Mem0
The memory layer for AI agents -- drop-in persistent memory infrastructure that remembers context across conversations and sessions.
- Actively maintained
- Permissive license
Overview
Mem0 gives agents and LLM apps a memory layer that persists relevant context (facts, preferences, past interactions) across sessions instead of starting from a blank slate every conversation, and integrates as a lightweight drop-in component rather than requiring a full agent platform. It works alongside most major agent frameworks rather than replacing them.
Mem0 is a fit for teams adding persistent, evolving context to an existing agent or chat application as a library-level integration -- distinct from Letta (also in this catalog), which is a full stateful-agent platform rather than a memory layer you embed into something else.
- Categories
- AI Agents & Agent Tools
- Languages
- Python, TypeScript
- License
- Apache-2.0
Related Projects
Letta
Apache-2.0A platform for building stateful agents with advanced memory that learns and self-improves over time, rather than resetting between conversations.
Actively maintained
- AI Agents & Agent Tools
LangGraph
MITBuild resilient, stateful agents as graphs -- explicit nodes and edges for control flow, rather than an implicit agent loop, for reliable long-running or multi-step workflows.
Actively maintained
- AI Agents & Agent Tools
Composio
MITPowers 1000+ toolkits, tool search, context management and authentication so AI agents can actually take action, not just plan it.
Actively maintained
- AI Agents & Agent Tools
MCP Servers
MITOfficial reference implementations of the Model Context Protocol -- the open standard now adopted across OpenAI, Google, Microsoft and Anthropic for connecting agents to tools and data.
Actively maintained
- AI Agents & Agent Tools
Spotted an error? Suggest an edit on GitHub.