engram-rs
Active·★ 28·MIT·Updated 2026-03-03
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.
#AI Memory Engine#Rust#Semantic Search#Memory Lifecycle#Topic Modeling#SQLite#LLM Integration#Agent Memory
01
Features
01Three-Layer Lifecycle (Buffer, Working, Core memory management)
02LLM Quality Gate for intelligent memory promotion
03Self-Organizing Topic Tree for automatic knowledge clustering
04Semantic Dedup & Merge of similar memories
05Activity-driven Automatic Decay of importance
02
Compatibility
Rust
Language
Verified via docs
Linux
Platform
Verified via docs
macOS
Platform
Verified via docs
Windows
Platform
Verified via docs
Docker
Deployment
Verified via docs
OpenAI API
LLM Integration
Verified via docs
03
Quick start
1
$ curl -fsSL https://raw.githubusercontent.com/kael-bit/engram-rs/main/install.sh | bash
04
Use cases
↳Enhancing AI agents with structured, evolving memory
↳Managing context and long-term knowledge for AI applications
↳Automating knowledge retention and recall for intelligent systems
↳Providing a self-organizing memory for LLM-powered assistants
05
Alternatives
⚡Top VS:
knowledge-graph-system★ 129
Kappa Graph — κ(G). A semantic knowledge graph where knowledge has weight. Extracts concepts, measures grounding strength, preserves disagreement, traces everything to source.
paiml-mcp-agent-toolkit★ 167
Pragmatic AI Labs MCP Agent Toolkit - An MCP Server designed to make code with agents more deterministic
ai-workshop★ 60
Building GenAI Apps in C#: AI Templates, GitHub Models, Azure OpenAI & More
project-synapse-mcp★ 11
Transforms raw text into interconnected knowledge graphs and autonomously generates insights through advanced pattern detection. It combines formal semantic analysis (Montague Grammar) with Zettelkasten methodology to create a true cognitive partnership with AI.
rekal★ 53
Long-term memory for LLMs. MCP server backed by hybrid search in a single SQLite file.
memory-journal-mcp★ 20
MCP server for AI Context + Project Intelligence. Overcome disconnected AI sessions with persistent project memory, triple search, knowledge graphs, and GitHub integration (Actions, Issues, Kanban Boards, Milestones, and PRs). Uses Tool Filtering. HTTP/SSE Transport Available.
Comments
Log in to leave a comment
No comments yet. Be the first!