Local & offline models — page 9

Keep Claude Code as your architect and route the token-heavy typing to a local GPU or a cheap API tier -- without leaving your session.

Form builder where a System 1 model (TypeSafe Jev or local Laya) picks the best shadcn input for each field

Detect reviewable procurement signals in French local deliberations before a matching BOAMP notice appears.

Local-first hybrid RAG: traditional vs Jev-style (System One) pipelines over your own documents — with a built-in benchmark lab (6 scenarios, 48 questions, independent LLM judge). Hybrid won +8.4pp correctness at identical cost.

Local-first SEC 8-K research lab: score filings point-in-time with Jev, OpenAI or local LLMs, and label which results can count as evidence. Never places orders.

One-click System One local inference API server

local jev equivalent designed for llama.cpp and qwen 3.8 27B

Open emulator of TypeSafe's Jev API on open models, plus a paired benchmark of local and hosted models against Jev

Local judge first, cloud Jev second: a privacy-first request router (llama.cpp + TypeSafe Jev)

Local computer use on macOS with Laya decisions — read any window's Accessibility tree, let a local System One model pick the control, execute via cua-driver. No screenshots, no vision, $0. Sibling of laya-browser-agent.

No project description available.

Hooks and MCP that make Claude Code, Claude Desktop and Codex delegate decisions to TypeSafe JEV through a local gateway.

Sniff your Markdown drafts against house rules with local regex checks and optional AI judgment calls.

⚡ JEV vs LAYA · Next-Gen AI Tetris Duel Benchmark Platform (TypeSafe Jev vs Local GPU ModernBERT) with React-Bits UI/UX

Route Claude Code and Codex turns with local Laya — $0, no key, nothing leaves the machine

Local-first ntfy -> TypeSafe Jev -> Hermes notification gate

Minimal Jev judgment core for Pi and other TypeScript apps: noul/choice/score across TypeSafe, OpenRouter, Cloudflare, Vercel, and local llama-server (JevK5)

Open-source Codex Skills collection — featuring Jev-powered skill routing for large local catalogs.

Ultra-low latency System One decision routing & 3-way benchmark arena (Rule Engine vs. Local SLM vs. Cloud LLM) inspired by TypeSafe Jev primitives.

Jev vs Laya on Bulgarian: two System One models suggest a category for each blog post. A local BgGPT names new topics.

Local-first, multilingual System One decision engine — ultra-fast, non-autoregressive, calibrated. Speaks the Jev /v1/systemone protocol.

Local Codex task triage with human-reviewed archiving and optional Jev analysis

No project description available.

A local Jev-compatible decision engine powered by a 1.16 GB quantized 8B model.