I reverse-engineered the three biggest agent-memory tools

I spent weeks reading about how Cognee, Graphiti, and Neo4j's `agent-memory` build their agent memory architectures. They converged on the same heavy knowledge-graph design: an ontology, LLM extraction pipelines, deduplication, the works.

I really wanted to use them for my personal use case, but that looks like such a heavy setup that adds a lot of friction and silos. Plus, it feels like I just get my data trapped in their service, for not a ton of value.

That's why my "long-term memory" still lives in Obsidian, Readwise, and Google Drive, with per-project LLM wikis as the agent's memory. No infrastructure. And I'm fine with it.

They ship memory as a product, which, in my opinion, at a personal or small scale, is overkill. You can build the same "knowledge graph" experience via plain old `.md` files within an LLM wiki memory.

But still, graphs are strong, so I adapted the same architecture from the Cognee, Graphiti, and Neo4j `agent-memory` stacks to build a data-mining tool with just MongoDB, VoyageAI, and Gemini Flash. But I scoped it to a very particular problem and ontology domain to avoid the KG noise.

On the other end of the spectrum, if you want to ship a product at medium-to-large scale, it makes sense to start using monsters such as Neo4j, Zep, or HydraDB.

But I am curious: what is your long-term memory setup? Obsidian + LLM wikis vs. Cognee/Graphiti/Zep? Do you actually use tools such as Cognee or Zep?

In case you are curious about how Cognee, Graphiti, and Neo4j's `agent-memory` work under the hood, I wrote a full breakdown here: https://www.decodingai.com/p/unified-memory-from-scratch-knowledge-graphs

2 points | by pauliusztin 12 hours ago

2 comments

  • denn-gubsky 5 hours ago
    Thanks for the useful article. I'm building a hierarchy chunked graph document memory as the project knowledge base in my agentic runtime. After reading your articles I will pay more attention into semantic search and retrieval methods. I also started from linked MD documents, but they are too big and contaminate agent's context, so I moved on to the chunked graph model for more selective retrieval operations.
  • coder-pm 11 hours ago
    Did any of these actually covers the invalidation? It's easy to store memory and access it but I'm curious how these tools handles the fact that something is not true anymore?
    [-]
    • pauliusztin 9 hours ago
      I found some strategies around this in agent-memory by Neo4j
      [-]
      • coder-pm 5 hours ago
        Can you share anything:)?