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
src/foreman/foreman/jev.py
from typesafe_sdk import AsyncTypeSafeClient, RetryPolicy
@thruwire408

foreman

Software factory foreman based on TypeSafe's Jev model

Agent toolingPython
src/config.mjs
import { choice, score } from "@typesafe-ai/sdk";
@gargpratyush217

jev-router

Route to the cheapest model in claude code for your task using jev-router

Agent toolingJavaScript
src/server/recommendations.ts
? "https://api.typesafe.ai/v1/systemone"
@kitze200

skillbox

Self-hosted, versioned skills library for AI agents. MCP, scoped clients, and optional Jev recommendations.

Agent toolingTypeScript
src/jev/client.ts
export const JEV_API_ENDPOINT = "https://api.typesafe.ai/v1/systemone";
@NiazMorshed2007171

jev-review

Local-first MCP plugin for continuous software-quality review by AI coding agents, powered by Jev.

Agent toolingTypeScript
src/index.ts
import { choice, noul, score } from "@typesafe-ai/sdk";
@jkudish121

jev-mcp

Fast, cheap, typed judgments from TypeSafe's Jev model, as MCP tools.

Agent toolingTypeScript
.claude-plugin/marketplace.json
"name": "jev",
@dbreunig120

building-with-jev-skill

A skill for writing and improving programs that call Jev, TypeSafe's System One model

Agent tooling
cmd/evaluate/evaluate_test.go
if r.URL.Path != "/v1/systemone" || r.Header.Get("Authorization") != "Bearer k" {
@itsmostafa118

typesafe-mcp

mcp connector to give your AI agent direct access to typesafe ai's jev model

Agent toolingGo
src/jev.ts
export const SYSTEM_ONE_URL = 'https://api.typesafe.ai/v1/systemone';
@tamaratran118

jev-pruner

Claude Code plugin: trim long Bash output with TypeSafe Jev before the model sees it

Agent toolingTypeScript
agent/lib/jev-router.ts
import { TypeSafeClient, choice, noul, type ChoiceCriteria, type EntryType } from "@typesafe-ai/sdk";
@vinilana95

jev-eval-agent

🇺🇸 English · 🇧🇷 Leia em português

Agent toolingHTML
src/transport.rs
//! port, empty or root path only. Canonical origins append `/v1/systemone`
@Dicklesworthstone69

skillranker

Rust CLI powered by Jev from TypeSafe.ai that ranks agent skills for the next step using live session context. Includes Claude Code hooks, structured JSON, abstention, and local feedback. Requires a TypeSafe API key.

Agent toolingRust
jevkit/client.py
"""One small, strict client for TypeSafe Jev (POST /v1/systemone).
@kerpopule68

hermes-jev-skills

Jev-powered model routing, memory, compaction, skill selection, computer and browser use for Hermes agents (also Claude Code and Codex)

Agent toolingPython
src/cli.ts
baseUrl: process.env.JEV_BASE_URL || 'https://api.typesafe.ai/v1/systemone',
@IAmUnbounded54

save-token-jev-clean

Portable, Jev-guided context compaction for coding agents.

Agent toolingTypeScript
packages/router/src/commands/runtime.ts
import { createLiveTypeSafeClient, type TypeSafePort } from "../semantic/typesafe-client.js";
@nidhi-singh0246

agent-router

CLI that picks Cursor, Claude Code, Codex, or OpenCode + model/effort for a task, then launches it. Powered by Jev and Herdr

Agent toolingTypeScript
app/streamlit_app.py
from typesafe_sdk import AsyncTypeSafeClient, TypeSafeError
@jexp40

neo4jev

Typesafe.ai System One Model Jev navigating a Neo4j graph by using a classifier over neighbouring relationships

Agent toolingJupyter Notebook
plugins/jev-rules/hooks/lib/jev.mjs
url: "https://api.typesafe.ai/v1/systemone",
@EliaAlberti37

jev-rules

Jev picks which of your rules apply to each prompt, so Claude only sees the ones that matter.

