THE COMMUNITY RESOURCE
DIRECTORY
Small decisions.
Small decisions.
Endless possibilities.
Find what people build with Jev. Explore tools, libraries, experiments and ideas from across the TypeSafe ecosystem.
11,066unique resources
29clear categories
220focused subcategories
Yourssave a personal reading list
YOUR NEXT BUILD STARTS HERE
Download catalog
Explore the collection
Browse groups
Model access & gateways159 of 159 matches
API gateways & proxies114 of 114 matches
| Resource | Stars | Description | Category | Save |
|---|---|---|---|---|
| 0G Serving Broker decisionsgithub.com | — | Provider broker for the 0G Compute Network with a decisions handler that proxies OpenRouter Decisions-style requests such as typesafe/jev-1.13 and bills them from the usage block. | Model access & gatewaysAPI gateways & proxies | |
| 0G Serving Broker decisions — repogithub.com | — | Provider broker for the 0G Compute Network with a decisions handler that proxies OpenRouter Decisions-style requests such as typesafe/jev-1.13 and bills them from the usage block. | Model access & gatewaysAPI gateways & proxies | |
| A3M Routergithub.com | 16 | Adaptive multi-model LLM router across 80+ providers with pheromone-trail failover and ensemble merging, where model=jev-auto lets Jev route each request to a suitable provider in a single pass. | Model access & gatewaysAPI gateways & proxies | |
| Agent Router TypeSafe schemagithub.com | — | Agent Router, the Envoy-based AI gateway formerly Envoy AI Gateway, adds TypeSafe System One request and response schema so Jev's /v1/systemone can be routed through it. | Model access & gatewaysAPI gateways & proxies | |
| Agent Router TypeSafe schema — apptheagentrouter.ai | — | Agent Router, the Envoy-based AI gateway formerly Envoy AI Gateway, adds TypeSafe System One request and response schema so Jev's /v1/systemone can be routed through it. | Model access & gatewaysAPI gateways & proxies | |
| ai_sdkgithub.com | 1 | az9713/jev-model-router — Jev (TypeSafe) model router on the Vercel AI Gateway · ai_sdk · JavaScript | Model access & gatewaysAPI gateways & proxies | |
| ai_sdkgithub.com | 16 | mejiasd3v/pi-jev-router — Automatic model routing for Pi using TypeSafe's Jev through Vercel AI Gateway · ai_sdk · JavaScript | Model access & gatewaysAPI gateways & proxies | |
| aio-proxy System One routegithub.com | — | Self-hosted multi-provider API proxy that exposes a TypeSafe System One route (POST /v1/systemone) alongside its OpenAI-style endpoints. | Model access & gatewaysAPI gateways & proxies | |
| aio-proxy System One route — appaioproxy.dev | — | Self-hosted multi-provider API proxy that exposes a TypeSafe System One route (POST /v1/systemone) alongside its OpenAI-style endpoints. | Model access & gatewaysAPI gateways & proxies | |
| aio-proxy System One route — repogithub.com | — | Self-hosted multi-provider API proxy that exposes a TypeSafe System One route (POST /v1/systemone) alongside its OpenAI-style endpoints. | Model access & gatewaysAPI gateways & proxies | |
| Bifrost TypeSafe providergithub.com | — | TypeSafe provider in the Bifrost AI gateway that exposes a drop-in /typesafe prefix, so clients written for api.typesafe.ai, including the official SDK, work through Bifrost unchanged. | Model access & gatewaysAPI gateways & proxies | |
| Bifrost TypeSafe provider — appwww.getmaxim.ai | — | TypeSafe provider in the Bifrost AI gateway that exposes a drop-in /typesafe prefix, so clients written for api.typesafe.ai, including the official SDK, work through Bifrost unchanged. | Model access & gatewaysAPI gateways & proxies | |
| Braintrust AI Proxy TypeSafe providergithub.com | — | Adds TypeSafe as a provider in the Braintrust AI proxy, with a script that syncs Jev model IDs, aliases and per-token pricing from the TypeSafe models API and docs. | Model access & gatewaysAPI gateways & proxies | |
| Braintrust AI Proxy TypeSafe provider — docswww.braintrustdata.com | — | Adds TypeSafe as a provider in the Braintrust AI proxy, with a script that syncs Jev model IDs, aliases and per-token pricing from the TypeSafe models API and docs. | Model access & gatewaysAPI gateways & proxies | |
| ChatBotKit platform decisionsgithub.com | — | Decision API in the open-source ChatBotKit AI backend (/api/v1/decision/create) that serves typed questions through TypeSafe, OpenRouter or Vercel AI Gateway providers with bounded timeouts and retries. | Model access & gatewaysAPI gateways & proxies | |
| ChatBotKit platform decisions — appcbk.ai | — | Decision API in the open-source ChatBotKit AI backend (/api/v1/decision/create) that serves typed questions through TypeSafe, OpenRouter or Vercel AI Gateway providers with bounded timeouts and retries. | Model access & gatewaysAPI gateways & proxies | |
| ChatBotKit platform decisions — repogithub.com | — | Decision API in the open-source ChatBotKit AI backend (/api/v1/decision/create) that serves typed questions through TypeSafe, OpenRouter or Vercel AI Gateway providers with bounded timeouts and retries. | Model access & gatewaysAPI gateways & proxies | |
