Jev Multi Agent

A reproducible lab measuring how several coding agents coordinate on one repository, plus Médula, a kernel that asks TypeSafe Jev before every write whether a change collides with what the other agents are doing.

A Claude Code plugin that keeps agents honest: Claude lays work out as phases with a definition of done and a check, and whenever it tries to stop, Jevflow runs the checks and asks Jev whether the work is really done. Several agents can share one plan.

A Jev-powered multi-agent coding factory for OpenAI Codex: one engineering request is routed to a model and effort lane or decomposed into a task DAG, workers run in parallel, verification gates every change, and failures get classified instead of blindly retried.

A modular TypeScript framework for role-playing agents and autonomous game NPCs powered by Jev: principles are authored in natural language, Jev selects eligible actions and communicative intents, and the host applies world effects and composes dialogue. Ships Fog Harbor, a playable 2D AI-town demo.

An instrumented spatial predator-prey framework for studying communication and collective dynamics in AI agents, separating the evolving world, request scheduling, controller adapters, and experiment records. A case study reports a signals-on minus signals-off rabbit-abundance difference of -0.0095.

Alibaba's multi-agent platform, which implements native TypeSafe Jev classification through JevClassifierModel for binary, choice and score routing across agent pipelines. Python 3.11+, Apache-2.0, with a FastAPI agent service and web UI.