A high-performance content filtering userscript for X (Twitter), combining instant local rules with Jev (TypeSafe System One) semantic decisions to block spam and hidden promotions with sub-100ms latency.
Local & offline models — page 14
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.
Real-time Super Mario game autonomously controlled by TypeSafe AI's "Jev" System One Decision Architecture. Features sub-100ms decision loops, live prompt & probability telemetry, multi-provider support (OpenRouter Jev & Groq LPUs), and an offline neural simulator.
A local TypeScript demo comparing Zod upgrades with TypeSafe Jev assessments.
A local second brain built on GBrain, with TypeSafe Jev for search ranking and page connections.
AI-assisted email, calendar, tasks and documents: TypeSafe Jev gives typed, probability-backed judgments; LLMs draft (OpenAI-compatible APIs, local models via Ollama/LM Studio, Claude Code, Codex); you approve every action.
Jev-style typed decisions (semantic ifs) from a local Ternary Bonsai 2 27B on Apple Silicon: one forward pass, no generation. Independent; not affiliated with TypeSafe/Jev.
0
Calibrated PR review gates powered by TypeSafe Jev: a GitHub Action, a local CLI, and an OpenCode plugin
Local browser playground for TypeSafe's Jev decision model via OpenRouter. Python stdlib only.
Watch Jev (TypeSafe) play heads-up No-Limit Hold'em, with decision probabilities on the side panel. Money/points scoreboard, offline CI, no secrets.
AI columns for CSV/JSONL files with TypeSafe's Jev — typed answers, confidence, review queue, resume and cost preview. Local-first, BYO key.
Winner-stays-on animal tournament refereed by Jev (TypeSafe System One): a local game to feel how fast typed decisions are. UI in Spanish.
Active-learning triage pipeline using TypeSafe Jev — route by confidence, log soft labels for local distillation
Japanese speech → local STT → Jev typed decisions → deterministic actions.
0
Local System One for typed decisions. Scores noul, choice, and score from option logits — never free JSON. TypeSafe-compatible POST /v1/systemone with layered routing: on-device LFM2.5 first, optional second encoder, cloud Jev only if local fails. Fine-tune on proprietary labels. Not official Jev.
Reproducing jev classifier API on top of llama.cpp
Agent memory that decides what to hydrate — local topology recall + TypeSafe Jev gates (not another dump-everything store).
0
Portable skills for coding agents: review changes, verify completion claims, and make typed decisions with Jev, local models, or your own server.
Chrome extension: collapse spam, bait, off-topic and AI-filler replies on X. Local rules + TypeSafe Jev, learns from what you hide.
Intercepts destructive shell commands before they run. ~2ms local fast-path, context-aware risk scoring via TypeSafe Jev, deterministic offline fallback. Single Rust binary for zsh, bash and fish.
Voice-driven UI command layer in the Jev style: speak mixer commands ("mute singer", "set reverb 25%") and the UI moves instantly. Jev-shaped decision interface (typed decision + confidence + threshold escalation), $0 local implementation now, TypeSafe Jev slottable later.
Score every Cognigy conversation against rubrics you write, using TypeSafe Jev instead of an LLM. CLI, local web UI, and an agent skill.
A small local HTTP service for TypeSafe AI's Jev through Vercel
0
Local-first visual decision debugger and regression testbench for TypeSafe AI Jev
Local-first skill router for coding agents. Inspired by TypeSafe Jev; optional swappable judge (not an official Jev product).