| Convex AI Gateway Jev supportgithub.com | — | Convex's AI Gateway serves Jev as typesafe/jev-1.13 through a decisions endpoint, callable from Convex actions via AI SDK's evaluate and the @convex-dev/ai-sdk-provider package. | Model access & gatewaysAPI gateways & proxies | |
| Convex AI Gateway Jev support — repogithub.com | — | Convex's AI Gateway serves Jev as typesafe/jev-1.13 through a decisions endpoint, callable from Convex actions via AI SDK's evaluate and the @convex-dev/ai-sdk-provider package. | Model access & gatewaysAPI gateways & proxies | |
| croit AIplanegithub.com | 23 | Self-hosted AI gateway with a TypeSafe System One-compatible /v1/systemone endpoint, so the official SDK can use it as base URL, plus System One-based automatic model routing and a GDPR/NDA content guard. | Model access & gatewaysAPI gateways & proxies | |
| endpointgithub.com | 16 | Das-rebel/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 · endpoint · TypeScript | Model access & gatewaysAPI gateways & proxies | |
| endpointgithub.com | 1 | Mistertelecom/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. · endpoint · TypeScript | Model access & gatewaysAPI gateways & proxies | |
| endpointgithub.com | 8 | adarshmishra07/jcm-router — Local proxy that picks the Claude model and effort per message using TypeSafe Jev. Routes subagents, leaves your cached main chat alone. · endpoint · TypeScript | Model access & gatewaysAPI gateways & proxies | |
| endpointgithub.com | 1 | alpbahadur/jevrouter — Drop-in decision/routing layer powered by TypeSafe Jev (System One) — typed Choice/Noul/Score routes with production safety gates. · endpoint · TypeScript | Model access & gatewaysAPI gateways & proxies | |
| endpointgithub.com | 39 | iammrduncan/typesafe-ai-benchmark — This is a LLM Gateway that mimics typesafe ai structured output. Like an imposter Jev. · endpoint · TypeScript | Model access & gatewaysAPI gateways & proxies | |
| endpointgithub.com | 2 | lucianfialho/jev-model-router — Cost-optimized OpenRouter model router using TypeSafe's Jev, with a live full-catalog scorer instead of a hardcoded model list · endpoint · Python | Model access & gatewaysAPI gateways & proxies | |
| endpointgithub.com | 14 | prismhq/jev-router — Open-source LLM router that uses TypeSafe's Jev to pick a model, on top of LiteLLM · endpoint · Python | Model access & gatewaysAPI gateways & proxies | |
| endpointgithub.com | 2 | tylerjharden/ailerix — Type-safe model router. Jev (System One) banks each request to a typed catalog route. · endpoint · TypeScript | Model access & gatewaysAPI gateways & proxies | |
| endpointgithub.com | 273 | vinilana/jev-gateway — A local LLM gateway for coding agents. When your agent is about to decide which tool to call, · endpoint · TypeScript | Model access & gatewaysAPI gateways & proxies | |
| endpointgithub.com | 51 | yusukebe/hono-jev-router — Route HTTP requests by meaning. A semantic router for Hono powered by Jev. · endpoint · TypeScript | Model access & gatewaysAPI gateways & proxies | |
| Experiential TypeSafe providergithub.com | — | TypeSafe provider in the Experiential open-source model gateway that dispatches Jev decisions natively and refuses to treat Jev as a chat model. | Model access & gatewaysAPI gateways & proxies | |
| Experiential TypeSafe provider — appexperientiallabs.ai | — | TypeSafe provider in the Experiential open-source model gateway that dispatches Jev decisions natively and refuses to treat Jev as a chat model. | Model access & gatewaysAPI gateways & proxies | |
| GPT-Load Jev channelgithub.com | — | Jev channel module for the self-hosted GPT-Load AI gateway, adding TypeSafe's official API as a provider with batch key import, scheduling and failover. | Model access & gatewaysAPI gateways & proxies | |
| GPT-Load Jev channel — appwww.gpt-load.com | — | Jev channel module for the self-hosted GPT-Load AI gateway, adding TypeSafe's official API as a provider with batch key import, scheduling and failover. | Model access & gatewaysAPI gateways & proxies | |
| Hack Club AI Jev endpointgithub.com | — | Jev forwarding route in Hack Club's free AI proxy for teens, reusing its Hack Club auth, API keys, spending limits and usage logging. | Model access & gatewaysAPI gateways & proxies | |
| Hack Club AI Jev endpoint — appai.hackclub.com | — | Jev forwarding route in Hack Club's free AI proxy for teens, reusing its Hack Club auth, API keys, spending limits and usage logging. | Model access & gatewaysAPI gateways & proxies | |
| https://x.com/ritakozlov/status/2100688919364845709 — Cloudflare’s Rita Kozlov confirms Jev is live x.com | — | on Cloudflare AI Gateway; 22 · 39 · 1K · 56K views. | Model access & gatewaysAPI gateways & proxies | |
| Jev on Fly.io Spritesx.com | — | Fly.io's TypeSafe connector for Sprites, which injects your Jev API key at a gateway so agents running inside hardware-isolated Sprites can call Jev without the key entering the sandbox. | Model access & gatewaysAPI gateways & proxies | |
| Jev on Fly.io Sprites — docsfly.io | — | Fly.io's TypeSafe connector for Sprites, which injects your Jev API key at a gateway so agents running inside hardware-isolated Sprites can call Jev without the key entering the sandbox. | Model access & gatewaysAPI gateways & proxies | |