Agent toolingJavaScript
scripts/askjev.py
ENDPOINT = "https://api.typesafe.ai/v1/systemone"
@shantanugoel34

ask-jev-skill

Skill for Hermes, and other agents, to ask typesafe's jev

Agent toolingPython
plugins/jev-desktop/scripts/bridge-client.mjs
const validUrl=url.protocol==='http:' && url.hostname==='127.0.0.1' && /^\d+$/.test(url.port) && url.pathname==='/v1/systemone' && !url.username && !url.passwor
@yikangy873-gif24

jev-desktop

TypeSafe Jev action selection inside Codex Computer Use

Agent toolingJavaScript
src/jev/transport.ts
TypeSafeClient,
@jomatsu17

pi-jev-auto-mode

Jev (TypeSafe System One) backed auto mode for the Pi coding agent: semantically auto-approves bash, write, and edit tool calls and fails closed when a decision cannot be made.

Agent toolingTypeScript
src/judge.ts
baseURL: "https://api.typesafe.ai",
@zszz314

Pi-Jev-Guide

原版 Pi Coding Agent 插件:按时机配置规则,并自带风险检查、输出脱敏、重复失败和缺少验证提醒。

Agent toolingTypeScript
src/engine.rs
endpoint: "https://api.typesafe.ai/v1/systemone".to_string(),
@AkashPriyadarshii11

jev-seo

100% free ₹0 agent-first SEO & GEO CLI suite and MCP server in Rust replacing Semrush and OpenSEO via DuckDuckGo and TypeSafe Jev System One

Agent toolingRust
jev_mcp/__init__.py
logging.getLogger("typesafe_sdk").setLevel(logging.WARNING)
@blakestone-x11

jev-mcp

MCP server for TypeSafe Jev: typed classify, score, check, match and screen for any agent, with confidence on every answer

Agent toolingPython
src/agents.ts
id: "jev", name: "Jev (TypeSafe AI)",
@whyashthakker11

beam-cli

Monitoring & Safety layer for all your agents. Open Source CLI & Skills for Claude Code, Codex, Cursor, Jev and your preferred agents.

Agent toolingTypeScript
internal/typesafe/client.go
endpoint     = "https://api.typesafe.ai/v1/systemone"
@BorisLeMeec10

jev

A claude code plugin for jev

Agent toolingGo
scripts/run_cases.py
ENDPOINT = "https://api.typesafe.ai/v1/systemone"
@altryne9

jevify

An agent skill to discover TypeSafe Jev opportunities, design typed questions, and learn from recent community experiments.

Agent toolingPython
package.json
"jev",
@imMamdouhaboammar9

fable-jev

⚡ Sub-100ms cognitive reflexes for autonomous coding agents. Powered by TypeSafe AI's Jev & get-fable.

Agent toolingTypeScript
__init__.py
"base_url": "",            # default https://api.typesafe.ai
@DECRUX98128

typesafe-skill-router

TypeSafe (Jev) skill routing for Hermes Agent: names the one skill worth loading, before the model call. Opt-in, stdlib only, ~$0.001 per routed turn.

Agent toolingPython
src/jev_router/transport.py
_ENDPOINT = "https://api.typesafe.ai/v1/systemone"
@GodsBoy8

jev-agent-skill-router

Typed, confidence-aware agent skill routing with TypeSafe Jev.

Agent toolingPython
hermes_jev/client.py
TYPESAFE_BASE_URL = "https://api.typesafe.ai"
@keeltrace8

hermes-jev

Typed System One decisions, ranking, verification, and an opt-in Hermes tool gate using TypeSafe Jev.

Agent toolingPython
baslat.py
'provider': provider, 'base_url': 'https://ai-gateway.vercel.sh/typesafe' if vercel else 'https://api.typesafe.ai',
@fornhere7

hafiza-os

Linux, macOS ve Windows için kaynaklı ikinci beyin. Claude Code, Codex ve Antigravity adaptörleri; yerel Markdown kasa, ayrı hafıza incelemesi, isteğe bağlı Mem0/Jev.

