typesafe_sdk

An idiomatic, type-safe Elixir port of the official TypeScript AI SDK (ai / ai-sdk) providing unified LLM integrations, streaming text and structured outputs, tool calling, and agentic workflows. Jev is their current flagship model and is the first System One model.

How it uses Jev

This project has moved Do not start new projects with typesafe sdk . TypeSafeSDK 0.4.1 is the final release of this package line. New development should use: system one sdk Current release: 0.5.0 system one sdk is the provider-neutral successor to this project and carries the semantic question API, prepared evaluations, typed answers, batching, telemetry, runtime controls, OTP integration, testing support, and decis…

Source: community catalog. Details and metrics reflect the published community snapshot and are not a performance endorsement. Documentation details extracted from GitHub · the README.

Keep exploring

Similar to typesafe_sdk

Browse all
typesafe project preview
SDKs & clients
An idiomatic Elixir client for the TypeSafe AI API
typesafe_sdk_ex project preview
SDKs & clients
Typesafe AI SDK in Elixir using Req
typesafe_ai (typesend) project preview
Unofficial Elixir SDK for the TypeSafe AI API
TypeSafe JavaScript SDK project preview
Official TypeScript/JavaScript client with inferred answer types. npm install @typesafe-ai/sdk.
ruby_llm-typesafe project preview
Integrations
TypeSafe structured-output provider for RubyLLM 2
ai-type-safe-platform project preview
Demos & playgrounds
TypeSafe platform bridge for Symfony AI
jev-bun1 project preview
Demos & playgrounds
TypeSafe の Jev を TypeScript SDK で使ってみる最初の 1 歩
Jev-Mem project preview
Agent tooling
Jev-Mem: System-One Controlled Agentic Memory
typesafe-local project preview
Benchmarks & research
Inspired by TypeSafe Ai, Ask a local LLM typed questions, get calibrated probabilities instead of text. Structured output without generation or parsing. MLX / Apple Silicon.