{
  "id": 16149855,
  "title": "Hy Memory 2.0: Tencent's Open-Source Model That Only Remembers",
  "url": "https://urgent.news/2026/10/23/hy-memory-2-0-tencents-open-source-model-that-only-remembers",
  "topic": "tech",
  "section": "Tech",
  "published": "2026-10-23T04:23:03.000Z",
  "source": {
    "name": "Dev.to",
    "slug": "dev-to",
    "url": "https://dev.to/neuraitool/hy-memory-20-tencents-open-source-model-that-only-remembers-4o8b"
  },
  "original_language": "en",
  "account": "On 15 October 2026, Tencent introduced Hy Memory 2.0, an open-source model designed to focus solely on managing an AI agent's memory. This release aims to solve the issue of AI agents forgetting information when a session is closed by offering a three-layer solution: Hy-Memory-30B-A3B, Apache 2.0 licensed and hosted on Hugging Face, along with a Python SDK for easy integration. The framework divides memory into three distinct types: chat memory, working memory, and coding memory, with diff chains tracking the reasons behind changes rather than just the changes themselves. MemHub, a local-first application, ensures authorized history is shared across various AI tools, allowing different agents to access each other's memories. Tencent's benchmarks show a 55.49% macro average in memory benchmarks, slightly outperforming Claude Opus 5's 54.62%. The release's key strengths include a permissive license, a small inference footprint, and the absence of competing open-source models specifically designed for memory management. This unification of memory management within a specialized model allows larger frontier models to allocate more tokens towards thinking, rather than remembering.",
  "summary": "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)…",
  "key_points": [
    "Tencent released Hy Memory 2.0 on 15 October 2026",
    "Model focuses solely on managing AI agent memory",
    "Three-layer solution includes chat, working, and coding memory"
  ],
  "editors_take": "By offloading memory management to a specialized open-source framework, developers can finally allow larger frontier models to prioritize reasoning and thinking over the heavy computational burden of long-term information retention.",
  "illustration": null,
  "coverage": {
    "outlets": 1,
    "also_reported_by": []
  },
  "ai_generated": true,
  "disclaimer": "Summaries, key points and the editor’s take are written by software from other outlets’ reporting and may contain errors — always check the linked original."
}