Official

TypeSafe docs, SDKs, playground, and repos they actually maintain.

Start here when you want the real API, not a fork with vibes. Docs, SDKs, playground, evals, and the manifesto. These links are the canonical source for endpoint shapes, pricing notes, and primitive definitions. When you compare latency or file a bug, cite TypeSafe surfaces first. This hub gathers every official entry we index so you can jump to docs.typesafe.ai or the playground without wading through community summaries.

19 listings in this bucket · Learn Jev

Official205

OfficialDemoFeatured

TypeSafe agent skills

Official agent skill for Claude Code, Codex, and compatible agents: primitives, patterns, and how to structure evaluations.

officialagentseval

Details Demo

OfficialTypeScript114

OfficialFeatured

TypeSafe JavaScript SDK

Official TypeScript/JavaScript client with inferred answer types. npm install @typesafe-ai/sdk.

officialsdk

Details

OfficialPython108

Official

System One adapter (Python)

Official drop-in TypeSafeClient replacement backed by OpenAI, Anthropic, and compatible LLM APIs, for comparing Jev against chat models.

officialsdk

Details

OfficialPython80

OfficialDemo

TypeSafe Python SDK

Official sync and async Python client. pip install typesafe-sdk.

officialsdk

Open link Demo

Official

OfficialDemo

TypeSafe AI

Company homepage, waitlist, and product overview.

official

Open link Demo

Official

OfficialDemo

Documentation

Introduction, primitives, patterns, cookbooks, HTTP API, and SDK references.

officialsdk

Open link Demo

Official

OfficialDemo

Quick start

Shortest path from an API key to a typed decision.

official

Open link Demo

Official

OfficialDemo

Playground

Paste a state, add questions, and see typed answers in the browser.

officialbrowser-use

Open link Demo

Official

OfficialDemo

HTTP API reference

Request and response contract for POST /v1/systemone.

official

Open link Demo

Official

OfficialDemo

Primitives

Choice, Score, and Noul: the three question types and what they return.

official

Open link Demo

Official

OfficialDemo

Patterns

Speculative fan-out, confidence-gated routing, composite scoring, and intent routing.

officialrouting

Details Demo

Official

OfficialDemo

Cookbooks

Reproducible recipes: parallel questions, reranking, guardrails, citation checks, extraction, hierarchical classification.

officialguardrailsrag

Details Demo

Official

OfficialDemo

Smart home demo

Official interactive demo of speculative fan-out: many questions in one call, code keeps the relevant answers.

official

Details Demo

Official

OfficialDemo

Workflow evals

Published eval methodology and per-model results for System One workflows.

officialeval

Open link Demo

Official

OfficialDemo

Jev 1.13 jaggedness

Known failure modes of the current public model, documented by TypeSafe.

official

Open link Demo

Official

OfficialDemo

Introducing System One Models and Jev

Launch post: architecture, RLCD training, pricing, Doom and Wikiracing demos, FAQ.

officialgame

Details Demo

Official

OfficialDemo

Manifesto

The case for machine-native intelligence built for software, not conversation.

official

Open link Demo

Official

OfficialDemo

Discord

Official TypeSafe server. Builder demos live in the Show and Tell channel.

official

Open link Demo

Official

@typesafeai on X

Product and research updates.

official

Open link