{"apiVersion":"v1","taxonomyVersion":1,"generatedAt":"2026-10-29T17:25:55.358Z","data":{"recordId":"wsa_8zf9vczg9647","score":1,"confidence":"high","capped":false,"capReason":null,"sources":[{"n":1,"url":"https://huggingface.co/tencent/Hy-Memory-30B-A3B","publisher":"Hugging Face","authority":"owner-controlled","verification":"verified","lastRetrievedAt":"2026-10-28T00:51:38.871Z","detectedPublishedAt":"2026-10-15T09:52:00.000Z","rights":"original"},{"n":2,"url":"https://github.com/Tencent-Hunyuan/Hy-Memory","publisher":"GitHub new repositories","authority":"owner-controlled","verification":"verified","lastRetrievedAt":"2026-10-28T00:51:38.871Z","detectedPublishedAt":"2026-10-15T13:06:56.000Z","rights":"original"}],"claims":[{"id":"a18c4af0-058b-4f69-99a8-2fabe8fec432","kind":"availability","statement":"Hy-Memory-30B-A3B is open-sourced on Hugging Face.","citations":[{"source":2,"supportProbability":0.98,"supports":true,"quote":{"text":"* *[new]* π₯π₯π₯ **[2026-10]**: π **Open-sourced** quantized **FP8** (**[Hy-Memory-30B-A3B-FP8](https://huggingface.co/tencent/Hy-Memory-30B-A3B-FP8)**) and **GGUF** (**[Hy-Memory-30B-A3B-GGUF](https://huggingface.co/tencent/Hy-Memory-30B-A3B-GGUF)**) versions ofβ¦","rights":"original"}}]},{"id":"8a2c4441-298e-4afc-b4fa-cf62f5f0b3cf","kind":"capability","statement":"The model is trained specifically for high-precision long-term memory extraction and conflict reconciliation.","citations":[{"source":2,"supportProbability":0.98,"supports":true,"quote":{"text":"> **TL;DR:** Trains a 30B-A3B MoE model via attributed reinforcement learning specifically for high-precision long-term memory extraction and conflict reconciliation.","rights":"original"}}]},{"id":"b80d7232-2ed0-49b6-baca-318663783bba","kind":"capability","statement":"It is a 30B-A3B MoE model.","citations":[{"source":2,"supportProbability":0.97,"supports":true,"quote":{"text":"> **TL;DR:** Trains a 30B-A3B MoE model via attributed reinforcement learning specifically for high-precision long-term memory extraction and conflict reconciliation.","rights":"original"}}]},{"id":"c483f6cf-243f-41ff-a3f1-cf046fd6cd6a","kind":"recommendation-relevant","statement":"Its technical report describes attributed reinforcement learning for long-term memory writing.","citations":[{"source":2,"supportProbability":0.97,"supports":true,"quote":{"text":"* *[new]* π₯π₯π₯ **[2026-10]**: π **Open-sourced** **[Hy-Memory-30B-A3B](https://huggingface.co/tencent/Hy-Memory-30B-A3B)** on Hugging Face along with its [technical report](https://arxiv.org/abs/2610.22196) on attributed reinforcement learning for long-termβ¦","rights":"original"}}]},{"id":"15c2a13d-1a92-4a13-9341-a5ef38ebcfa6","kind":"capability","statement":"The model is designed to execute the write path inside external memory frameworks.","citations":[{"source":1,"supportProbability":0.97,"supports":true,"quote":{"text":"**Hy-Memory-30B-A3B** is a compact long-term-memory writer model (~3B active parameters) developed by Tencent Hunyuan to execute the write path inside external memory frameworks.","rights":"original"}}]},{"id":"454bc753-cced-4e43-8184-460f4caa44a1","kind":"capability","statement":"It decides what information to retain, how to represent it, and how new evidence should update persistent memory.","citations":[{"source":1,"supportProbability":0.97,"supports":true,"quote":{"text":"It directly replaces the general-purpose LLM inside **Mem0**, **MemOS**, and **Hy-Memory** (covering Chat, Working, and Coding scenarios), deciding what information to retain, how precisely to represent it, and how new evidence should update the persistent memory bank.","rights":"original"}}]},{"id":"c654050d-dfcd-4227-a1f5-314195e11913","kind":"availability","statement":"Model weights, configuration, and model card are available on Hugging Face.","citations":[{"source":1,"supportProbability":0.95,"supports":true,"quote":{"text":"- **Model Weights, Configuration, and Model Card:** [https://huggingface.co/tencent/Hy-Memory-30B-A3B](https://huggingface.co/tencent/Hy-Memory-30B-A3B)","rights":"original"}}]},{"id":"53e5f4cb-cbf5-4895-9a69-10a553ba0ed2","kind":"deployment","statement":"The model can be deployed with vLLM and called through an OpenAI-compatible API.","citations":[{"source":1,"supportProbability":0.98,"supports":true,"quote":{"text":"Deploy the model with vLLM (tested with v0.31.0) using `--served-model-name hy-memory`, then call the OpenAI-compatible API.","rights":"original"}}]},{"id":"cd32ad5a-e133-4199-9f06-de309b5be6b3","kind":"recommendation-relevant","statement":"It is intended to replace the general-purpose LLM inside Mem0, MemOS, and Hy-Memory.","citations":[{"source":1,"supportProbability":0.97,"supports":true,"quote":{"text":"It directly replaces the general-purpose LLM inside **Mem0**, **MemOS**, and **Hy-Memory** (covering Chat, Working, and Coding scenarios), deciding what information to retain, how precisely to represent it, and how new evidence should update the persistent memory bank.","rights":"original"}}]}]},"nextCursor":null,"license":{"catalog":{"name":"CC BY 4.0","spdx":"CC-BY-4.0","url":"https://creativecommons.org/licenses/by/4.0/","attribution":"wowsuchai","attributionUrl":"https://wowsuchai.withglint.app","covers":["catalog metadata","classifications","generated summaries","feed event metadata"]},"excluded":{"covers":["source quotations","linked source content"],"terms":"Not licensed by wowsuchai. Source quotations and linked source content keep their original rights."}}}