questions: { refund: boolean, spam: boolean, }
simple-jev
Turn any open model into a classifier/jev endpoint
ALL 788 PROJECTSEvery project
All788Agent tooling154SDKs & clients131Applications106Benchmarks & research83Lists & resources56Games & simulation49Guardrails & review47Browser & computer use42Open reproductions35Infrastructure31Search & retrieval25Context engineering25Official4▶ Runnable only182
questions: { refund: boolean, }
typesafe-ai-benchmark
This is a LLM Gateway that mimics typesafe ai structured output. Like an imposter Jev.
questions: { route: choice, urgent: boolean, severity: score, }
Nemotron_Jev
Nemotron Diffusion Decision Lab
questions: { model: choice, effort: choice, is_followup: boolean, }
jcm-router
Local proxy that picks the Claude model and effort per message using TypeSafe Jev. Routes subagents, leaves your cached main chat alone.
questions: { difficulty: score, needs_reasoning: boolean, stakes: score, // +5 }
tiershift
Shift every LLM call to the cheapest model that can handle it. Routing decided by TypeSafe Jev in ~180 ms. No training data. Policy in plain YAML. TypeScript and Python.
questions: { is_billing: boolean, }
jev-workbench
Build versioned judgment functions on TypeSafe's Jev once, then call the same published version from your backend over HTTP and from coding agents over MCP. The vendor key stays on your machine.
questions: { hallucination_sensitive: boolean, }
ailerix
Type-safe model router. Jev (System One) banks each request to a typed catalog route.
questions: { tier: choice, is_greeting: boolean, }
jev-model-router
Jev (TypeSafe) model router on the Vercel AI Gateway
questions: { same_intent: boolean, }
jevcache
Skip expensive LLM calls when TypeSafe Jev says same intent. OpenAI-compatible local cache proxy — npx @kushalicious/jevcache
questions: { eligible: boolean, }
NEXUS-AI-Gateway-with-JEV
AI gateway that validates before it executes: Lead plans, JEV validates, Worker generates. Local-first control plane, 359-provider catalog.
-- jev.api_url default 'https://api.typesafe.ai/v1/systemone' (proxies, mocks, tests)
pg-jev
Ask your Postgres tables questions in plain language. A PostgreSQL extension powered by TypeSafe's Jev.
"/v1/systemone",
openjev-sglang
Jev-compatible API endpoint based on open models (prefill-only)
"https://api.typesafe.ai/v1/systemone"
pg_typesafe
Pre-alpha PostgreSQL extension for TypeSafe AI (Jev) categorical classification
// mock-jev: a local stand-in for TypeSafe's `POST /v1/systemone`, for driving the router
jev-gateway
A local LLM gateway for coding agents. When your agent is about to decide which tool to call,
const res = await fetch(`${options.baseURL ?? 'https://api.typesafe.ai'}/v1/systemone`, {hono-jev-router
Route HTTP requests by meaning. A semantic router for Hono powered by Jev.
* - api.typesafe.ai (commercial Jev, "System One")
a3m-router
⚡ Adaptive multi-model LLM router — 80+ providers, Jev System One single-pass routing (model=jev-auto), pheromone-trail failover, parallel ensemble merge. npm: adaptive-memory-multi-model-router
static constexpr const char *SYSTEMONE_PATH = "/v1/systemone";
duckdb-jev
DuckDB extension: typed Jev answers as real SQL types
import { createGateway, experimental_evaluate as evaluate } from "ai";pi-jev-router
Automatic model routing for Pi using TypeSafe's Jev through Vercel AI Gateway
export const DECISIONS_URL = 'https://api.typesafe.ai/v1/systemone'
jev-telop-live
Talk to your camera, and Japanese variety-show captions and manga effects appear on their own, matched to what you are saying.
import { TypeSafeClient } from "@typesafe-ai/sdk";safer-with-jev
Neon Function proxy for the Neon AI Gateway with TypeSafe Jev routing.
import { score, TypeSafeClient } from "@typesafe-ai/sdk";jev-router
Cost-aware LLM router that picks the cheapest model capable of handling a query, using TypeSafe's Jev for fast classification instead of an LLM call.
TYPESAFE_URL = "https://api.typesafe.ai/v1/systemone"
jev-router
Open-source LLM router that uses TypeSafe's Jev to pick a model, on top of LiteLLM
"model": "typesafe/jev-1.13",
slo-router
SLO-aware LLM inference router with Jev decisions, live queue metrics, counterfactual evaluation, and reproducible latency/cost benchmarks
jev_model: str = "jev-latest"
jev-model-router
Route among multiple LLMs and multi-model provider keys without leaking secrets.
DEFAULT_BASE_URL = "https://api.typesafe.ai"
vgi-typesafe
A VGI worker exposing TypeSafe System One questions (choice, noul, score) to DuckDB/SQL as LATERAL-joinable table functions
* Falls back to `POST {baseURL}/v1/systemone` with the same wire questionsjevrouter
Drop-in decision/routing layer powered by TypeSafe Jev (System One) — typed Choice/Noul/Score routes with production safety gates.
const { TypeSafeClient, choice, noul, score } = await import("@typesafe-ai/sdk");switchboard-ai
Adaptive multi-model AI orchestration runtime using Jev for cost-aware routing, confidence-based escalation, tool selection, and model execution
"url": f"http://{args.host}:{args.port}/v1/systemone",jevify
Supersimple way to serve LLMs as a Jev-like endpoint
JEV_ENDPOINT = "https://api.typesafe.ai/v1/systemone"
jev-model-router
Cost-optimized OpenRouter model router using TypeSafe's Jev, with a live full-catalog scorer instead of a hardcoded model list
delivery = { via: "jev" };Cynosure
Jev-based adaptive model routing with structured decisions, persistent feedback, and hybrid retrieval
"""FastAPI app: POST /v1/systemone, Jev-compatible contract."""
jev-local
Local Jev-compatible evaluation server: POST /v1/systemone with typed noul/choice/score, open weights, no waitlist