zcode-jev

Typed judgment layer for coding agents — gates from PRD to ship. Jev-ready, provider-agnostic.

How it uses Jev

Typed judgment layer for coding agents — gates from PRD to ship. Jev-ready.

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 zcode-jev

Browse all
pi-jev (y0usaf) project preview
Agent tooling
TypeSafe Jev as a decision layer for the Pi coding agent: a measured tool-call gate plus jev_ask for typed, calibrated answers
pi-quiet-ask project preview
Agent tooling
TypeSafe Jev as the pi coding agent's quiet decision layer
jev-mcp (rashedInt32) project preview
MCP server exposing TypeSafe Jev as typed, calibrated judgment tools: classify, score, check, batched ask. Ships as a Claude Code plugin.
jevflow project preview
Applications
Probabilistic AI decisions as composable backend primitives — typed judgments (noul/score/choice), deterministic thresholds, and explainable workflows. Powered by TypeSafe's Jev, provider-agnostic.
agent-fastpath project preview
Browser & computer use
Jev MCP server: a decision layer for coding agents, built on TypeSafe Jev (System One model). Ship gates, risk checks, file triage that keeps files out of context, and a safe headless browser, with calibrated confidence. For Claude Code, Codex, Cursor.
ruby_llm-providers-typesafe project preview
Benchmarks & research
TypeSafe System One models (Jev) for RubyLLM: typed judgments, evaluations and reranking.
system-one (iamaamir) project preview
Benchmarks & research
Provider-neutral System One runtime for TypeScript and Pi
eve project preview
Integrations
Vercel's open agent framework, which ships Jev as the default evaluation model in its experimental evaluate path.
s1-rs project preview
SDKs & clients
Typed System One layer for Rust (Choice/Score/Noul).