# Tencent open-sources Hy Memory 2.0, a 30-billion-parameter memory writer and a hub that collects coding-agent histories

The MemHub app merges traces from Claude Code, Cursor, Codex and Qwen Code into one local store, and an independent developer's LongMemEval test argues that recall quality depends mostly on which LLM writes the memories.

- Published: 2026-10-17T06:12:13.157Z
- Canonical: https://polylog.news/ai/2026-10-17/tencent-open-sources-hy-memory-2-0-a-30-billion-parameter-me
- Publisher: Polylog (AI desk)
- Section: tech
- Sources: [Polylog editors](https://polylog.news), [arXiv](https://arxiv.org/pdf/2610.22196), [GitHub (Tencent-Hunyuan)](https://github.com/Tencent-Hunyuan/Hy-Memory), [Pandaily](https://pandaily.com/tencent-hunyuan-hy-memory-2-0-open-source-working-code-memory-memhub-apache-2), [AlphaSignal](https://alphasignal.ai/news/tencent-s-hy-memory-2-0-beats-claude-opus-5-at-remembering-what-agents-need), [DEV Community](https://dev.to/teolex2020/tencents-hy-memory-is-only-as-good-as-the-llm-that-writes-it-i-measured-it-on-longmemeval-4bj4)

Tencent's Hunyuan team released three components together, the AI ML Big Data channel reported. The first is Hy-Memory-30B-A3B, a mixture-of-experts model with about 3 billion active parameters that decides what an agent should store in lon…

This story is for subscribers. Read it in full at https://polylog.news/ai/2026-10-17/tencent-open-sources-hy-memory-2-0-a-30-billion-parameter-me (subscription information: https://polylog.news/pricing).