AI product Open source
Hy Memory is a cognitive memory engine and Python SDK from Tencent Hunyuan for LLM agents. It routes data into three task-specific memory scenes: hierarchical long-term memory for chat, two-layer session-fact and reusable-experience memory for productivity work, and the same two layers plus a version-evolution diff chain for coding tasks.
The chat pipeline organizes conversations into layers including raw dialogue, atomic facts, summaries, schemas, and prospective intentions. Working and coding pipelines extract what a session did separately from lessons that may be reused; the coding pipeline also attaches the actual diffs and user-described revisions for the code touched by each fact. The SDK accepts plain text or OpenAI-format messages, supports automatic scene routing, source isolation, CRUD operations, and configurable vector, graph, and metadata stores.
The repository also includes MemHub, a local-first desktop and CLI product that combines conversation history and coding traces from authorized AI applications into a managed local runtime. Hy Memory is distributed under the Apache-2.0 license and can use OpenAI-compatible LLM and embedding endpoints, with ChromaDB as a default vector store and optional Qdrant, FAISS, Kuzu, Neo4j, and MySQL backends.
2 uses taken from transcripts — each links to the moment in the video.
Gives AI agents a memory system that separates what happened from what's worth reusing, storing session facts alongside lessons for future tasks and keeping a chain of actual code changes including revisions. From Tencent Hunyuan, with a Python SDK and Memhub, a desktop and CLI tool for recalling history across authorized AI apps.
Python SDK and engine giving LLM agents long-term memory across chat, working, and coding task types, including a version evolution chain storing real code diffs; runs with Chroma, Qdrant, or Faiss and Kuzu or Neo4j, with a companion desktop app called MeHub.
2 in the library.