Agent memory management with decision models

Codex port of fast-jev-compaction that re-injects Jev-selected verbatim history after compaction; the author advises against using it.

TypeScript framework for role-playing NPCs: Jev picks actions and communicative intents, the host composes dialogue.

OMP extension keeping one endless chat as a summary tree, with five Jev judge gates for rules, prefetch, compression, tools and recall.

Research runtime where every agent step is a bounded typed decision, with a paged virtual option space over tools and memory.

Research runtime that lets a bounded decision model like Jev operate over large tool, memory and context spaces via a virtual option space.

Agent memory system where Jev or local Laya controls memory organisation, query routing, retrieval budgets and stopping.

Zilliz's cross-agent Markdown memory with an optional Jev reranker that asks yes/no relevance questions about retrieved chunks.

Production control plane for OpenClaw agents: Jev routes each Slack message to its task, with Temporal workflows, an evaluator and memory.

Android AI chat client and SillyTavern-compatible endpoint where Jev screens memories for relevance and serves as a judge tool.

Federated knowledge retrieval engine for agents that uses Jev to route queries to backends and re-rank evidence, with keyword fallback.

Ten runnable JavaScript lessons where Jev judges agent situations like memory conflicts and handoffs while code enforces explicit policy.

AI town simulation forked from a16z ai-town where Jev picks each agent's next legal move and an LLM handles dialogue and memory.

Agent context compactor where Jev scores transcript segments to keep verbatim or move behind a recoverable pointer.

Dry-run Solana paper trader where Jev picks one action per cycle from the venues actually reachable; code owns sizing and risk.

Independent experiments on Jev for search stopping, memory reranking and multi-hop relation selection, with stated limits.

X walkthrough of the Jev API followed by three demos: voice-controlled browsing, AI memory and YouTube preprocessing.