Jev ecosystem projects — page 12

Systematic software development framework for AI coding agents upgraded with TypeSafe Jev System One typed decisions

Snake auto-played by TypeSafe's Jev model: one System One choice per tick, legal moves and facts generated in code

Agent-ergonomic CLI for TypeSafe's Jev: fast calibrated judgments (pick, rate, check, rank, triage, guard) from the shell

Research design for a Jev-native agent system: tool integration, speculative parameter proposals, external helper logits Top-k proposals with Jev-controlled fallback ,decision-aware hierarchical memory, and dependency-aware replanning.Feature:Jev naturallanguage conversation prototype using external helper logits and dynamic Top-k token selection.

Jev-powered decision layer for DeepSeek Harness

Jev-powered relevance filtering and reranking for RAG in Python.

Screens an AI agent's tool calls before they run and tool results before the agent reads them. An MCP proxy plus a hooks adapter for a client's built-in tools.

Interactive TypeScript coding CLI powered by Jev typed decisions and constrained AST generation.

Community TypeSafe AI playground: 110 use cases, games, dilemmas and model challenges, with editable prompts, A/B comparisons and a mobile-friendly UI.

Fully customizable Advisor and Executor flow plugin for the Pi Coding Agent

Run Jev-style typed decisions locally on your Mac with low RAM usage and fast responses

an open-source, from-first-principles reconstruction of the ideas behind TypeSafe AI's Jev, written in pytorch

A Jev-powered resolver for agent harnesses to find deterministic commands and their context in a nested capability tree.

The decision layer for your Rails app. A Rails-native wrapper around TypeSafe's Jev System One API: typed, calibrated decisions in your control flow.

sort by meaning: order lines along a plain-English dimension, from pairwise comparisons judged by TypeSafe's Jev model

The first general-purpose System One agent for Jev

Super fast Jev like server, model agnostic, working with any OpenAI compatible endpoint

A Minesweeper benchmark for LLM agents. One identical board, up to nine models in parallel, one clock, one tool layer.

Evidence-backed knowledge graph construction with typed Jev relation decisions

The invalidation layer for AI memory. Every fact gets a lease; new evidence ends it. Built on TypeSafe Jev.

Run SemIf (Jev-style semantic-if decisions) on a CPU — no GPU. Reads typed option probabilities straight from an open model in one forward pass, plus a web UI.

Claude Code Stop hook that blocks an unverified done: reads the transcript for evidence, asks Jev once, fails open on everything else

Evidence-backed use cases, patterns, and guidance for building with Jev, TypeSafe AI's System One model. Every claim is labeled and sourced.