engram-rs
Memory engine for AI agents — time axis (3-layer decay/promotion) + space axis (self-organizing topic tree). Hybrid search, LLM consolidation. Single Rust binary.
engram-rs is a memory engine for AI agents that organizes knowledge along two axes: time (three-layer decay & promotion) and space (self-organizing topic tree). It intelligently promotes important memories, fades noise, and automatically clusters related knowledge, providing a more effective alternative to flat memory stores.
Features
Compatibility
Quick start
Use cases
Alternatives
Related searches
Comments
- OOaklyn WhiteApr 14, 2026
Rust implementation means memory operations are fast and the footprint is small.
- RRiver JohnsonMar 18, 2026
Good for agents that need intelligent memory management, not just storage.
- AAspen KimMar 5, 2026
Time-axis decay and space-axis organization for agent memory is a principled design.
- CCasey BrownMar 3, 2026
Three-layer memory decay mimics how human memory prioritizes recent and important information.