolingTypeScript
src/commands.ts
questions: {
  is_billing: boolean,
  category: choice,
}
runnable
@TheoOliveira18

pi-jev

Semantic tool routing and typed System One decisions for the Pi coding agent using TypeSafe Jev

Agent toolingTypeScript
src/guard.js
questions: {
  directed: boolean,
  kind: choice,
}
runnable
@leepokai11

jev-guard

Auto mode for every coding agent, built on Jev: risk-scores every tool call with session context (deny / ask / allow), flags prompt injection in results, checks skills and plugins. Claude Code, Codex, Copilot, Gemini, Cursor, pi, OpenCode, ACP.

Agent toolingJavaScript
scripts/smoke.ts
questions: {
  is_urgent: boolean,
  department: choice,
  frustration: score,
}
runnable
@Brainwires10

jevwire

Jev decision layer for agents: MCP server, embeddable DecisionModel library, and an escalate-only Claude Code plugin (TypeSafe AI's Jev)

Agent toolingTypeScript
test/jev.test.ts
questions: {
  skill: choice,
}
runnable
@madeye10

pi-jev

Jev-assisted file retrieval and request caching for faster Pi workflows

Agent toolingTypeScript
belay.mjs
questions: {
  claims_done: boolean,
  claims_verified: boolean,
  verification_applies: boolean,
  // +1
}
runnable
@valentynkit9

jev-belay

Claude Code Stop hook that blocks an unverified done: reads the transcript for evidence, asks Jev once, fails open on everything else

Agent toolingJavaScript
extensions/quiet-ask/packs/intent.ts
questions: {
  intent: boolean,
}
runnable
@HyunjunJeon8

pi-quiet-ask

TypeSafe Jev as the pi coding agent's quiet decision layer

Agent toolingTypeScript
test/backends.test.ts
questions: {
  is_bug: boolean,
  team: choice,
  urgency: score,
}
runnable
@shitianfang8

jev-use

Claude Code / Codex / pi plugin that hands agent steps needing no text output to Jev (TypeSafe's judgment model) — measured p50 ~230 ms and ~$0.02 per 1,000 judgments, with typed escalation back to the LLM

Agent toolingJavaScript
scripts/demo.mjs
questions: {
  intent: choice,
  isUrgent: boolean,
}
runnable
@matthewp7

flue-jev-demo

Flue agent routing with TypeSafe Jev through Cloudflare AI Gateway

Agent toolingTypeScript
src/guard.ts
questions: {
  context_needed: choice,
}
runnable
@harshwasan6

pi-jev-sentinel

Pi coding-agent extension: TypeSafe Jev checks for tool calls, tool outputs and replies (prompt injection, approvals, secret scrubbing, task pinning)

Agent toolingTypeScript
test/jev-pin.test.ts
questions: {
  q1: boolean,
}
runnable
@Kevthetech1435

super-jev

A small, extensible decision-to-action harness for TypeSafe Jev

Agent toolingPython
service/jev.mjs
questions: {
  connected: boolean,
}
runnable
@Devin-AXIS4

jev-dsh-decision

Jev DSH 决策引擎|面向 Agent Harness 的结构化决策插件。原生支持 DeepSeek Harness,通过 iPolloWork 支持 OpenCode、Codex Harness。

Agent toolingJavaScript
examples/standalone-game/src/index.ts
questions: {
  is_impossible: boolean,
}
runnable
@buberlo3

dsh-jev

Jev-powered decision layer for DeepSeek Harness

Agent toolingTypeScript
tests/typesafe-jev.test.ts
questions: {
  is_urgent: boolean,
  frustration: score,
}
runnable
@buchmark3

claude-jev

Claude Code plugin that scores review findings, debug hypotheses and design options with TypeSafe's Jev — calibrated probabilities instead of one more opinion.

Agent toolingTypeScript
test/key.test.mjs
questions: {
  is_urgent: boolean,
}
runnable
@cyberofficial3

dsh-plugin-jev

Agent-facing TypeSafe Jev (System One) for the DSH Web GUI. The model itself

Agent toolingJavaScript
hooks/suggest.ts
questions: {
  needs_skill: boolean,
}
runnable
@BeLazy1672

typesafe-mod

Claude Code mod that routes decisions to TypeSafe's Jev model: ranks installed skills per prompt, and answers the agent's own this-or-that questions when confident.

Agent toolingTypeScript
source/jev-workflows/src/contracts.ts
questions: {
  category: choice,
  reached_assertion: boolean,
  missing_context: boolean,
}
runnable
@integrate-your-mind2

jev-codex-plugin

Open-source Codex plugin for TypeSafe Jev decision consultation, failure diagnosis, and evidence-based completion review

Agent toolingJavaScript
router.mjs
questions: {
  complexity: score,
  needsPlanning: boolean,
}
runnable
@jcpsimmons2

jev-model-router-demo

Throwaway Jev demo: route coding tasks to Grok Build or Codex Astra

Agent toolingJavaScript
src/policy.ts
questions: {
  destructive: boolean,
  exfiltration: boolean,
  privilege: boolean,
  // +4
}
runnable
@RiskAverseTech2

toolgate

Open auto mode for AI agents — a calibrated tool-call firewall powered by TypeSafe Jev. Ships as a Claude Code hook

Agent toolingTypeScript
skills/tenbin/templates/questions.py
questions: {
  category: choice,
  bug_severity: score,
  has_repro_steps: boolean,
  // +2
}
runnable
@simota2

tenbin

MCP server and agent skill for the TypeSafe AI System One API (Jev): decompose a judgment into Choice / Score / Noul questions, lint them, measure on labelled data, and put calibrated thresholds in code

Agent toolingTypeScript
test/gateway.test.ts
questions: {
  relevant: boolean,
  category: choice,
}
runnable
@tonyzdev2

pijev

PiJev: a terminal coding agent with Jev in the loop — Jev ranks the repository's files before the first call, picks skills and triages failures; your coding model writes the code. Built on Pi.