Agent toolingPython
scripts/jev_client.py
ENDPOINT = "https://api.typesafe.ai/v1/systemone"
@win4r7

jev-skill-suggester

用 TypeSafe Jev 推荐已安装 Skill / Bounded installed-skill recommendations with TypeSafe Jev. Python CLI, Codex skill, bilingual docs and live examples.

Agent toolingPython
tools/typesafe_query.py
base_url="https://api.typesafe.ai", retry=RetryPolicy(max_retries=1),
@3clyp505

a0-typesafe-ai

TypeSafe AI Jev judgments for Agent Zero, with typed tools and probability cards.

Agent toolingPython
packages/packs/src/loader.ts
} from "@typesafe-ai/sdk";
@AbdelStark4

bicameral

Hybrid coding harness: System 2 writes, System 1 (Jev) runs reflexes.

Agent toolingTypeScript
packages/jev-pref/src/config.js
model: undefined, // undefined = advocaat default (jev-latest / typesafe-ai/jev)
@doeixd4

jev-pref

Turn your AGENTS.md preferences into a fast, Jev-powered AI linter.

Agent toolingJavaScript
jev_ultrafast_mcp/config.py
TYPESAFE_ENDPOINT = "https://api.typesafe.ai/v1/systemone"
@jiawei6864

jev-ultrafast-mcp

Hand the browser work off: an MCP server where a decision model drives the page for your agent, so a flow costs one tool call instead of a turn per click. Ref-based element tables, code-checked assertions, zero-model macro replay. Speaks CDP to your Chrome.

Agent toolingPython
src/jev_auto_mode/cli.py
"--provider", choices=["jev", "haiku", "anthropic"], required=True
@RahulBalakavi4

claude-code-jev

Experimental Jev permission gate for Claude Code via OpenRouter, with reproducible latency and cost benchmarks

Agent toolingPython
jev_studio/cli/provider.py
return (env.get("TYPESAFE_BASE_URL") or "https://api.typesafe.ai").rstrip("/")
@utk21034

jev-studio

if you're experimenting with jev it will be easier from here

Agent toolingPython
scripts/refresh-jev-research.sh
for u in "https://docs.typesafe.ai/llms.txt" "https://evals.typesafe.ai/" "https://openrouter.ai/typesafe/jev-1.13"; do
@246013

Augustus

Agent skill: design judgment-assisted systems with TypeSafe Jev (System One). Maps Choice/Score/Noul onto decision theory, reranking, and routing. Composition algebra, question design, validation gates. MIT.

Agent toolingPython
client.py
Thin httpx wrapper around POST https://api.typesafe.ai/v1/systemone.
@ajensenwaud3

hermes-jev-plugin

TypeSafe Jev (System One) decision tools for Hermes Agent: jev_check / jev_route / jev_score / jev_evaluate

Agent toolingPython
skills/jev-judgment/scripts/jev.py
This is a thin pass-through for ``POST /v1/systemone``. The request body
@HyunjunJeon3

jev-judgment

Agent Skill: send closed coding-agent judgments to TypeSafe Jev

Agent toolingPython
src/request.ts
export const SYSTEM_ONE_URL = 'https://api.typesafe.ai/v1/systemone';
@leonaaardob3

fast-dev-compaction

Codex plugin: verbatim Jev-guided context restoration around session compaction. Port of tamaratran/fast-jev-compaction to Codex lifecycle hooks.

Agent toolingTypeScript
src/jev.ts
export const JEV_URL = process.env.CANNY_JEV_URL ?? "https://api.typesafe.ai/v1/systemone";
@qkal3

Canny

Stops AI coding agents from claiming work is done without evidence. Deterministic hooks decide, TypeSafe's Jev advises. Append-only ledger, zero runtime dependencies.

Agent toolingTypeScript
src/lib.ts
return { kind: "connection", message, retryable: true, hint: "Check network access to api.typesafe.ai." };
@rashedInt323

jev-mcp

MCP server exposing TypeSafe Jev as typed, calibrated judgment tools: classify, score, check, batched ask. Ships as a Claude Code plugin.