| Jev on OpenRouterx.com | — | OpenRouter's announcement that Jev is available in beta through its API, returning a typed decision with a probability instead of generated text. | Model access & gatewaysAPI gateways & proxies | |
| Jev on Requestywww.requesty.ai | — | Practical guide to Jev that shows how to call it through Requesty's OpenAI-compatible router as typesafe/jev-latest, using the questions response format, with pricing math and caveats. | Model access & gatewaysAPI gateways & proxies | |
| Jev on Vercel AI Gateway — gatewayvercel.com | — | Vercel AI Gateway model page for typesafe-ai/jev with pricing and a playground; the gateway also supports TypeSafe clients and an HTTP API for Jev. | Model access & gatewaysAPI gateways & proxies | |
| jev-gatewaygithub.com | 273 | Local LLM gateway for Codex, Claude Code, OpenCode, and Gemini clients that hands the which-tool-to-call decision to Jev and forwards all other traffic to your usual model. | Model access & gatewaysAPI gateways & proxies | |
| jev-model-routergithub.com | 1 | Web chat where Jev picks which LLM should answer each message and the chosen model replies, both through the Vercel AI Gateway, with a documented development journey and reliability evaluation. | Model access & gatewaysAPI gateways & proxies | |
| jev-model-router (OpenRouter)github.com | 2 | Python router that classifies each request and picks the cheapest capable model from OpenRouter's live, full catalog on every decision instead of a hardcoded model list. | Model access & gatewaysAPI gateways & proxies | |
| jevcache (semantic cache)github.com | 9 | Local OpenAI-compatible proxy that reuses a cached chat completion when Jev judges a new request to have the same intent as an earlier one, and fails open on Jev errors; one test went from 3244ms to 394ms. | Model access & gatewaysAPI gateways & proxies | |
| jevroutergithub.com | 1 | Drop-in decision/routing layer powered by TypeSafe Jev (System One) — typed Choice/Noul/Score routes with production safety gates. | Model access & gatewaysAPI gateways & proxies | |
| LLM Gateway System One endpointgithub.com | — | Self-hosted distributed LLM gateway with a web UI that adds a decisions proxy handler so System One requests to Jev pass through its routing, keys and usage logging. | Model access & gatewaysAPI gateways & proxies | |
| LLM Gateway TypeSafe modelgithub.com | — | LLM Gateway registers Jev 1.13 as a TypeSafe decision model, routing state-plus-questions requests to the /v1/systemone endpoint through its unified gateway. | Model access & gatewaysAPI gateways & proxies | |
| LLM Gateway TypeSafe model — appllmgateway.io | — | LLM Gateway registers Jev 1.13 as a TypeSafe decision model, routing state-plus-questions requests to the /v1/systemone endpoint through its unified gateway. | Model access & gatewaysAPI gateways & proxies | |
| Mistertelecom/NEXUS-AI-Gateway-with-JEVgithub.com | 1 | AI gateway that validates before it executes: Lead plans, JEV validates, Worker generates. Local-first control plane, 359-provider catalog. | Model access & gatewaysAPI gateways & proxies | |
| MobAI-Inc/Cynosuregithub.com | 1 | Jev-based adaptive model routing with structured decisions, persistent feedback, and hybrid retrieval | Model access & gatewaysAPI gateways & proxies | |
| model_idgithub.com | 2 | Pinutss/jev-model-router — Route among multiple LLMs and multi-model provider keys without leaking secrets. · model_id · Python | Model access & gatewaysAPI gateways & proxies | |
| model_idgithub.com | 9 | kushals256/jevcache — Skip expensive LLM calls when TypeSafe Jev says same intent. OpenAI-compatible local cache proxy — npx @kushalicious/jevcache · model_id · TypeScript | Model access & gatewaysAPI gateways & proxies | |
| model_idgithub.com | 8 | zeeshan8281/slo-router — SLO-aware LLM inference router with Jev decisions, live queue metrics, counterfactual evaluation, and reproducible latency/cost benchmarks · model_id · Python | Model access & gatewaysAPI gateways & proxies | |
| Netlify AI Gateway skillgithub.com | — | Netlify's official agent skill for its AI Gateway, which lists TypeSafe Jev as a provider with injected credentials and shows a Netlify Function routing contact-form submissions to sales, support or spam with one Choice. | Model access & gatewaysAPI gateways & proxies | |
| Netlify AI Gateway skill — repogithub.com | — | Netlify's official agent skill for its AI Gateway, which lists TypeSafe Jev as a provider with injected credentials and shows a Netlify Function routing contact-form submissions to sales, support or spam with one Choice. | Model access & gatewaysAPI gateways & proxies | |
| New API Jev pluginx.com | — | Plugin that exposes Jev's Choice, Score and Noul through a self-hosted New API gateway, so the official TypeSafe SDK can point at the gateway without code changes. | Model access & gatewaysAPI gateways & proxies | |
| New API Jev plugin — pluginsnewapi.pro | — | Plugin that exposes Jev's Choice, Score and Noul through a self-hosted New API gateway, so the official TypeSafe SDK can point at the gateway without code changes. | Model access & gatewaysAPI gateways & proxies | |
