| Name | Modified | Size | Downloads / Week |
|---|---|---|---|
| Parent folder | |||
| README.md | 2026-04-03 | 708 Bytes | |
| v0.2.0 -- Omni-SimpleMem_ Multimodal Memory source code.tar.gz | 2026-04-03 | 55.1 MB | |
| v0.2.0 -- Omni-SimpleMem_ Multimodal Memory source code.zip | 2026-04-03 | 55.2 MB | |
| Totals: 3 Items | 110.3 MB | 2 | |
What's New
🧠Omni-SimpleMem: Multimodal Memory
SimpleMem now supports text, image, audio & video memory.
- +411% on LoCoMo F1 over previous baselines
- +214% on Mem-Gallery F1
- 5.81 q/s retrieval throughput (3.5x faster)
- Built on three principles: Selective Ingestion, Progressive Retrieval, Knowledge Graph Augmentation
Other Changes
- README restructured with parallel SimpleMem (text) + Omni-SimpleMem (multimodal) organization
- Added Roadmap for upcoming multimodal infrastructure (cross-session, MCP, Docker)
- All 13 language READMEs updated
- Bug fixes and stability improvements
Full Changelog: https://github.com/aiming-lab/SimpleMem/compare/v0.1.0...v0.2.0