Typed decisions with TypeSafe's Jev, the first System One model
⚡ Foq — the FREE, local, open-source alternative to Jev. Typed System 1 decisions in ~25 ms — no waitlist, no cloud, no per-token cost. foq.fr
System1 AI web testing with deterministic replay and self-healing scripts.
The calculator software for WacOS/BaSYS. Part of the WacOS operating system project.
Not an LLM. Teach bounded decision skills from examples or observed APIs, validate, then run and save them locally. Optional MLX acceleration.
Paseo plugin that routes each message to a preset on Codex, Claude, OpenCode, or any other installed provider.
A TypeScript library that answers a decision question with a probability distribution over every option, using any existing LLM
Hybrid System 1 (Laya 33ms fast reflex) + System 2 Autonomous Plan-to-Code Orchestrator
The first fully systematic AGI agent browser. browser automation at machine speed.
A general-purpose AI decision model taught to play chess. Laya (Convai Innovations, ModernBERT-large, 421M, Apache 2.0) was never trained on chess. LayaChess fine-tunes it on DeepMind's ChessBench and wraps it in a Leela-style search engine.
JEV-Local: System-1 decision engine for local LLMs. Mimics TypefAI JEV: structured choices only, no chatter, calibrated confidence. Works with Ollama, vLLM, llama.cpp, LM Studio.
A System One decision model finetuned on persian data.
jev-laya-system-1: Security & calibration middleware for System 1 AI models like jev & laya
High-speed, zero-token System 1 decision gateway for AI coding agents
A NeuralNetwork architecture embedding a JEPA-style predictive-coding System 1 router inside a System 2 transformer
System1Bench: Benchmarking Jev-Style Decision Models. Reproducible Laya baselines, typed decisions, bilingual evaluation, OOS detection, safety and robustness.
To associate your repository with the system1 topic, visit your repo's landing page and select "manage topics."