| new-api TypeSafe plugingithub.com | — | Official task plugin for the new-api gateway that serves Jev at POST /typesafe/v1/systemone (jev-1.13.0, jev-latest, jev-preview), billing actual input tokens with free output, directly or through another new-api gateway. | Model access & gatewaysAPI gateways & proxies | |
| new-api TypeSafe plugin — repogithub.com | — | Official task plugin for the new-api gateway that serves Jev at POST /typesafe/v1/systemone (jev-1.13.0, jev-latest, jev-preview), billing actual input tokens with free output, directly or through another new-api gateway. | Model access & gatewaysAPI gateways & proxies | |
| new-api-plugin-typesafegithub.com | 3 | Task plugin for the self-hosted QuantumNous new-api gateway that serves Jev over the native /v1/systemone protocol with token billing, using TypeSafe or Vercel AI Gateway as the upstream. | Model access & gatewaysAPI gateways & proxies | |
| new-api-sync TypeSafe providergithub.com | 21 | Sync engine for new-api gateways (used by UnoRouter) with a typesafe provider type that syncs Jev from OpenRouter's decisions route into the gateway with its own sell price and 32,000-token context. | Model access & gatewaysAPI gateways & proxies | |
| new-api-sync TypeSafe provider — appunorouter.com | — | Sync engine for new-api gateways (used by UnoRouter) with a typesafe provider type that syncs Jev from OpenRouter's decisions route into the gateway with its own sell price and 32,000-token context. | Model access & gatewaysAPI gateways & proxies | |
| OctoHubgithub.com | 7 | Rust LLM proxy with one OpenAI-style API over 20+ providers, multi-tenant keys and request logging, whose config can map an evaluation model "jev" to TypeSafe or Cloudflare. | Model access & gatewaysAPI gateways & proxies | |
| OctoHub — appoctomind.run | — | Rust LLM proxy with one OpenAI-style API over 20+ providers, multi-tenant keys and request logging, whose config can map an evaluation model "jev" to TypeSafe or Cloudflare. | Model access & gatewaysAPI gateways & proxies | |
| OpenCode Zen Jev endpointgithub.com | — | OpenCode's Zen gateway serves Jev 1.13 at a /v1/systemone endpoint with the Zen API key, plus a limited-time free jev-1.13-free model. | Model access & gatewaysAPI gateways & proxies | |
| OpenCode Zen Jev endpoint — docsopencode.ai | — | OpenCode's Zen gateway serves Jev 1.13 at a /v1/systemone endpoint with the Zen API key, plus a limited-time free jev-1.13-free model. | Model access & gatewaysAPI gateways & proxies | |
| opencode2api System One proxygithub.com | — | Local proxy that exposes OpenCode Zen and Go models as OpenAI and Anthropic APIs, adding a System One route for Jev decision requests. | Model access & gatewaysAPI gateways & proxies | |
| openproxy decision enginegithub.com | — | Self-hosted LLM gateway whose decision engine routes prompts with System One models, either Jev as an HTTP upstream or local Laya ONNX in process, and exposes its own /v1/systemone endpoint. | Model access & gatewaysAPI gateways & proxies | |
| openproxy decision engine — repogithub.com | — | Self-hosted LLM gateway whose decision engine routes prompts with System One models, either Jev as an HTTP upstream or local Laya ONNX in process, and exposes its own /v1/systemone endpoint. | Model access & gatewaysAPI gateways & proxies | |
| OpenRouter Go SDK System Onegithub.com | — | Official OpenRouter Go SDK support for sending state and typed questions to System One models like Jev through OpenRouter. | Model access & gatewaysAPI gateways & proxies | |
| OpenRouter Python SDK System Onegithub.com | — | Official OpenRouter Python SDK module for sending state and typed questions to System One models like Jev through OpenRouter. | Model access & gatewaysAPI gateways & proxies | |
| OpenRouter TypeSafe SDK guidegithub.com | — | Documentation page from OpenRouter on pointing the official TypeSafe JavaScript or Python SDK at OpenRouter's base URL to run Jev through the System One API with OpenRouter billing. | Model access & gatewaysAPI gateways & proxies | |
| OpenRouter TypeSafe SDK guide — repogithub.com | — | Documentation page from OpenRouter on pointing the official TypeSafe JavaScript or Python SDK at OpenRouter's base URL to run Jev through the System One API with OpenRouter billing. | Model access & gatewaysAPI gateways & proxies | |
| OpenRouter TypeScript SDK System Onegithub.com | — | Official OpenRouter TypeScript SDK resource that sends state and typed questions to System One models such as Jev, mapping bare IDs like jev-latest onto the typesafe/ namespace. | Model access & gatewaysAPI gateways & proxies | |
| OpenRouter TypeScript SDK System One — codegithub.com | — | Official OpenRouter TypeScript SDK resource that sends state and typed questions to System One models such as Jev, mapping bare IDs like jev-latest onto the typesafe/ namespace. | Model access & gatewaysAPI gateways & proxies | |
| orq.ai classify APIgithub.com | — | TypeScript SDK for the orq.ai gateway whose beta classify resource runs typed noul, choice and score questions against classify models such as typesafe/jev-latest. | Model access & gatewaysAPI gateways & proxies | |