Agent toolingTypeScript
src/lib/risk/jev.ts
process.env.TYPESAFE_ENDPOINT ?? "https://api.typesafe.ai/v1/systemone";
@246012

rh-guard

Reward-hack radar for coding agents: structural denies + TypeSafe Jev System One sidecar for Claude Code & Cursor hooks

Agent toolingTypeScript
jev_mcp_dispatcher.py
from typesafe_sdk import Choice, Noul, TypeSafeClient
@abhishekashokvkumar2

jev-mcp-dispatcher

Natural-language MCP tool dispatcher powered entirely by TypeSafe's Jev — no general-purpose LLM. Discovers a simple MCP server's tool signatures at runtime and uses Jev's typed primitives (Choice/Noul) to pick the right tool and extract its arguments straight out of the sentence.

Agent toolingPython
src/classifier.ts
import { noul, TypeSafeClient, type NoulResponse } from "@typesafe-ai/sdk";
@alexsatch2

omp-auto-mode

Plugin for oh-my-pi that uses Typesafe Jev API to classify tool calls as safe/unsafe/ask

Agent toolingTypeScript
__init__.py
_TOOLSET = "jev"
@bojansandhaus2

jev-decisions

Jev Decisions Plugin for Hermes (and other AI Agents): tool risk reviews, human approval recommendations, evidence checks, and a local decision journal.

Agent toolingPython
src/jev.ts
import type { EntryType, NoulQuestion as SdkNoulQuestion, Usage } from '@typesafe-ai/sdk';
@CrowdLinker2

JevPromptCoach

Claude Code plugin that scores how well you prompt a coding agent, and shows whether your habits are improving. Runs on TypeSafe's Jev model. Zero added latency.

Agent toolingTypeScript
src/jev_mode/client.py
DEFAULT_ENDPOINT = "https://api.typesafe.ai/v1/systemone"
@ddfeyes2

jev-mode

I kept watching coding agents burn context on decisions that aren't hard - triage 400 tickets, tag 600 files, route to one of six teams. jev-mode moves those verdicts to a typed-judgment model. I A/B'd it: 78% fewer tokens, 16x less work-attributable input, accuracy 96.1% vs 93.7%. Python, no deps, MIT.

Agent toolingPython
plugins/tasks/typesafe/1.0.0/plugin.js
//   POST /v1/systemone  {model, state, questions}  ->  {model, answers, usage}
@FFatTiger2

new-api-plugin-typesafe

TypeSafe AI System One (Jev) task plugin for QuantumNous/new-api — native /v1/systemone, synchronous evaluation, token billing

Agent toolingJavaScript
jev_client.py
request = Request('https://api.typesafe.ai/v1/systemone',
@gholtzap2

jev-codex-model-and-effort-router

Copy and paste this into your coding agent:

Agent toolingPython
src/core/jevClient.ts
TypeSafeClient,
@ibrahemid2

git-jev-stage

Select Git changes for staging with a plain-language description.

Agent toolingTypeScript
src/client.ts
/** Defaults to `~typesafe/jev-latest`. */
@ingebyd2

fast-jev-compaction-openrouter

Fork of tamaratran/fast-jev-compaction: Jev via OpenRouter with zero data retention (zdr, data_collection: deny)

Agent toolingTypeScript
src/config.rs
pub const DEFAULT_API_URL: &str = "https://api.typesafe.ai";
@kindintelligence2

jev-rust-review

Rust-aware code review for Claude Code and coding agents, powered by TypeSafe Jev

Agent toolingRust
agent/primitives.py
from typesafe_sdk import Choice, Noul, Score, TypeSafeClient, TypeSafeAPIError
@lhemerly2

mcts-agent

Discriminative Monte Carlo Tree Search using TypeSafe Jev System One Primitives and Gemini

Agent toolingPython
src/skill_router/questions.py
from typesafe_sdk import Choice, Noul
@lomeshdutta2

skill-router

Tell Claude Code which installed skill a session needs, using Jev (TypeSafe AI) for the decision and skills.sh for discovery.

