Local and open-weight AI

Hy-Memory-30B-A3B: Attributed Reinforcement Learning for Long-Term Memory Writing

Observed ; updated .

Hy-Memory-30B-A3B is a compact long-term-memory writer trained across Mem0, MemOS, and Hy-Memory to decide what to retain and how to update persistent memory. It reported top results on all evaluated memory harnesses, including held-out EverMemOS, with a higher macro average than Claude Opus 5.

Sources

Reference: Anthropic

Why it matters
A unified, compact writer can lower serving costs and improve long-term memory quality across established memory frameworks.
Who is affected
Developers building language-model applications that need persistent memory beyond a context window may benefit from a single writer that works across multiple memory frameworks.

Model facts

Only what a source states is shown here. Hardware fit is never worked out from the size of the weights.

Licence
apache-2.0
Weights
https://huggingface.co/tencent/Hy-Memory-30B-A3B
Formats
No formats stated.
Runtimes
Transformers

Figures

No figures stated by a source. Memory and speed needs are not estimated here.