Open infrastructure for training, evaluating, and deploying System 1 decision models across language and multimodal backbones.
-
Updated
Nov 20, 2026 - Python
Open infrastructure for training, evaluating, and deploying System 1 decision models across language and multimodal backbones.
Non-autoregressive decision engine on ModernBERT (151M) with calibrated uncertainty (RLCD), TypeSafe AI Jev benchmark audit, and in-browser WebGPU playground
⚡ Millisecond System-1 judgement for every tool call in DeepSeek Harness — Jev-powered risk classification & evidence-gated auto-approval. Fail-closed by construction. dsh 生态第一个 System-1 决策插件
Real-time drone swarm autonomy simulation using Jev for fast System 1 reflex decisions and collision avoidance, with optional System 2 reasoning for strategic guidance
DoubleTakeBench: 525 evidence-based judgment questions from coding-agent trajectories for evaluating System 1 models and LLMs.
⚡ 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
Jebadiah, an open System One decision model: trainer, data builders, evals and every run record
Portable System-1 decision layer for agent harnesses with host-owned routing, receipts, replay, and fail-open integrations.
Local Hybrid System-One Decision Engine (JevCompat 32/32 MUST, AnyJev L0 Prefill, StartLux Cascade, OpenJev-RLCD² Trainer, Zero-Shot AI Safety Guardrails)
Fast System-1 Decision, Arbitration & Safety Engine for Autonomous AI Agents (Powered by TypeSafe Jev)
System 1 for your coding agent: cut token use by deciding, not generating.
The first screen-time app built on Kev and Jev. Local-first on Apple silicon for free & privacy. Blocks the mechanism (Shorts, feeds, livestreams), not the site or app.
POK-Agent: a Windows computer-use AI agent. A large model plans (System 2) and a small fast model acts on screen (System 1: JEV or local Laya). Repeated tasks become muscle memory, so the big model is called less every time. Local-first, voice and vision, Rust + Tauri, open source.
Fast, calibrated System-1 decisions (Jev/Laya-style) on your NPU/GPU, plus per-prompt skill & MCP tool leasing that cuts agent context ~99%.
Multilingual, non-autoregressive System 1 decision model.
High-throughput native C# .NET 10 System-1 discrete decision & policy engine. Sub-millisecond non-autoregressive decision primitives (Choice, Noul, Score) with calibrated confidence in bare-metal GPU & unified APU memory.
Laya System-1 typed decisions for Hermes Agent — fast local triage, classification, and risk flags
A.N.S.W.E.R.R. — The Zero-Latency Reflex AI. Bridges deliberative language models with werr's zero-memory procedural boundary engine. Instant, typed decisions in <1ms.
Three-stage System-1 / System-2 cognitive router (Triage -> Modulation -> Call) for Hermes Agent using Microsoft-Decision-1.1 on Foundry and GitHub Copilot models
To associate your repository with the system-1 topic, visit your repo's landing page and select "manage topics."