A Jev practice catalog and local-first Agent skill router: map recurring logs to reusable decisions, tools, and workflows.
Agent tooling — page 38
Frameworks, routers and utilities that use Jev to choose tools or branches inside a larger agent system.
1,206 active projects in this collection. All collections →
Calibrated Jev 1.13 percentages for Cline ask_question options — PreToolUse/PostToolUse hooks, a Cline plugin, a universal MCP server and a CLI.
0
Score AI agent context for relevance with Jev, and prune what's no longer useful.
0
Dertek AI - A fast, cost-efficient AI agent for coding and knowledge work. Agentic cli with TypeSafe Jev that uses fewer LLM tokens, lowers LLM cost, and routes tasks to the right model.
Fact-checking skill for DeepSeek Harness: multi-source verification against the open web, domestic and international ecosystems, optional TypeSafe Jev (System One) judgements.
Ask Jev (TypeSafe System One) typed questions from DeepSeek Harness: batch judgements with probabilities, configured per user in Settings.
A portable agent skill for bounded decisions through TypeSafe Jev and Vercel AI Gateway.
Preserve exact context across Codex compaction with Jev. Open-source plugin, CLI, and library.
Hermes 插件：被标记的危险命令交给 TypeSafe Jev 裁决——放行则执行，拒绝则拦截并弹出系统通知+提示音；clarify 提问同样提醒。
Type-safe intent classification guard for agentic workflows
0
CLI and MCP server for TypeSafe's Jev model, built for scripts, agents, and automation.
0
将你的jev变成mcp插件，接入任意agent(Claude,codex,Cherry Studio)。辅助llm决策层。Turns your jev into an MCP plugin, helping LLM make decisions.
Classify page context, score configurable risks and apply advertiser-owned brand-safety policy.
Experimental opt-in Jev skills and config for Claude Code — the companion to jev-codex-tools.
0
Command-line tool for the TypeSafe Jev decision model, through the official API or OpenRouter: typed yes/no, choice and score questions with calibrated confidence, and confidence gating as exit codes.
0
High-performance Unix semantic reflex CLI powered by TypeSafe Jev for agent progressive discovery & pipelines
让 Agent 长出「操作杆」：用 System One 模型（Jev）承担高频判断、多模态模型当眼睛。给思路 + 可跑的参考实现（75 条离线断言，零依赖零 key）
让 AI Agent 直接调用 TypeSafe AI「Jev」决策模型的 Skill —— 免 API key，纯标准库 CLI。Agent Skill for TypeSafe AI Jev (System One).
No project description available.
A Jev-powered security guard for AI agents: blocks dangerous tool calls, strips prompt injection, scans skills. Works with Claude Code, Codex, Copilot CLI, Gemini CLI, Cursor, and OpenCode.
Open-source developer harness and runtime safety toolkit for AI coding agents powered by TypeSafe AI / Jev
Classify financial PDFs with TypeSafe Jev via OpenRouter, with a probability per document type.
A Claude Code plugin that takes skills already in use and adds one thing to each: a typed judgment from [TypeSafe](https://typesafe.ai) Jev (System One) at the points where the skill previously relied on the agent's own impression.
Self-improving agents that know what's noise: typed decisions instead of generated text, a policy that evolves from the agent's own mistakes, and a report of how much of the gain was selection luck.