mem0 and mengram
These are competitors, as both projects aim to provide a universal or human-like memory layer for AI agents, offering similar functionalities for managing semantic, episodic, and procedural memory.
About mem0
mem0ai/mem0
Universal memory layer for AI Agents
Implements multi-level memory (user, session, agent state) with adaptive retrieval that achieves 26% higher accuracy and 90% lower token usage than baseline approaches. Supports multiple LLMs and vector stores, with SDKs for Python and JavaScript, plus integrations for LangGraph and CrewAI. Offers both self-hosted open-source deployment and a managed platform with CLI tooling for memory management operations.
About mengram
alibaizhanov/mengram
Human-like memory for AI agents — semantic, episodic & procedural. Experience-driven procedures that learn from failures. Free API, Python & JS SDKs, LangChain & CrewAI integrations.
Supports semantic/episodic/procedural memory extraction through conversational APIs and file uploads (PDF, DOCX, TXT, MD using vision AI), with automatic procedure evolution triggered by failure feedback or implicit detection from conversation context. Offers multi-user isolation, cognitive profiling via system prompts, and Claude Code hooks for zero-config auto-save/recall in Claude IDE; integrates with LangChain, CrewAI, and MCP, plus data import from ChatGPT and Obsidian.
Related comparisons
Scores updated daily from GitHub, PyPI, and npm data. How scores work