Agent toolingPython
server.py
TYPESAFE_URL = "https://api.typesafe.ai/v1/systemone"
@masa-med-ai2

typesafe-screening-mcp

MCP server: screen PubMed titles/abstracts against a query or clinical question with TypeSafe Jev

Agent toolingPython
src/jev-adapter.ts
const ORIGIN = "https://api.typesafe.ai";
@miniLV2

Jev-Auto-Router

Codex 可恢复委派:Capsule → Jev 选路 → Policy Guard(仅 ALLOW/DENY)→ Root 验收。自动委派默认关闭。Recoverable Codex delegation via Jev + Policy Guard; Root keeps acceptance.

Agent toolingTypeScript
src/jev.ts
export const JEV_ENDPOINT = 'https://api.typesafe.ai/v1/systemone';
@MongLong02142

jev-gate

Not every coding task needs your best model. Experimental Jev-powered model routing for Claude Code — V3 prototype runs today, V4 routes at the task boundary.

Agent toolingTypeScript
test_credentials.py
with patch('jevseek.models.OpenAI') as ds, patch('jevseek.models.TypeSafeClient') as jev:
@morcoan2

JevSeek

A local coding workspace pairing Jev action routing with DeepSeek argument generation. Native tools, persistent sessions, React desktop, and documented research.

Agent toolingPython
src/gate.ts
import { experimental_evaluate as evaluate } from 'ai';
@NicolasMontone2

jev-tool-permissions

Jev-backed tool approval gate and tool-list pruning for the Vercel AI SDK

Agent toolingTypeScript
packages/dsh-plugin/src/agent/jev-client.ts
export const JEV_MODEL = '~typesafe/jev-latest'
@rottenpen2

agent-stardew

星露谷农场小助手:Jev 自主游玩、dsh 插件、独立 CLI 与 SMAPI Mod

Agent toolingTypeScript
src/config.mjs
baseUrl: "https://api.typesafe.ai/v1",
@ShivamPansuriya2

jev-skill-gate

Cut Claude Code's skill manifest by ~75% with TypeSafe Jev. Scores every installed skill for relevance and hides the rest via skillOverrides — 12,750 → 3,185 tokens on a 217-skill install, for $0.0009 a session.

Agent toolingJavaScript
stop_verify.py
API = "https://api.typesafe.ai/v1/systemone"
@VladyslavHontar2

clear-head

Claude Code Stop hook that checks an AI assistant's claims against what it actually read this session, using TypeSafe's Jev as the judge

Agent toolingPython
bin/index.js
const API_ENDPOINT = process.env.TYPESAFE_ENDPOINT || "https://api.typesafe.ai/v1/systemone";
@y9Finsi2

jev-mcp

Universal Model Context Protocol (MCP) Server for TypeSafe Jev (System One) semantic code search and validation.

Agent toolingJavaScript
scripts/validate_repo.py
server = mcp.get("mcpServers", {}).get("jev", {})
@2023Anita1

codex-jev-assistant

Codex Plugin with typed Jev judgments for risk review, evidence checks, context screening, and reranking.

Agent toolingPython
src/config.ts
import { choice, score } from "@typesafe-ai/sdk";
@aaronshaf1

opencode-jev-orchestrator

Keeps OpenCode on a cheap sticky model for warm cache; Jev escalates hard turns to stronger subagents.

Agent toolingTypeScript
src/jev.rs
let response = match ureq::post("https://api.typesafe.ai/v1/systemone")
@AkashPriyadarshii1

jev-scout

Zero-hallucination open-source repo and crate scout powered by TypeSafe AI Jev System One scoring

Agent toolingRust
packages/cli/src/core/jev/types.ts
export const DEFAULT_BASE_URL = "https://api.typesafe.ai/v1/systemone";
@bestagentkits1

jev-skillful

Per-prompt capability router for coding agents: resolves installed skills, MCP servers, agents and commands against your prompt via TypeSafe Jev, and measures whether the injection actually helps.

Agent toolingTypeScript
skills/judging-with-typesafe/scripts/typesafe.py
API = "https://api.typesafe.ai/v1/systemone"
@carlsonchik1

judging-with-typesafe

Скилл для агентов Letta: суждения по критериям через TypeSafe System One (Jev)

Agent toolingPython
hooks/providers.ts
join(or(env.TYPESAFE_BASE_URL, 'https://api.typesafe.ai'), '/v1/systemone'),
@chrishan171

claude-jev-mod

Typed decisions in Claude Code: adds $.jev over TypeSafe's Jev, through OpenRouter, Vercel AI Gateway, Cloudflare Workers AI, LiteLLM or the TypeSafe API.

