English(EN) Hy Memory 2.0: Tencent's Open-Source Model That Only Remembers

腾讯发布 Hy Memory 2.0 以管理 AI 代理的记忆

作者 PulseAugur 编辑部 · [1 个来源] · 2026-10-23 04:23

腾讯发布了 Hy Memory 2.0，这是一个开源堆栈，旨在管理 AI 代理的记忆。该系统包括一个专门用于记忆写入的 30B 参数模型，一个将记忆分为聊天、工作和编码类型的 Python SDK，以及一个名为 MemHub 的本地优先应用程序，用于跨工具历史记录同步。尽管腾讯声称在记忆基准测试中与 Claude Opus 相当，但这些结果是其自行报告的。Hy Memory 2.0 堆栈旨在通过将记忆管理任务卸载给一个专门的、更小的模型来提高 AI 代理的效率。 AI

影响专门的记忆模型可以提高 AI 代理的效率并减少前沿模型的 token 使用量。

排序理由发布用于专门 AI 任务的开源模型和框架。[lever_c_demoted from research: ic=1 ai=1.0]

在 dev.to — LLM tag 阅读 →

AI 生成摘要 · Google Gemini · 来自 1 个来源。我们如何撰写摘要 →

本文如何被排名

Signal score: 3 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 发布用于专门 AI 任务的开源模型和框架。[lever_c_demoted from research: ic=1 ai=1.0]
Source corroboration: Single-source cluster; Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics: model release, product; Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance: High; Clearly on-topic for AI-industry coverage.
Story freshness: Same-day; Cluster formed today. Ranking reflects the current source set at time of score.

完整方法见我们的编辑标准。

报道来源 [1]

dev.to — LLM tag TIER_1 English(EN) · NeurAITool · 2026-10-23 04:23

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

<p>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 s…

本文如何被排名

报道来源 [1]

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

相关实体

相关话题