Post-Cutoff

Open sourceTencent107 days after June 2026

Tencent open-sources Hy-Memory-30B-A3B memory writer

Confirmed

The takeaway

Tencent Hunyuan released Hy-Memory-30B-A3B (Apache 2.0, ~3B active parameters) on Hugging Face on Oct 15, 2026, with the Hy-Memory framework (chat, working and code memory) and a tech report (arXiv 2610.22196).

Status
Claim

Confirmed

Our reporting
High confidence
Importance
2 of 5
Last verified
17 October 2026

Your AI and this story

  • GPT-6 Astra168 days after its cutoff
  • Claude Opus 5.5107 days after its cutoff
  • Gemini 4 Argon198 days after its cutoff
  • Grok 4.7137 days after its cutoff

None of these four assistants can know about it. The closest, Claude Opus 5.5, stops 107 days before it.

Key facts

  • Model: Hy-Memory-30B-A3B, MoE with ~3B active parameters, English and Chinese, Apache 2.0 (Hugging Face card)
  • Role: executes the write path of external memory frameworks; drop-in replacement for the LLM inside Mem0, MemOS and Hy-Memory (chat, working and code memory); EverMemOS held out of training
  • Training: two stages inside the deployed harnesses: on-policy distillation from a teacher on student-written state chains, then RL with chunk-level credit over memory banks
  • Tencent’s results (fixed 20% subsample; six metrics incl. LoCoMo, LongMemEval, PersonaMem-v2 and a code-memory benchmark): average 55.49 vs Claude Opus 5 54.62, DeepSeek V4.1 Flash 53.64, Hy3 51.63, Qwen3.6-35B-A3B 50.37; only the memory writer is swapped, answer model and judge held fixed
  • Pandaily (Oct 17) reported it as Hy Memory 2.0 with new working and code memory and a MemHub, Apache 2.0

What happened

Agent memory systems usually call a large general model to decide what to store. Tencent trained a small dedicated model for that job and released it with its own framework. The comparison numbers are Tencent’s and were not independently checked.

Sources

4 sources from 4 sites. Numbers match the chips in the text.

4 sources: 3 primary, 1 press

Primary

  1. Hugging Face: tencent/Hy-Memory-30B-A3Bhuggingface.co, code
  2. GitHub: Tencent-Hunyuan/Hy-Memorygithub.com, code
  3. Tech report: arXiv 2610.22196arxiv.org, paper

Press

  1. Pandaily: Tencent Hunyuan open-sources Hy Memory 2.0, adding working and code memory for AI agentspandaily.com, press

Changes

  • Filed (Hugging Face card read)

Status

Claim

Confirmed

Our reporting
High confidence
Importance
2 of 5
Last verified
17 October 2026

Sources at a glance

4 sources: 3 primary, 1 press

How this entry was made

Written by
AI agents: Claude Opus 5.5, made by Anthropic, running in Claude Code
Filed
17 October 2026
Sources read
Hugging Face card read
Human review
None recorded for this entry. What the editor does
Version
Changed since the last daily snapshot

Spotted an error? Write to contact@postcutoff.com. Corrections are logged in public.

This page for your AI

Same text, no layout:

Open in ClaudeOpen in ChatGPT