Agent toolingTypeScript
scripts/jev_compact.py
DEFAULT_MODEL = os.environ.get("JEV_MODEL", "typesafe/jev-1.13")
@de-niji1

jev-hermes

Jev for Hermes: cheap intent gates + verbatim tool compaction on OpenRouter

Agent toolingPython
src/gateway.ts
* SDK's `experimental_evaluate`, not the chat-completions endpoints.
@Dharundp61

jev-carryforward

What your last session knew, scored against what this one is doing. MCP server: a per-project ledger written as things happen, recalled per task with TypeSafe's Jev evaluation model via Vercel AI Gateway.

Agent toolingTypeScript
jev/client.py
"""Native HTTP client for Experiential /v1/systemone.
@dhava-gautama1

noulgate

A gate for your agent's expensive steps, powered by TypeSafe Jev (System One). Offline-first, OpenRouter or direct, MIT.

Agent toolingPython
src/jev.ts
typesafe: { key: "TYPESAFE_API_KEY", model: "jev-latest", endpoint: "https://api.typesafe.ai/v1/systemone" },
@felpsdev1

jev-classifier

Local tool-routing classifier for coding agents, with a gateway, MCP integrations, and decision logs.

Agent toolingTypeScript
index.ts
const defaultModel = "typesafe/jev-1.13";
@gregb1001

gavel

Stop burning LLM calls on classification. Route bugs, triage failures, and gate PRs in 200ms for $0.00002. OpenClaw plugin for TypeSafe Jev structured decisions.

Agent toolingPython
skills/decision-first/scripts/ask.py
ENDPOINT = os.environ.get("TYPESAFE_API_BASE", "https://api.typesafe.ai") + "/v1/systemone"
@harrymunro1

decision-first

Agent skill that spots bounded-judgment steps, tries a typed decision model (TypeSafe's Jev) first, and documents every attempt

Agent toolingPython
test/config.test.ts
const typesafe = configFromEnv({ TYPESAFE_API_KEY: 'ts', JEVC_MODEL: 'jev-1.13', JEVC_BASE_URL: 'https://proxy.example/v1/systemone' });
@iefnaf1

pi-jev

Pi extension suite powered by Jev: selective context compaction and model routing

Agent toolingTypeScript
airlock/client.py
"""Thin HTTP client for the TypeSafe /v1/systemone endpoint.
@jonathanavis961

jev-kit

Everything you need to run TypeSafe's Jev with Claude Code: a tool-call guard, tier guard, file search, browser agent, review, belay, compaction and installers.

Agent toolingPython
custom_components/jev_assist/const.py
TYPESAFE_BASE_URL: Final = "https://api.typesafe.ai"
@luxus1

ha-conversation-jev

Home Assistant custom component: Conversation agent with Jev fast-path + Grok fallback

Agent toolingPython
index.ts
const API_URL = 'https://api.typesafe.ai/v1/systemone';
@mja001

cmdc-auto-mode

Auto permission mode for Command Code: screens every tool call with TypeSafe Jev before it runs, and rejects anything out of scope.

Agent toolingTypeScript
runtime/review_patch.py
API_URL = "https://api.typesafe.ai/v1/systemone"
@mozbz1

jev-review-hook

Jev powered code review hook for agents

Agent toolingPython
internal/jev/client.go
const Endpoint = "https://api.typesafe.ai/v1/systemone"
@muse05091

jev-preflight

A bounded Jev risk check for Claude Code: eight risk axes, one request, one optional reinspection.

Agent toolingGo
extensions/router.ts
const response = await (options.fetch ?? fetch)("https://api.typesafe.ai/v1/systemone", {
@mwijanarko11

pi-jev-agent

pi-jev-agent is an experimental extension for the Pi coding agent. It uses TypeSafe Jev to choose the next tool before each language-model step.

