跳到正文
DEV Community· NeurAITool·· 2026-10-23AI 評分62

騰訊開源 Hy Memory 2.0 記憶技術堆疊,專責管理 AI Agent 記憶

Hy Memory 2.0: Tencent's Open-Source Model That Only Remembers

AI 導讀

騰訊於 2026 年 10 月 15 日推出開源記憶系統 Hy Memory 2.0,包含記憶寫入模型、Python SDK 框架及 MemHub。Hy-Memory-30B-A3B 是 30B 參數、約 3B 啟用的 MoE 模型,採 Apache 2.0 授權;框架將記憶分為聊天、工作和編碼三類,MemHub 可同步不同 AI 工具中經授權的歷史。

正文

NeurAITool

AI agents forget. Close the session and your preferences, project setup and half your instructions are gone. Tencent's answer, released on 15 October 2026, is not a bigger model — it's a specialist: Hy Memory 2.0, an open-source stack whose only job is deciding what an agent should remember.

What's in the release

Three layers:

  • Hy-Memory-30B-A3B — a 30B-parameter MoE model (~3B active) purpose-trained for the "memory-write" step: what to keep, how to store it, and how new facts overwrite old ones. Apache 2.0, on Hugging Face.
  • The framework — a Python SDK (pip install hy-memory) that splits memory into three types instead of one chat log: chat memory, working memory, and coding memory — diff chains that keep why a change was made, not just what changed.
  • MemHub — a local-first app that syncs authorised history across your AI tools, so one agent can recall what another did. No Windows build yet, and the day-one installer had gaps.

About those benchmarks

Tencent reports a 55.49% macro average across memory benchmarks vs 54.62% for Claude Opus 5. Read that as parity, not a rout — these are Tencent's own benchmarks, not independently replicated. The solid facts are the license, the tiny inference footprint, and that nothing else open-source is purpose-built for this slot: the model drops into Mem0 or MemOS as the memory-writer without changing your storage or retrieval.

The bigger shift

October's releases keep unbundling the monolith: DeepSeek's V4.1-Flash for speed, Meta's Muse Wonder splitting memory and focus, and now Tencent offloading remembering entirely. A 3B-active specialist doing the bookkeeping means your frontier model spends its tokens thinking.

Full breakdown with pros, cons and the honest caveats: Hy Memory 2.0 on NeurAITool

來源:DEV Community · dev.to