typesafe-ai-playground (markjaquith)

A playground for experiments around Jev, TypeSafe's System One model.

How it uses Jev

Just a playground for experiments around Jev, TypeSafe's System One model.

Getting started

The file argument accepts UTF-8 text, including Markdown, CSV, and JSON as text. Input is sent in full to TypeSafe in one evaluation, without truncation. PDF and other binary formats must first be converted to text. Empty input is an error. When a file is supplied, it takes precedence over stdin.

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-ai-playground (markjaquith)

Browse all
typesafe-arena project preview
Demos & playgrounds
A playground for TypeSafeAI's Jev Model
guard-jev project preview
Demos & playgrounds
Comment-moderation playground: paste a comment, Jev decides what to do with it.
jevplay project preview
Demos & playgrounds
TypeSafe Jev playground — custom Choice/Score/Noul builder with live distributions
jevalyn project preview
SDKs & clients
The decision layer for your Rails app. A Rails-native wrapper around TypeSafe's Jev System One API: typed, calibrated decisions in your control flow.
Jev Driving Lab project preview
Jev for robotics
Interactive experiments from support routing to a 3D driving simulation: structured sensor state in, typed steer, brake, and overtake decisions out.
jev-lab project preview
Benchmarks & research
TypeScript experiments, evaluations, and latency benchmarks for TypeSafe's Jev model
jevplayground project preview
Browser & computer use
Browser-only playground for Jev (TypeSafe AI's decision model) via Vercel AI Gateway
fast-dev-compaction project preview
Agent tooling
Codex plugin: verbatim Jev-guided context restoration around session compaction. Port of tamaratran/fast-jev-compaction to Codex lifecycle hooks.
jev-reviews project preview
Benchmarks & research
TypeSafe AI - Jev - first look and experiment with its API + Google reviews experiments