Local daemon serving the pinned TypeSafe Jev wire surface, backed by a configurable OpenAI-compatible model.
Local & offline models — page 11
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.
JimmyJenk: a local harness for Jev-style System-One decisions (Noul / Choice / Score) from any LLM's token logprobs. vLLM + llama.cpp backends, playground, calibration and robustness evals.
Semantic classification of Outlook, Gmail and IMAP mailboxes with Jev (TypeSafe) — one category per message, preview by default, cost-capped, local. C# / .NET 10, MIT.
Private, browser-only analytics dashboard for your Netflix export. 12 tabs, local parsing, opt-in AI.
0
Local typed decisions on ARM: a TypeSafe-compatible System One API for Raspberry Pi. llama.cpp Q8 backbone + torch decision head; 4.8x faster than the official SDK, decisions identical.
Experimental local-first macOS voice automation using whisper.cpp, TypeSafe Jev routing, typed actions, and optional Ollama generation.
Inspect failures, retries, and skipped jobs behind a green GitHub Actions run. Local evidence reports with optional Jev classification.
0
Search your Mac screen history. Native SwiftUI app with automatic Jev search, your own API key, and local fallback.
0
Local MCP server giving coding agents Jev-backed filters: jev_grep, jev_rank, jev_search
Jev-powered model router - measured 77.8% token-cost savings on real workloads. Local-first, cloud when it earns its cost. No accounts, no keys.
Bench of typed decision models: Jev vs OpenJev vs Laya, small local LLMs and cheap hosted LLMs on the same zero-shot classification tasks, in English and French.
0
Assistant vocal français pour macOS : Whisper local + décisions Jev, actions sûres, interface Liquid Glass.
Record instrumented workflow failures, replay tool traces offline and minimize response fixtures.
A Jev practice catalog and local-first Agent skill router: map recurring logs to reusable decisions, tools, and workflows.
The Intelligent, Off-Script AI Teleprompter powered by TypeSafe Jev and Local Voice Tracking
Local-first classroom signals with two-pass Chinese ASR, structured TypeSafe Jev judgments, and auditable teacher-private interventions.
Stranger danger for AI agents: detect prompt injection in content your agent fetches, before it reads it. Runs on TypeSafe's Jev System One model by default; local and keyword detectors included. Benchmarked, failures published.
0
A wrapper that gets more value out of TypeSafe's JEV model: transcript compaction, cost-control modes, and a local usage ledger for Claude Code and Codex.
Jev Guard is a real-time Windows process monitoring application powered by TypeSafe's Jev AI model. It tracks newly launched processes, logs event metadata (paths, command lines, and parent processes) to a local SQLite database, and classifies risk levels—labeling events as benign, suspicious, or malicious on a live interactive dashboard.
Host a local two-truths-and-a-lie party game where Jev is a finite-choice guest.
0
Ask questions about your documents and get answers with probabilities. Windows & Android app for Jev (TypeSafe AI) via Vercel AI Gateway — reads whole books, PDFs, Word and images, with on-device OCR. Bring your own key.
Same maze, same rules, N decision backends. A zero-key, zero-dependency arena that measures Jev / LLM / local decision models on speed, cost, calibration error (ECE) and invalid-output rate.
Local web app for TypeSafe Jev decision probabilities
Heads-up no-limit Texas hold'em against TypeSafe Jev. The local engine deals and settles; Jev answers typed questions, and code composes the bet.