| orq.ai classify API (Python)github.com | — | Python SDK for the orq.ai gateway with a classify resource that runs typed noul, choice and score questions against classify models such as typesafe/jev. | Model access & gatewaysAPI gateways & proxies | |
| orq.ai classify API (Python) — apporq.ai | — | Python SDK for the orq.ai gateway with a classify resource that runs typed noul, choice and score questions against classify models such as typesafe/jev. | Model access & gatewaysAPI gateways & proxies | |
| orq.ai classify API (Python) — repogithub.com | — | Python SDK for the orq.ai gateway with a classify resource that runs typed noul, choice and score questions against classify models such as typesafe/jev. | Model access & gatewaysAPI gateways & proxies | |
| orq.ai classify API — repogithub.com | — | TypeScript SDK for the orq.ai gateway whose beta classify resource runs typed noul, choice and score questions against classify models such as typesafe/jev-latest. | Model access & gatewaysAPI gateways & proxies | |
| Phaseo TypeSafe System One supportgithub.com | — | System One protocol and executor in Phaseo, an OpenAI-compatible AI gateway with health-aware routing and cost and latency telemetry, so Jev decision requests can be sent through the gateway. | Model access & gatewaysAPI gateways & proxies | |
| Phaseo TypeSafe System One support — appphaseo.app | — | System One protocol and executor in Phaseo, an OpenAI-compatible AI gateway with health-aware routing and cost and latency telemetry, so Jev decision requests can be sent through the gateway. | Model access & gatewaysAPI gateways & proxies | |
| Phaseo TypeSafe System One support — repogithub.com | — | System One protocol and executor in Phaseo, an OpenAI-compatible AI gateway with health-aware routing and cost and latency telemetry, so Jev decision requests can be sent through the gateway. | Model access & gatewaysAPI gateways & proxies | |
| Pinutss/jev-model-routergithub.com | 2 | Route among multiple LLMs and multi-model provider keys without leaking secrets. | Model access & gatewaysAPI gateways & proxies | |
| Plexus decisions gatewaygithub.com | — | Unified LLM API gateway that adds a Jev-style decisions endpoint, routing state-plus-questions requests to TypeSafe /v1/systemone or OpenRouter's decisions API. | Model access & gatewaysAPI gateways & proxies | |
| Routstr TypeSafe upstreamgithub.com | — | Decentralized pay-per-request AI inference proxy, paid with Cashu Bitcoin micropayments, that adds a TypeSafe System One decision endpoint and Jev model catalog. | Model access & gatewaysAPI gateways & proxies | |
| Routstr TypeSafe upstream — docsdocs.routstr.com | — | Decentralized pay-per-request AI inference proxy, paid with Cashu Bitcoin micropayments, that adds a TypeSafe System One decision endpoint and Jev model catalog. | Model access & gatewaysAPI gateways & proxies | |
| routstrd System One pass-throughgithub.com | — | Local daemon for the Routstr provider network that forwards TypeSafe /v1/systemone request bodies verbatim, since the strict endpoint rejects the chat-completion fields it adds elsewhere. | Model access & gatewaysAPI gateways & proxies | |
| routstrd System One pass-through — repogithub.com | — | Local daemon for the Routstr provider network that forwards TypeSafe /v1/systemone request bodies verbatim, since the strict endpoint rejects the chat-completion fields it adds elsewhere. | Model access & gatewaysAPI gateways & proxies | |
| sdkgithub.com | 5 | andrelandgraf/safer-with-jev — Neon Function proxy for the Neon AI Gateway with TypeSafe Jev routing. · sdk · TypeScript | Model access & gatewaysAPI gateways & proxies | |
| sdkgithub.com | 3 | iamvatsalpatel/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. · sdk · TypeScript | Model access & gatewaysAPI gateways & proxies | |
| sdkgithub.com | 9 | rajdhakad9826/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. · sdk · TypeScript | Model access & gatewaysAPI gateways & proxies | |
| SLO Routergithub.com | 8 | OpenAI-compatible proxy that routes each request to the cheapest backend meeting its latency SLO, with optional Jev 1.13 semantic features; a live run found Jev changed no routes and raised p95 from 77.93 ms to 490.38 ms. | Model access & gatewaysAPI gateways & proxies | |
| TokenHub Jev semantic routinggithub.com | — | TokenHub, an enterprise AI gateway, can use Jev to choose the provider and upstream model for eligible Chat Completions requests among the candidates its base routing produced. | Model access & gatewaysAPI gateways & proxies | |
| TokenHub Jev semantic routing — appthinkinai-labs.github.io | — | TokenHub, an enterprise AI gateway, can use Jev to choose the provider and upstream model for eligible Chat Completions requests among the candidates its base routing produced. | Model access & gatewaysAPI gateways & proxies | |
| TrustedRouter Jevgithub.com | — | TrustedRouter, an end-to-end encrypted LLM gateway running in hardware enclaves, lists TypeSafe AI Jev as typesafe-ai/jev on a decide endpoint, with input pricing refreshed hourly from TypeSafe's models page. | Model access & gatewaysAPI gateways & proxies | |
