Memori and aius
These tools are competitors, with Memori offering a more mature and widely adopted SQL-native memory layer, while aius provides a newer, graph-RAG based approach for long-term memory in AI agents and LLMs.
About Memori
MemoriLabs/Memori
SQL Native Memory Layer for LLMs, AI Agents & Multi-Agent Systems
Automatically intercepts and persists LLM conversations to SQL, then intelligently retrieves relevant context on subsequent queries—achieving 81.95% accuracy on long-context tasks while reducing token usage to ~5% of full-context approaches. Integrates directly with OpenAI, Anthropic, and other LLM providers via SDK wrappers, plus hooks into OpenClaw agents and MCP-compatible tools (Claude Code, Cursor) without requiring code changes. Supports bring-your-own-database deployments for self-hosted setups alongside cloud-hosted options.
About aius
markmbain/aius
The long-term memory for your Superagents 🥷and LLMs 🤖. Built with GraphRAG, Knowledge graphs and autonomous ai agents
Implements a modular MemorySystem architecture with pluggable storage backends (KV, Graph, Vector databases) and isolated MemoryPods for different memory types—episodic, entity, working, short-term, and long-term—enabling agents to develop persistent self-awareness and learn individual user behaviors dynamically. Designed as a composable framework that equips AI agents with configurable input sensors, memory layers, processing functions, and output tools, supporting multi-modal content ingestion across formats and languages for building collaborative agent ecosystems.
Related comparisons
Scores updated daily from GitHub, PyPI, and npm data. How scores work