Updated
Memary
An open-source Python library that gives autonomous agents long-term memory by storing what they learn in a knowledge graph (Neo4j or FalkorDB) and tracking the entities a user talks about most.
Open sourceSelf-hostableFree tier
In maintenance · Oct 2024: No commits since October 2024, and the last PyPI release (0.1.3) was on 27 May 2024. Source ↗
Profile checked
Ask your AI about this, with this page as the source:ChatGPT ↗Claude ↗Perplexity ↗
How makers use Memary
What Memary is used for
Agent Memory · Open-source library →Experimenting with knowledge-graph memory for an agent, stored in Neo4j or FalkorDB.Trade-off: Unmaintained since 2024, so expect to fix breakages with newer model and graph libraries yourself.
When to use Memary, and when not
Something else fits better if
- You want to add user memory to an existing agent with a few API calls and a free tier to start: Mem0 or Supermemory.
- Memory must stay on your own infrastructure, built as a graph over your data: Cognee or Graphiti.
- Your agent needs dated facts that change over time, from business data as well as chats: Zep or Graphiti.
- You'd rather build the agent on a platform where memory is built in: Letta.
- You want memory as plain Markdown files you can read, edit and share across your own AI tools: Basic Memory.
Who uses it
No maker's live product on record yet.
We haven't found a product that uses Memary yet.
None of these in makers' own words.