Skip to content
Metatext Decide — typed decisions for your agents, with a probability on every answerGet early access
Metatext
Sign Up

ai-type-safe-platform

Symfony AI platform bridge for TypeSafe, letting PHP Symfony apps call System One models like Jev.

Demo
View on GitHub ↗

Overview

TypeSafe Platform is the TypeSafe bridge package for Symfony AI, the AI component family of the Symfony PHP framework. It lets Symfony applications use TypeSafe's System One models, such as Jev, through the Symfony AI platform abstraction.

The README is a short read-only mirror notice linking to TypeSafe's docs on System One, questions, models and the API reference; issues and pull requests go to the main symfony/ai repository.

What the decision model decides

TypeQuestionAnswers
OtherWhatever Choice, Score or Noul questions the application defines(inferred)—

How it works

  1. Install the bridge with Symfony AI
  2. Configure a TypeSafe key
  3. Send state and typed questions via the platform
  4. Use the typed result in the app

Strengths

  • Official Symfony ecosystem package
  • Uses Symfony AI's common abstraction

Caveats

  • README has almost no usage detail
  • Read-only subtree split; contribute upstream

At a glance

Type
Demo
Language
PHP
Runtime
Symfony AI bridge
Has code
yes

Use cases and integrations

How curated lists describe it

Frequently asked questions

What is it?

A Symfony AI bridge for TypeSafe's System One API.

Where do I report issues?

In the main symfony/ai repository.

Where are the API docs?

docs.typesafe.ai, linked from the README.

Related projects

  • Ax

    Ax, a DSPy-style multi-language LLM framework, listed with a native TypeSafe provider for Boolean, Choice, Score and raw Jev questions.

    PluginproductionTypeScript
  • Effect

    Effect TypeScript library whose @effect/ai-typesafe package maps classify, probability and rating operations to Jev questions.

    ProjectproductionTypeScript
  • instructor-php

    PHP monorepo whose Polyglot module adds a TypeSafe driver for typed Noul, Choice and Score decisions alongside LLM inference.

    ProjectproductionPHP
  • req\_llm

    Elixir library for unified LLM calls across providers, with an evaluate interface that calls Jev via TypeSafe or OpenRouter.

    ProjectproductionElixir
  • synkora-ai

    Self-hosted multi-tenant AI agent platform listed as including optional TypeSafe client tools for classification, scoring and yes/no.

    LibraryproductionPython
  • TanStack AI

    Provider-agnostic TypeScript AI SDK; per list sources, an @tanstack/ai-typesafe adapter exposes Jev decisions through decide().

    ServiceproductionTypeScript