jev (BorisLeMeec)

A claude code plugin for jev

How it uses Jev

A Claude Code plugin backed by TypeSafe's Jev — a small model that returns calibrated probabilities instead of prose, at $0.042 per million tokens. It reads your files so the agent doesn't have to.

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 jev (BorisLeMeec)

Browse all
claude-jev-plugin project preview
Agent tooling
TypeSafe Jev semantic guardrails for Claude Code
claude-jev (0x7067) project preview
Agent tooling
Claude Code plugin: Jev for rule checks, verbatim compaction, and prompt routing
jev-pruner project preview
Agent tooling
Claude Code plugin: trim long Bash output with TypeSafe Jev before the model sees it
claude-jev project preview
Benchmarks & research
Claude Code plugin that scores review findings, debug hypotheses and design options with TypeSafe's Jev — calibrated probabilities instead of one more opinion.
llm-typesafe project preview
Applications
LLM plugin for accessing Jev and other TypeSafe AI models
TypeSafe agent skills project preview
Official agent skill for Claude Code, Codex, and compatible agents: primitives, patterns, and how to structure evaluations.
hermes-jev-skills project preview
Browser & computer use
Jev-powered model routing, memory, compaction, skill selection, computer and browser use for Hermes agents (also Claude Code and Codex)
jev-browser-skill project preview
Browser & computer use
Let Jev, TypeSafe's ~100ms decision model, drive your browser. A plug-and-play skill for Claude Code and Codex.
dsh-jev-decide project preview
Benchmarks & research
DSH plugin: register TypeSafe Jev (System One decision model) as an agent tool — jev_decide returns calibrated probabilities (noul/choice/score) for routing/triage/guardrail judgments, no text generation. 把 TypeSafe Jev 决策模型注册为 DSH agent 工具