Agent tooling — page 12

⚡ Ultra-fast, low-cost intelligent task classifier and 3-tier routing engine powered by TypeSafe Jev (System One)

Semantic MCP firewall powered by Jev — screens every tool call, tool result, and tool description with calibrated System One verification. 94% block recall, 0 false positives, ~$0.00002/check.

Minimal agent loop where Jev directs control flow and a LangChain chat model writes argument values and the final response.

A pi extension that exposes TypeSafe (Jev, System One) judgments as five pi tools, so a model can make narrow semantic judgments while your code and your users keep control of thresholds, weights, and actions.

PiJev: a terminal coding agent with Jev in the loop — Jev ranks the repository's files before the first call, picks skills and triages failures; your coding model writes the code. Built on Pi.

CLI and agent skill for TypeSafe System One (Jev): typed Choice, Score, and Noul judgments.

Claude Code mod that routes decisions to TypeSafe's Jev model: ranks installed skills per prompt, and answers the agent's own this-or-that questions when confident.

Route models and tools with TypeSafe

Run AI coding agents in parallel, each in its own git worktree. Desktop app for Linux, macOS and Windows (Tauri + Rust).

Grok skill: Jev as a judgment sensor in a builder-agent loop (priors × probabilities → next act)

Predict another skill's next closed decision with TypeSafe Jev — without running that skill.

No project description available.

Meta-Architect (MA) is a workflow layer that adds architecture, evidence, and release-gate discipline on top of Codex, MCP, and other 55+ AI coding agents — without replacing them.

AI-driven autonomous NPCs and adventurer bots for Ultima Online — fight, loot, craft, trade, and socialize via YAML archetypes

A unified, async Python framework for LLM applications—chat, autonomous agents, RAG, and sandboxed code execution. Supports OpenAI, Anthropic, Gemini, Ollama, and more through a single API. Features an 8-phase cognitive reasoning cycle, Docker-based isolation, human-in-the-loop approvals, session management, and comprehensive observability.

Local knowledge search with three modes: BM25 + Jev by default, agentic multi-query lexical search + Jev without vectors, and optional BM25 + embeddings/RRF + Jev, with grounded streaming answers.

System 1 for your coding agent: cut token use by deciding, not generating.

Shared memory Jev-based plugin for multi-agent coding: subagents and Codex/Claude Code/Cursor hand-offs share one project memory. 一个多agent协同高效记忆统筹插件

One AI skill + MCP server for Claude Code, Codex and Hermes: Jev (TypeSafe) gates large-model turns (event triage, review verdicts, owner questions, tool choice), runs build-and-repair loops with independent review, routes models and skills, and guards Git steps. Script-only watch mode and a shared HTTP server.

Pi extension that audits rpiv-todo board drift every 10 agent loops using TypeSafe's jev model, injecting corrective nudges when the agent wanders off-task

GPT teacher consults for DSH: stateless one-shot codex teachers behind a hard per-task consult budget, a read-only sandbox and a deterministic prefilter.

Comparing LLM-as-judge vs TypeSafe Jev for agent guardrails: same rules, same agent, measured on cost, latency, calibration and coverage.

Keep skill catalogs outside the main LLM context. Jev selects relevant skills through one read-only MCP tool.

Jev-powered decision skills for Claude Code and Codex. Opt-in, advisory, fail-open.