Sub-100ms security gate for AI agent tool calls, powered by TypeSafe's Jev (System-1) decision model. Single-request Choice/Noul/Score evaluation, dual-factor blocking matrix, calibrated-confidence routing, fail-closed parsing, zero-config local fallback. LangChain-ready.
Local & offline models — page 5
Local alternatives and on-device decision models that follow the System One interface, plus shims for existing Jev clients.
368 active projects match this task, ordered by traction.
Jev Decisions Plugin for Hermes (and other AI Agents): tool risk reviews, human approval recommendations, evidence checks, a local decision journal, local decision supervision, and learned corrections.
AI life-and-civilization simulation: TypeSafe Jev makes every decision (typed, probabilistic, auditable); LLMs plan — OpenAI-compatible APIs, local models (Ollama, LM Studio), Claude Code, Codex.
3
Private Mac voice diary: local Parakeet transcription, Jev sorting, Notion library
Run jev-browser on a fully local JEV-style decision engine (no cloud API). Warm-browser fork, VRAM guard, measured benchmarks, run traces.
3
Fast Rust CLI for TypeSafe Jev: typed decisions, offline linting before you pay
Topic memory for LLM agents — edited, not accumulated: a topic keeps the starting question, conclusion, impact and dependencies; process is not memory. OKF bundle for dsh, local-first, git-traceable, budgeted LLM-free injection.
2
Ctrl+F that finds by meaning - highlights the sentence you meant, with receipts. Extension + local helper + playground (early scaffold).
A decision layer for agent control flow — yes/no, choice and rubric questions answered from one token's probabilities, measured against labelled sets — with a Claude Code permission hook and a trainable local judge
Pi coding agent extension that shifts to the right LLM for each prompt, using a local (Laya) or remote (Jev) decision model to judge task difficulty.
A fast System One decision model (Jev or local Laya) picks which LLM answers each prompt: OpenAI-compatible Go gateway + decision benchmark
2
Local MCP server exposing TypeSafe Jev (System One decision model) as native Claude Code / Codex tools
Drop-in /v1/systemone proxy that shadows Jev with local decision models (Kev, Laya) and reports whether you can swap
2
Two System One models fight a real Doom deathmatch. Laya (322M, open weights, local MLX) vs Jev (TypeSafe hosted). Same state, same typed questions, same shield — only the model differs.
2
Watch Jev play Freedoom in a local dashboard. TypeSafe direct and Vercel AI Gateway, inspectable decisions, and bounded spending.
Local-first Markdown memory alignment and source-linked search with optional Jev judgments
MCP-first toolkit for TypeSafe/Jev — the System One decision model. One stdio server (jev mcp) serves any MCP-capable harness, backed by one local event log and Prometheus impact metrics you can scrape into your own Grafana.
Distill a repeated Jev classification task into a local model, on the fly — same answers, your hardware.
Hands-on demos for TypeSafe's Jev (System One) model: six runnable examples and four field notes. Runs offline with no API key; samples/ holds real measured output from jev-1.13.0.
Offline $0 decision layer for coding agents: Choice/Score/Noul primitives, BELKI confidence gatekeeper, ultra-planning, red-teaming, research and RLVR self-improvement -- as an MCP server + CLI + Claude Code skill.
2
Text/PDF - File categorization and sorting with Typesafe AI Jev or local calibrated decision model
Watch TypeSafe Jev make highway driving decisions. Includes live API and offline gameplay previews.
2
Train lightweight language backbones for typed decisions and candidate probabilities. CE/Brier training, evaluation, and an offline end-to-end demo.
2
Alert triage as a UNIX filter: JSONL security alerts in, typed decisions out. Runs on TypeSafe Jev or a local model; policy routing stays in code.