| TrustedRouter Jev — apptrustedrouter.com | — | TrustedRouter, an end-to-end encrypted LLM gateway running in hardware enclaves, lists TypeSafe AI Jev as typesafe-ai/jev on a decide endpoint, with input pricing refreshed hourly from TypeSafe's models page. | Model access & gatewaysAPI gateways & proxies | |
| TrustedRouter Jev — repogithub.com | — | TrustedRouter, an end-to-end encrypted LLM gateway running in hardware enclaves, lists TypeSafe AI Jev as typesafe-ai/jev on a decide endpoint, with input pricing refreshed hourly from TypeSafe's models page. | Model access & gatewaysAPI gateways & proxies | |
| TypeSafe Jev on LiteLLMdocs.litellm.ai | — | LiteLLM announcement that its proxy (v1.103.0-rc) passes through TypeSafe's /v1/systemone endpoint with logging and cost tracking, so clients call Jev with a LiteLLM virtual key. | Model access & gatewaysAPI gateways & proxies | |
| TypeSafe Jev on LiteLLM — repogithub.com | — | LiteLLM announcement that its proxy (v1.103.0-rc) passes through TypeSafe's /v1/systemone endpoint with logging and cost tracking, so clients call Jev with a LiteLLM virtual key. | Model access & gatewaysAPI gateways & proxies | |
| unhardcodedgithub.com | 8 | OpenAI-compatible LLM router that picks a model per request from a caller-supplied policy, and serves decision models including Jev through POST /v1/decisions with the same selection and fallback. | Model access & gatewaysAPI gateways & proxies | |
| unhardcoded — docsgithub.com | 8 | OpenAI-compatible LLM router that picks a model per request from a caller-supplied policy, and serves decision models including Jev through POST /v1/decisions with the same selection and fallback. | Model access & gatewaysAPI gateways & proxies | |
| uni-api TypeSafe backendgithub.com | — | Adds TypeSafe Jev as a backend to uni-api, a unified LLM API gateway with load balancing, so decision requests route through the same OpenAI-style interface as its other providers. | Model access & gatewaysAPI gateways & proxies | |
| uni-api TypeSafe channelgithub.com | 26 | Web console for the self-hosted uni-api LLM gateway that can add a typesafe engine channel, proxying POST /v1/systemone so Jev's Choice, Noul and Score questions go through the gateway. | Model access & gatewaysAPI gateways & proxies | |
| Venice System One compatibilitydocs.venice.ai | — | API reference for Venice's TypeSafe-compatible POST /systemone alias of its Decisions API, letting System One clients call Jev through Venice. | Model access & gatewaysAPI gateways & proxies | |
| Venice System One compatibility — repogithub.com | — | API reference for Venice's TypeSafe-compatible POST /systemone alias of its Decisions API, letting System One clients call Jev through Venice. | Model access & gatewaysAPI gateways & proxies | |
| Vercel AI Gatewayvercel.com | — | Serves typesafe-ai/jev on Vercel's AI Gateway through the AI SDK's experimental evaluate interface, where the Boolean primitive maps to TypeSafe's Noul. | Model access & gatewaysAPI gateways & proxies | |
| Vercel AI Gateway — announcementx.com | — | Serves typesafe-ai/jev on Vercel's AI Gateway through the AI SDK's experimental evaluate interface, where the Boolean primitive maps to TypeSafe's Noul. | Model access & gatewaysAPI gateways & proxies | |
| YoMo TypeSafe System One providergithub.com | — | YoMo, a serverless edge AI agent framework, adds a TypeSafe System One provider that proxies Jev decision requests through its geo-distributed model API layer. | Model access & gatewaysAPI gateways & proxies | |
| YoMo TypeSafe System One provider — appyomo.run | — | YoMo, a serverless edge AI agent framework, adds a TypeSafe System One provider that proxies Jev decision requests through its geo-distributed model API layer. | Model access & gatewaysAPI gateways & proxies | |
| ZenMux TypeSafe System One APIzenmux.ai | — | API reference for calling TypeSafe System One evaluation requests with Jev through the ZenMux model gateway. | Model access & gatewaysAPI gateways & proxies | |
| ZenMux TypeSafe System One API — repogithub.com | — | API reference for calling TypeSafe System One evaluation requests with Jev through the ZenMux model gateway. | Model access & gatewaysAPI gateways & proxies |
Cloud platforms2 of 2 matches
| Resource | Stars | Description | Category | Save |
|---|---|---|---|---|
| Cloudflare Jev model cataloggithub.com | — | Cloudflare's model catalog entry for typesafe/jev, listing Jev for Noul, Choice and Score evaluation at $0.042 per million input tokens and free output, with a worked example. | Model access & gatewaysCloud platforms | |
| Cloudflare Jev model catalog — docsdevelopers.cloudflare.com | — | Cloudflare's model catalog entry for typesafe/jev, listing Jev for Noul, Choice and Score evaluation at $0.042 per million input tokens and free output, with a worked example. | Model access & gatewaysCloud platforms |
Hosting & serving7 of 7 matches
| Resource | Stars | Description | Category | Save |
|---|---|---|---|---|
| Beam managed System One endpointgithub.com | — | Beam's serverless GPU runtime can host a decision-kind managed endpoint that serves a System One model on TypeSafe's /v1/systemone contract. | Model access & gatewaysHosting & serving | |