Agent toolingTypeScript
src/jev.mjs
// "~typesafe/jev-latest" always points to the newest Jev. The tilde matters:
@nexibeo1

jev-organize

Throw in a pile of company files and get them classified and organized by department, type, sensitivity, date, counterparty and PII, with an index for AI agents. Powered by TypeSafe's Jev on OpenRouter (17¢ per 1,000 files). Zero-dependency Node CLI + Claude skill + Codex agent.

Agent toolingJavaScript
limpet.py
"typesafe": ("https://api.typesafe.ai/v1/systemone", "jev-latest", "noul", "noul"),
@noplan-inc1

limpet

A Stop hook that stops your coding agent from stopping too early. Plain-language rules, judged by jev.

Agent toolingPython
core.py
TS_URL = os.environ.get("TS_MCP_TS_URL", "https://api.typesafe.ai/v1/systemone")
@Obrais-cloud1

typesafe-mcp

MCP server exposing TypeSafe (Jev/System One) to the fleet: judge, rerank, systemone

Agent toolingPython
tests/mock_server.py
#   - TypeSafe native-shaped: POST /v1/systemone, GET /v1/models
@okooo5km1

jev

Typed decisions from the shell: an unofficial stdlib-Python CLI and Agent Skill for TypeSafe's Jev model, via the TypeSafe API (default) or OpenRouter. Yes/no, choice and ordinal scores with calibrated probabilities, semantic grep and batch mode.

Agent toolingPython
src/evaluator/jev.ts
const fn = (mod['experimental_evaluate'] ?? mod['evaluate']) as EvaluateFn | undefined;
@paulobueno1641

jev-mcts

Busca em arvore (MCTS/PUCT) com avaliacao tipada do TypeSafe Jev e portao humano obrigatorio. A arvore supoe, a sonda mede: marco so e concedido por codigo de saida verde.

Agent toolingTypeScript
scripts/jev_judge.py
DEFAULT_URL = "https://api.typesafe.ai/v1/systemone"
@poponline631

hermes-jev-north-star

Hermes Agent skill whose north-star gate is judged by Jev (TypeSafe System One): turn an intention into a checkable finish line, generate the run prompt, and let Jev rank what is still unproven.

Agent toolingPython
src/jev.ts
export function createDecider(endpoint = "https://api.typesafe.ai/v1/systemone"): Decide {
@purplesmoke051

opencode-plugin-jev-auto-model-router

Opt-in Auto (Jev) model routing for OpenCode with a configurable model allowlist

Agent toolingTypeScript
jiffy/model.py
TYPESAFE_URL = "https://api.typesafe.ai/v1/systemone"
@rahulpalivela181

jiffy

general Chrome agent — Jev + OpenRouter

Agent toolingPython
src/index.ts
model: "~typesafe/jev-latest",
@Ravinder821

jev-flash-router

open-sourced jev-flash-router: an MCP server for TypeSafe's new Jev model. AI coding agents waste hundreds of reasoning tokens just deciding which file to edit, which route to pick, or whether a diff breaks tests. Jev evaluates state and outputs calibrated probabilities. Works with Cursor, Windsurf, & Claude Code

Agent toolingTypeScript
src/jev.ts
const DEFAULT_API_BASE = "https://api.typesafe.ai/v1";
@redrossa1

pi-model-router

Pi extension that classifies each prompt with TypeSafe's Jev and routes it to the best model you're logged into.

Agent toolingTypeScript
plugins/jev-router/config.py
model: str = "typesafe:jev-1.13.0"
@rsdkrasen1

hermes-jev-router

TypeSafe/Jev router plugin for Hermes Agent — compact tool results, suppress duplicate tools, skip unnecessary main-model calls

Agent toolingPython
src/pipeline/judge-jev.ts
import { type NoulQuestion, noul, TypeSafeClient } from "@typesafe-ai/sdk";
@savka7771

jev-search

Fast deep research for the pi coding agent: reads up to 100 pages in full per round, Jev keeps only the passages that answer your questions.

