Local & offline models — page 6

Chimera: a local-first, human-controlled AI agent workspace. Apache-2.0 source beta.

Parallel web search for terminals and agents, with local Chromium and Jev-guided exploration.

Lints Jev requests before they are sent: offline checks for missing none-of-the-above options and broken state paths, then Jev itself for what structure cannot decide.

A token efficient, local LLM friendly agentic coding harness: a complete agent runtime (agent loop, tool pipeline, sandboxing, session persistence) with four front-ends — a Blazor web UI, a headless CLI, and JSON-RPC / ACP stdio servers for editors and automation.

Local-first chat agent that runs comfortably with small-context local LLMs (from 2B) without losing the original goal of a long conversation. Multi-window context with rollovers, SKILL.state runtime, memory carry-over, three-tier auto web search, and a stalled-session detector. Next.js + FastAPI + SQLite + LanceDB, packaged for Docker Compose.

Safe Python-like script node with a System One decision model: ask yes/no, choice, and score questions via TypeSafe AI's Jev API, with local GGUF LLMs as a fallback. Multiple inputs and outputs let one node handle math, logic, text editing, conditional routing, resolution selection, filename generation, and more.

Offline Jev token counting and request accounting for Node.js and Next.js. MIT TypeScript port of LabGuy94/jevtok.

Local playground and test bench for TypeSafe's Jev System One model: typed questions, calibrated-probability answers, and side-by-side comparison with an LLM baseline.

JEV and local LAYA for MCP. Typed decisions, bounded inference and durable decision records.

Open-source AI agent decision layer for Codex, Claude Code, Hermes, Antigravity and VS Code. TypeSafe Jev MCP routing, 38 recipes, local gates and receipts; optional Laya-MLX on Apple Silicon.

本地运行的手绘风格探索工具：借助 TypeSafe Jev 按主题筛选 261 条风格资料，并复制用于图像生成的提示词。 A local hand-drawn style explorer powered by TypeSafe Jev.

Self-contained showcases of JuL (Juste un LLM) — local typed decisions reproducing jevable.com ideas, running on the wemm-4b-4bit model.

Agent skill for writing programs with Laya and laya-cli — local typed decisions (Choice/Score/Noul), port of building-with-jev-skill to Laya

Fuses two System-1 decision models (Laya + Jev) into one auditable verdict — confidence-weighted fusion, disagreement escalation to a local adjudicator, append-only JSON decision logs.

Local retrieval without embeddings. Every answer comes back as the original passage with its coordinates (path:start-end), so a person or an agent can open the exact lines. No Embedding, Zero Cost, Fully Local.

Talk to your Mac and it acts before you finish the sentence. Jev (TypeSafe) + ElevenLabs + on-device Whisper.

极简现代 macOS 暗黑胶囊输入法：集成小狼毫 (Weasel) · 万象拼音海量词库与 400MB 语法模型 · TypeSafe Jev AI / Ollama · 图形化交互设置控制中心 (WebUI)

Go harness for Jev/Kev decision models: TypeSafe, Vercel AI Gateway, and in-process Kev via llama.cpp

Local MCP server for TypeSafe Jev typed decisions, with Codex integration

Speak a UI into existence: local whisper.cpp transcription → Jev (TypeSafe AI) → json-render → shadcn/ui. A voice-driven UI prototyper built on Next.js.

Local benchmark comparing TypeSafe Jev and Laya-MLX for structured issue classification

A fast, local-first gateway for aggregating and routing TypeSafe Jev model endpoints | 一款快速、本地优先的网关，用于聚合与路由 TypeSafe Jev 模型入口

JevCore Agent — local coding harness (Jev decisions, Guard hard policy, MCP + CLI)

AI text rewriting and document summarization with Jev checks for missing ideas and automatic repair. Local editor and CLI.