Guardrails for AI agent actions. Deterministic policy, Jev semantic checks, and replayable decisions.
Jev ecosystem projects — page 190
5191 repositories with documented relationships and source evidence.
Typed questions to a model, verdict in code, thresholds from your labels
No project description available.
TypeSafe AI is a San Francisco AI lab building System One models — a class of model trained to return typed, calibrated decisions for software instead of generated text. Its flagship and first System One model, Jev, is served by a single HTTP endpoint: POST /v1/systemone takes a `state` (a string, JSON object, or array) plus a map of typed…
No project description available.
No project description available.
Cache-aware, TypeSafe-driven model tier router for Claude Code
No project description available.
Fail-closed Jev policy gate for Hermes Agent tool calls
No project description available.
Open WebUI pipeline that routes prompts to a cheap or expensive LLM using TypeSafe AI classification
Experimental out-of-tree Kubernetes scheduler plugin that uses TypeSafe's Jev model to produce typed, advisory diagnoses for unschedulable Pods.
No project description available.
Unofficial Go port of the TypeSafe AI SDK
Community Rust SDK for the TypeSafe AI API. A port of the official JavaScript SDK.
No project description available.
No project description available.
Community-built Rust SDK for the TypeSafe AI API (System One / Jev). A port of typesafe-sdk-python
Typed decisions from TypeSafe AI's Jev model inside TYPO3: a decision editor and playground in the backend, powermail_cond operators, and submission routing
Measure meaning by perturbing text and watching a calibrated probability move. Ablation attribution over TypeSafe's Jev, reported against a measured noise floor.
Use jev to classify tags for pages
See what an AI agent actually did, not just its score. Labels every step of a CLI agent's run and compares two rounds against the noise a re-run produces anyway.
A stop-loss for coding agents. Counts loops in code, judges drift with TypeSafe's Jev, and never sends your source anywhere.
Play tic-tac-toe against TypeSafe Jev using typed System One decisions.