Agent toolingTypeScript
src/analysis/jev-client.ts
import { TypeSafeClient, type TypeSafeClientConfig } from '@typesafe-ai/sdk';
@shubhangi0131

prompt-oscilloscope

Analyze prompts with TypeSafe Jev before GitHub Copilot

Agent toolingTypeScript
src/client.ts
TypeSafeClient,
@siddicky1

omp-typesafe

TypeSafe AI (Jev) adversarial reviewer and typesafe_ask tool for the omp coding agent

Agent toolingTypeScript
src/provider.ts
TypeSafeClient,
@stoopid-computers1

jev-bot

Computer Use Agent developed with Jev

Agent toolingTypeScript
src/jev.ts
const response = await (this.options.fetch ?? fetch)('https://api.typesafe.ai/v1/systemone', {
@teempai1

jev-in-codex

Jev-powered tool and skill selection, context search, and output triage for Codex via MCP

Agent toolingTypeScript
decision.ts
response = await request('https://api.typesafe.ai/v1/systemone', { method: 'POST',
@thesammykins1

jev_ampcode

A small advisory tool for comparing supplied alternatives against supplied evidence.

Agent toolingTypeScript
typesafe_agent_gates/judgments.py
from langchain_typesafe import Choice, Noul, NoulCriteria
@ThiagaoBR1

typesafe_agent_gates

LangChain / Deep Agents middleware that uses TypeSafe's System One model (Jev) for typed judgments in unattended coding agents: a shell-command gate (database, production, destructive, secrets), issue triage and routing by severity and urgency, merge-request detection, and review of weakened tests. Measured with live probes.

Agent toolingPython
structured_aux/config.py
DEFAULT_MODEL = "~typesafe/jev-latest"
@trajectoire-ai1

hermes-structured-aux-models

A Hermes Agent model-provider plugin that routes selected auxiliary tasks through bounded Jev decision calls on OpenRouter instead of free-form chat prompts.

Agent toolingPython
src/providers/typesafe.mjs
constructor({ apiKey = process.env.TYPESAFE_API_KEY, endpoint = process.env.TYPESAFE_ENDPOINT ?? "https://api.typesafe.ai/v1/systemone", model = process.env.TYP
@typakon41

jev-layer

Portable System-1 decision layer for agent harnesses with host-owned routing, receipts, replay, and fail-open integrations.

Agent toolingJavaScript
plugin.json
"jev",
@Umbylicus1

umby-jev-stack

Portable agent skill: TypeSafe Jev as a cheap code-review classifier (HTTP + optional jev-review MCP)

Agent tooling
jcyber/clients/jev.py
questions to typesafe_sdk types and projects the response back to jcyber's
@undeemed1

Jcyber

Agent-driven bug bounty / pentest framework: one gated chain over five systems (Caido, HexStrike, Jev, Memgraph, TencentDB, Prometheus)

Agent toolingPython
jev_mcp.py
name="jev",
@vit-cerny1

jev-browser-kit

Give any MCP-capable LLM harness an on-demand real-browser search tool (TypeSafe Jev) with per-run timing and cost tracking.

Agent toolingPython
src/jev_mcp/decisions.py
"model": os.environ.get("JEV_DECISIONS_MODEL", "~typesafe/jev-latest"),
@wahahaorg1

jev-mcp

jev-mcp turns browser-use/jev-ultrafast into one local, session-aware MCP server for fast read-only product research. Jev selects an action and observed target from a DOM snapshot;

Agent toolingPython
plugins/codex-jev-compaction/lib/core.mjs
export const ENDPOINT = 'https://api.typesafe.ai/v1/systemone';
@Wang-auspicious1

codex-jev-compaction

Jev-powered context curation for Codex. Build compact, traceable handoff context through native plugins and skills.

Agent toolingJavaScript
hooks/typesafe-check.sh
"3. Would a sensible person answer it in under a second from text you can show them? -> TypeSafe/Jev.\n" +
@wotai-dev1

typesafe-jev-tools

A Claude Code hook that asks whether the decision you are writing needs a model at all. Includes a measured 149-row comparison of TypeSafe Jev against Claude Haiku 4.5.

Agent toolingShell