Infra / SDKs / Integrations

Self-hosted Docker service and web console that serves Laya's multilingual model on Jev's /v1/systemone format behind API keys.

Ollama-style runtime that pulls System One decision models from Hugging Face and serves them locally behind /v1/systemone.

Jev- and OpenAI-Decisions-compatible System One server on DiffusionGemma 26B-A4B, also serving Laya, Clef and other open models.

Local Jev-compatible API on a Mac: Qwen via llama.cpp/Metal reads one output token per question for text and image decisions.

Native Swift port of OpenJev: a Jev-compatible /v1/systemone server on Apple Silicon Macs and libraries for on-device iPhone decisions.

GGUF-native Rust and CUDA engine tuned for cold starts, with a system1 command that scores candidate answers in one forward pass.

Rust server on candle that serves open decision models like Laya and Clef behind a System One-compatible API with dynamic batching.

Runs Laya System 1 models on a Mac's GPU in Rust with custom Metal kernels, serving the same /v1/systemone API as laya serve.

Deploys DiffusionGemma-Jev behind a TypeSafe-compatible API on a Cloud Run GPU, with snake, dino and tetris demos.

GitHub Next's Bun server that exposes a Jev-compatible /v1/systemone API by asking DiffusionGemma for probabilities via a chat endpoint.

Training-free runtime turning local Qwen3/Qwen3.5 checkpoints into a Jev-style Noul/Choice/Score service via candidate-token logits.

Bring-your-own-key wrapper that exposes Upstage Solar Pro4 or Mini4 behind Jev's /v1/systemone shape, with a comparison benchmark.

Gateway that distils System One or LLM answers into small fine-tuned classifiers and serves them when confident, falling back otherwise.

Archived early Jev-compatible API server running Qwen3.6-35B-A3B prefill-only on SGLang via Modal; superseded by SGLang's native endpoint.

Drop-in faster backend for Open-Jev-27B using custom CUDA kernels, a prefix tree and CUDA graphs: about 6x lower JevBench latency.

Paused C#/.NET 10 non-autoregressive decision engine running a Laya/mmBERT checkpoint locally, returning Choice, Score and Boolean answers.

CUDA-native engine that serves open Qwen3.5 checkpoints behind a Jev-compatible API, reading option logits without decoding.

Core ML and Neural Engine port of Laya for Apple Silicon, about 5 ms per short decision on an M3 Max with energy benchmarks.

Code Mode for MCP where retrieval shortlists tools and Jev picks one or says none fits, benchmarked on several tool-use suites.

Installable agent skills for triage, routing, code review and document work with Jev, plus 108 scenarios and recorded examples.

Hugging Face blog on llama.cpp's /v1/systemone endpoint serving decision models locally in Jev's wire format.

Vercel Labs terminal CLI for AI tasks that can use Jev as the evaluation model for its evaluate command.

Single-tool MCP server that acts as a code-review gate powered by TypeSafe Jev.

Vercel AI SDK for TypeScript, whose TypeSafe provider lets apps call Jev through a shared evaluate interface.

TypeSafe's official Jev documentation: concepts, primitives, HTTP API, patterns, cookbooks and SDK references.

Netlify AI Gateway support for TypeSafe Jev: call @typesafe-ai/sdk from Netlify Functions with Netlify handling keys and billing.

Vercel AI Gateway model page hosting Jev as typesafe-ai/jev for AI SDK evaluate calls, with no TypeSafe waitlist.

OpenRouter's catalogue of decision models from several publishers behind its alpha Decisions API, with an agent-skill usage guide.

Official Vercel AI SDK provider @ai-sdk/typesafe-ai for calling Jev as an evaluation model with experimental_evaluate.

TypeSafe AI's GitHub Pages repository; no description or README was published.