| Beam managed System One endpoint — appbeam.cloud | — | Beam's serverless GPU runtime can host a decision-kind managed endpoint that serves a System One model on TypeSafe's /v1/systemone contract. | Model access & gatewaysHosting & serving | |
| endpointgithub.com | 335 | ekzhang/openjev-sglang — Jev-compatible API endpoint based on open models (prefill-only) · endpoint · Python | Model access & gatewaysHosting & serving | |
| endpointgithub.com | 577 | featherless-ai/simple-jev — Turn any open model into a classifier/jev endpoint · endpoint · Python | Model access & gatewaysHosting & serving | |
| endpointgithub.com | 25 | fidecastro/jevify — Supersimple way to serve LLMs as a Jev-like endpoint · endpoint · Python | Model access & gatewaysHosting & serving | |
| endpointgithub.com | 3 | us/jev-local — Local Jev-compatible evaluation server: POST /v1/systemone with typed noul/choice/score, open weights, no waitlist · endpoint · Python | Model access & gatewaysHosting & serving | |
| Nemotron Diffusion Decision Labgithub.com | 12 | Experimental container that serves the dense Nemotron-Labs-Diffusion-14B model behind a TypeSafe-shaped API, with a browser explorer for Choice, Noul and Score distributions. | Model access & gatewaysHosting & serving |
More projects & source code20 of 20 matches
| Resource | Stars | Description | Category | Save |
|---|---|---|---|---|
| AI/ML API Jev — repogithub.com | — | AI/ML API documentation for serving TypeSafe Jev as typesafe/jev under its decision-models API, with a playground and Python/Node.js snippets for state-plus-questions requests. | Model access & gatewaysMore projects & source code | |
| AntSeed TypeSafe providergithub.com | — | Peer-to-peer AI inference market where providers can offer TypeSafe System One decisions through a provider-typesafe plugin, discovered by buyers over DHT. | Model access & gatewaysMore projects & source code | |
| endpointgithub.com | 4 | Query-farm/vgi-typesafe — A VGI worker exposing TypeSafe System One questions (choice, noul, score) to DuckDB/SQL as LATERAL-joinable table functions · endpoint · Python | Model access & gatewaysMore projects & source code | |
| endpointgithub.com | 28 | colliber/duckdb-jev — DuckDB extension: typed Jev answers as real SQL types · endpoint · C++ | Model access & gatewaysMore projects & source code | |
| endpointgithub.com | 87 | giuliosmall/pg_typesafe — Pre-alpha PostgreSQL extension for TypeSafe AI (Jev) categorical classification · endpoint · C | Model access & gatewaysMore projects & source code | |
| endpointgithub.com | 2 | molis-ai/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. · endpoint · TypeScript | Model access & gatewaysMore projects & source code | |
| endpointgithub.com | 5 | ponyo877/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. · endpoint · JavaScript | Model access & gatewaysMore projects & source code | |
| endpointgithub.com | 12 | pst2154/Nemotron_Jev — Nemotron Diffusion Decision Lab · endpoint · HTML | Model access & gatewaysMore projects & source code | |
| endpointgithub.com | 389 | realZachi/pg-jev — Ask your Postgres tables questions in plain language. A PostgreSQL extension powered by TypeSafe's Jev. · endpoint · Shell | Model access & gatewaysMore projects & source code | |
| HarnessRouter systemone basegithub.com | — | HarnessRouter, a self-hosted unified interface for agent harnesses, runs a systemone base that serves Jev through either TypeSafe's API or OpenRouter under their own model ids. | Model access & gatewaysMore projects & source code | |
| Jev Livegithub.com | 5 | Camera app for macOS that adds Japanese variety-show captions, manga sound-effect words, speed lines and mood effects while you talk, with Jev alone deciding what appears and when from a closed set. | Model access & gatewaysMore projects & source code | |
| jev-localgithub.com | 3 | Local server compatible with the /v1/systemone API that answers typed noul, choice and score questions with probabilities from open weights, so the official SDK can point at it; the default scorer is a deterministic stub. | Model access & gatewaysMore projects & source code | |
| jev-router (daviddl9)github.com | 0 | Router extension for the OMP and Pi coding agents where Jev picks the worker tier for each step, keeping planning and review on a strong model and sending bounded tasks to cheaper workers. | Model access & gatewaysMore projects & source code | |
| jevify (fidecastro)github.com | 25 | Adapter that serves any model with logprobs behind an OpenAI-compatible endpoint, or a small in-process model, as a Jev-like endpoint by reading typed answers off the next-token distribution in Jev's API shape. | Model access & gatewaysMore projects & source code | |
| model_idgithub.com | 1 | MobAI-Inc/Cynosure — Jev-based adaptive model routing with structured decisions, persistent feedback, and hybrid retrieval · model_id · TypeScript | Model access & gatewaysMore projects & source code | |
| Pollinations Jev APIgithub.com | — | The Pollinations gen API serves Jev as typesafe/jev-1.13 through a typed POST /alpha/decisions endpoint and Chat Completions, plus an Ask Jev MCP server with a jev_decide tool. | Model access & gatewaysMore projects & source code | |
