MemU is an agentic memory framework for LLM and AI agent backends. It receives multimodal inputs (conversations, documents, images), extracts them into structured memory, and organizes them into a hierarchical file system that supports both embedding-based (RAG) and non-embedding (LLM) retrieval.
MemU is collaborating with four open-source projects to launch the 2026 New Year Challenge. πBetween January 8β18, contributors can submit PRs to memU and earn cash rewards, community recognition, and platform credits. πJoin the community here: https://discord.gg/KaWy6SBAsx
| Feature | Description |
|---|---|
| ποΈ Hierarchical File System | Three-layer architecture: Resource β Item β Category with full traceability |
| π Dual Retrieval Methods | RAG (embedding-based) for speed, LLM (non-embedding) for deep semantic understanding |
| π¨ Multimodal Support | Process conversations, documents, images, audio, and video |
| π Self-Evolving Memory | Memory structure adapts and improves based on usage patterns |
MemU organizes memory using a three-layer architecture inspired by hierarchical storage systems:
| Layer | Description | Examples |
|---|---|---|
| Resource | Raw multimodal data warehouse | JSON conversations, text documents, images, videos |
| Item | Discrete extracted memory units | Individual preferences, skills, opinions, habits |
| Category | Aggregated textual memory with summaries | preferences.md, work_life.md, relationships.md |
Key Benefits:
- Full Traceability: Track from raw data β items β categories and back
- Progressive Summarization: Each layer provides increasingly abstracted views
- Flexible Organization: Categories evolve based on content patterns
MemU processes diverse content types into unified memory:
| Modality | Input | Processing |
|---|---|---|
conversation |
JSON chat logs | Extract preferences, opinions, habits, relationships |
document |
Text files (.txt, .md) | Extract knowledge, skills, facts |
image |
PNG, JPG, etc. | Vision model extracts visual concepts and descriptions |
video |
Video files | Frame extraction + vision analysis |
audio |
Audio files | Transcription + text processing |
All modalities are unified into the same three-layer hierarchy, enabling cross-modal retrieval.
Try MemU instantly without any setup:
π memu.so - Hosted cloud service with full API access
For enterprise deployment and custom solutions, contact info@nevamind.ai
| Base URL | https://api.memu.so |
|---|---|
| Auth | Authorization: Bearer YOUR_API_KEY |
| Method | Endpoint | Description |
|---|---|---|
POST |
/api/v3/memory/memorize |
Register a memorization task |
GET |
/api/v3/memory/memorize/status/{task_id} |
Get task status |
POST |
/api/v3/memory/categories |
List memory categories |
POST |
/api/v3/memory/retrieve |
Retrieve memories (semantic search) |