Engram 用分组/主题/作用域结构化记忆,解决 AI 记忆混乱问题

Most memory systems don’t actually organise memory. They only accumulate it… And that’s where th...

精选理由

做 AI 应用尤其是编程助手或对话系统的团队,记忆混乱是常见痛点——Engram 的结构化方案直接解决了检索噪声和跨会话污染,值得点开看看怎么落地。

AI 摘要

Weaviate 发布 Engram,一种结构化记忆系统,将记忆组织为分组、主题和作用域,而非简单累积。分组定义用例边界,主题指定提取的信息类型,作用域限定记忆归属(项目级、用户级、会话级)。这解决了传统记忆系统因无结构导致的跨用户污染、跨会话干扰和检索噪声问题。例如,编程助手可分离仓库级、用户级和会话级记忆,提升检索清晰度。Engram 通过异步管道处理原始输入,并利用 Weaviate 的多租户保持边界完整。

原文 · Weaviate

Most memory systems don’t actually organise memory. They only accumulate it… And that’s where th...

Most memory systems don’t actually organise memory. They only accumulate it… And that’s where things start to break. When memory has no structure, everything gets mixed together: - One user can affect the wrong memory boundary - One session can pollute the next - One use case can contaminate a completely different workflow - Retrieval gets noisier over time instead of sharper That’s not memory. That’s blob storage with hope. Engram takes a stricter approach. It organises memory into **groups**, **topics**, and **scopes**. - Groups define the use-case boundary by combining the topics you care about with the pipeline that processes them. - Topics define what kind of information should become memory, because Engram only extracts memories that match your configured topics. - Scopes define who or what that memory belongs to, including project-wide, user-scoped, and property-scoped boundaries. So instead of dumping everything into one shared memory pool, you can model memory the way your applications would work. A coding assistant, for example, could separate: - Repo-level memory like code architecture - User-level memory like personal preferences - Session-level memory like the current conversation summary Same memory system. Different boundaries. Much cleaner retrieval. Also, Engram processes raw inputs into maintained memory through async pipelines that extract memories, reconcile them with existing ones, and commit the final results. Weaviate’s multi-tenancy keeps boundaries intact, and the structure keeps retrieval reliable. Because memory only becomes useful when it has structure. Learn more: weaviate.io/blog/engram-de… Get started: console.weaviate.cloud/signin?utm_sou… 💬 0 🔄 3 ❤️ 10 👀 340 📊 3 ⚡