| sdkgithub.com | 2 | cannacre8ive/switchboard-ai — Adaptive multi-model AI orchestration runtime using Jev for cost-aware routing, confidence-based escalation, tool selection, and model execution · sdk · JavaScript | Model access & gatewaysMore projects & source code | |
| switchboard-aigithub.com | 2 | Adaptive multi-model AI orchestration runtime using Jev for cost-aware routing, confidence-based escalation, tool selection, and model execution | Model access & gatewaysMore projects & source code | |
| ThinkAI decision APIgithub.com | 9 | PHP SDK for the ThinkAI model aggregation service whose decision() resource evaluates Jev noul and choice questions (model jev-latest) next to chat, image and voice APIs. | Model access & gatewaysMore projects & source code | |
| ← Back to Awesome Jevgithub.com | 24 | Listed by the source without a separate description. | Model access & gatewaysMore projects & source code |
More posts & discussions4 of 4 matches
| Resource | Stars | Description | Category | Save |
|---|---|---|---|---|
| Jev on DGridx.com | — | DGrid added Jev 1.13 to its model catalog, serving routing, classification and scoring requests with multiple typed questions per call. | Model access & gatewaysMore posts & discussions | |
| Jev on the Venice APIx.com | — | Demo marking Jev's beta launch on the Venice API, classifying 24,000 Hacker News posts into 12 categories in about 2 minutes. | Model access & gatewaysMore posts & discussions | |
| Jev on the Venice API — announcementx.com | — | Demo marking Jev's beta launch on the Venice API, classifying 24,000 Hacker News posts into 12 categories in about 2 minutes. | Model access & gatewaysMore posts & discussions | |
| TypeSafe console — announcementx.com | — | Official console for creating API keys, trying Jev in the playground and inspecting live requests. | Model access & gatewaysMore posts & discussions |
More guides & websites12 of 12 matches
| Resource | Stars | Description | Category | Save |
|---|---|---|---|---|
| Agent action approval — modelopenrouter.ai | — | OpenRouter Labs recipe that runs four checks (off task, could destroy, untrusted input, ask first) on each of 24 coding or ops agent tool calls in one request, so risky steps stop for a person: 96 answers in 0.5 s. | Model access & gatewaysMore guides & websites | |
| AI/ML API Jevdocs.aimlapi.com | — | AI/ML API documentation for serving TypeSafe Jev as typesafe/jev under its decision-models API, with a playground and Python/Node.js snippets for state-plus-questions requests. | Model access & gatewaysMore guides & websites | |
| AI/ML API Jev — appaimlapi.com | — | AI/ML API documentation for serving TypeSafe Jev as typesafe/jev under its decision-models API, with a playground and Python/Node.js snippets for state-plus-questions requests. | Model access & gatewaysMore guides & websites | |
| AntSeed TypeSafe provider — appantseed.com | — | Peer-to-peer AI inference market where providers can offer TypeSafe System One decisions through a provider-typesafe plugin, discovered by buyers over DHT. | Model access & gatewaysMore guides & websites | |
| HarnessRouter Super Mario kit — appharnessrouter.ai | — | Starter kit where a System One model plays Full Screen Mario in a headless browser several times a second, reading the game state as a few literal sentences and choosing one control. | Model access & gatewaysMore guides & websites | |
| Jev on DGrid — appdgrid.ai | — | DGrid added Jev 1.13 to its model catalog, serving routing, classification and scoring requests with multiple typed questions per call. | Model access & gatewaysMore guides & websites | |
| Jev on Venicedocs.venice.ai | — | Venice API lists Jev (System One) as a beta model under the id jev-latest, so it can be called through Venice's private-inference API. | Model access & gatewaysMore guides & websites | |
| Jev on Venice — sitevenice.ai | — | Venice API lists Jev (System One) as a beta model under the id jev-latest, so it can be called through Venice's private-inference API. | Model access & gatewaysMore guides & websites | |
| OpenCode Zenopencode.ai | — | Hosts Jev on a TypeSafe-compatible endpoint, including a free variant. | Model access & gatewaysMore guides & websites | |
| OpenRouter Jev Labopenrouter.ai | — | Runnable recipes for ticket triage, agent action approval, candidate extraction, feed filtering, and more. | Model access & gatewaysMore guides & websites | |
| Pollinations Jev API — apppollinations.ai | — | The Pollinations gen API serves Jev as typesafe/jev-1.13 through a typed POST /alpha/decisions endpoint and Chat Completions, plus an Ask Jev MCP server with a jev_decide tool. | Model access & gatewaysMore guides & websites | |
| Pollinations Jev API — docsgen.pollinations.ai | — | The Pollinations gen API serves Jev as typesafe/jev-1.13 through a typed POST /alpha/decisions endpoint and Chat Completions, plus an Ask Jev MCP server with a jev_decide tool. | Model access & gatewaysMore guides & websites |
No matches this time
Try a broader search or reset your filters to explore the full collection.
Showing 159 of 159 resources