Agent toolingTypeScript
agent/extensions/lib/jev-client.ts
questions: {
  ping: boolean,
}
runnable
@yunusemrejr2

yunuspi

Yunus Pi is a heavily customized harness experience built on top of a forked Pi harness (pi.dev). It uses patches, extensions, skills, and custom provider configs to customize the overall experience. It uses advanced machine learning, Jev, Cactus Needle 3 and similar technologies.

Agent toolingJavaScript
src/jev/real.ts
questions: {
  action: choice,
  asset: choice,
  condition_operator: choice,
}
runnable
@axiomarchitecture1

axiom-agent-runtime

Reference prototype exploring agentic commerce: TypeSafe/Jev → Axiom → Argent → Silverscript on Kaspa.

Agent toolingTypeScript
scripts/smoke.ts
questions: {
  severity: score,
  area: choice,
}
runnable
@BYK1

jev-mcp

An eval-first MCP server for TypeSafe's Jev, a System One model that returns typed judgments (noul, choice, score) with probabilities instead of generated text.

Agent toolingTypeScript
test/adapters.test.ts
questions: {
  destructive: boolean,
  secrets: boolean,
}
runnable
@clownware1

bouncer

Jev-powered Judgment layer for Claude Code. Stops paying reasoning prices for if-statements: a PreToolUse hook scores every tool call against a YAML policy you own — allow / deny in ~100 ms, no LLM in the loop. TypeSafe Jev now, local models next. Dry-run by default, calibration table published.

Agent toolingTypeScript
.claude/hooks/warden.js
questions: {
  is_exquisite_and_dynamic: boolean,
  animation_verdict: choice,
  primary_deficiency: choice,
}
runnable
@connectedGraph1

claude-jev-warden

Real-time quality gate and Art Director Warden for Claude Code powered by TypeSafe Jev 1.13 non-autoregressive decision model

Agent toolingHTML
lib/review.ts
questions: {
  needs_rewrite: boolean,
  visual: choice,
}
runnable
@eachann10241

pi-jev-reply

Pi extension: clearer replies via Jev review + optional rewrite/visuals

Agent toolingTypeScript
scripts/jev-probe.ts
questions: {
  is_urgent: boolean,
  department: choice,
}
runnable
@emirbartu1

opencode-system-one

Opencode plugin using Jev (system one model) as part of software development process. Not affiliated with Opencode team.

Agent toolingTypeScript
src/cli/doctor.ts
questions: {
  alive: boolean,
}
runnable
@FrancoisChastel1

jev-code

Jev, TypeSafe's System One classifier, as a tool inside Claude Code, Codex, Pi, and OpenCode: typed classify, check, score, rank, and ask, plus one-command setup.

Agent toolingTypeScript
lib/jev.ts
questions: {
  outOfScope: boolean,
  contradictsPrevious: boolean,
  shouldFlag: boolean,
}
runnable
@getexcited1

stepwarden

Every tool call your agent makes, checked before it runs. A Claude Code plugin that uses TypeSafe AI's Jev to verify each pending tool call against the session plan, then allows it, asks you, or blocks it. Proof of concept

Agent toolingTypeScript
mcp_server.py
questions: {
  scope_alignment: score,
  touches_state: boolean,
  breaks_contracts: boolean,
  // +2
}
runnable
@greenyamao1

Antigravity-mcp-semantic-search-with-TypeSafeAi

Fast semantic code search & diff sanity auditor for AI coding assistants (Antigravity, Cursor, Claude Code) powered by TypeSafe System One.

Agent toolingPython
packages/core/src/find.ts
questions: {
  edit: choice,
  contract: choice,
  caller: choice,
  // +2
}
runnable
@Kelbie1

hunch

Semantic code review with Jev, plain-English rules and Agent Skills.

Agent toolingTypeScript
src/jev/analyze.ts
questions: {
  needs_vision: boolean,
  needs_tools: boolean,
}
runnable
@Mandrilsquad14411

jev-model-router

Pick the best AI model and reasoning effort for any task in ~1s. Plugin for Claude Code, Claude Desktop and Codex, powered by TypeSafe's Jev decision model and live OpenRouter pricing. Balance intelligence, speed and cost, or choose your priority.

Agent toolingTypeScript
src/lib/product.ts
questions: {
  disposition: choice,
  risk: score,
  data_exfil_risk: boolean,
  // +2
}
runnable
@ndolinschi1

toolgate

Agent tool/MCP call gate — allow / ask_human / deny via TypeSafe Jev

Agent toolingTypeScript
src/jev.mjs
questions: {
  relevance: choice,
}
runnable
@zbush1

jev-context

Codex code-search plugin using Jev relevance filtering with auditable token metrics

Agent toolingJavaScript