Viewing profile — pauliusztin
pauliusztin
HN member- Joined
- Wed, Jan 26, 2022, 8:01 PM UTC
- HN karma
- 3
- Public activity
- 47 items
- HN profile
- View on Hacker News ↗
About pauliusztin
Recent public activity
- story
- story
-
comment
Comment #48921380
I found some strategies around this in agent-memory by Neo4j
- story
-
story
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 ont…
- story
-
story
3 dangers of being locked into a harness. Your context layer is true freedom
Models are commoditizing fast. Harnesses already have. A "free" open-source harness feels like freedom, but the deeper I built in, the more I'd lose. "Free" open-source harnesses d…
- story
- story
- story
-
story
I spent a year building agent memory on knowledge graphs. Here are my 5 mistakes
I spent the past year building a unified memory layer for my AI agents using knowledge graphs and ontologies on top of MongoDB. I followed every trend first. I reached for the shin…
- story
- story
- story
- story
- story
- story
- story
- story
-
story
My 11-step GraphRAG pipeline, what worked, and what's still broken
While building a financial assistant for an SF start-up, we learned that AI frameworks add complexity without value. When I started building a personal assistant with GraphRAG, I c…
- story
- story
- story
- story
- story