zensystemai/zengram

Zengram

多智能体AI系统的共享内存。

快速入门 • 工作原理 • 基准 • 适配器 • API文档 • 配置

将Claude代码中的事实存储在你的笔记本电脑上，从服务器上的自主代理调出，从另一个会话获取简报——所有这些都通过同一个内存系统。它诞生于一个生产环境，当时没有允许多个AI代理在不同机器间共享内存。

---

问题

你运行多个人工智能代理——开发用Claude Code，任务用自主代理。它们各自保持上下文，会话间忘记一切。当一个代理发现重要信息时，其他代理永远不会知道。

工作原理

打字记忆

事件是不可变的历史。事实按键上升——新事实取代旧事实。状态追踪当前状态。决策记录选择和推理。每种类型都有自己的生命周期、衰变规则和突变语义。

统一存储

Zengram

Shared memory for multi-agent AI systems.


Quick Start •
How It Works •
Benchmarks •
Adapters •
API Docs •
Config

Store a fact from Claude Code on your laptop, recall it from an autonomous agent on your server, get a briefing from another session — all through the same memory system. Born from a production setup where nothing existed that let multiple AI agents share memory across separate machines.

---

The Problem

You run multiple AI agents — Claude Code for development, autonomous agents for tasks. They each maintain their own context and forget everything between sessions. When one agent discovers something important, the others never learn about it.

How It Works

Typed Memory

Events are immutable history. Facts upsert by key — new facts supersede old ones. Statuses track current state. Decisions record choices and reasoning. Each type has its own lifecycle, decay rules, and mutation semantics.

Unified Storage

Every memory lives in a single Postgres database: pgvector (HNSW) for semantic vector search and structured tables for queries, entities, and full-text search. Get both “find memories similar to X” and “give me all facts with key Y” from the same system — one container, no separate vector service.