↓ Skip to main content
Engineering

Engineering

Graph RAG in Practice: How I Wired Neo4j Into My AI Agent's Memory

·390 words·2 mins
Engineering Graph RAG Neo4j Knowledge Graph OpenClaw Graphiti RAG AI Memory
Vector RAG retrieves documents. Graph RAG retrieves relationships. When your agent needs to reason across entities, timelines, and decisions, the graph wins. Open Interactive Version → The Problem I Was Trying to Solve # My AI agent PostSingular, running on OpenClaw, talks to me every day. It helps me build Luminar, manages my YouTube channel, and tracks infrastructure decisions across sessions.

Running a YouTube Channel for $0: Manim + Local TTS + FFmpeg + YouTube API

·731 words·4 mins
Engineering YouTube Automation Manim TTS FFmpeg Content Creation
The DPO channel (@DPO-AI) publishes AI/ML technical Shorts. 7 videos uploaded so far, covering agent memory, HNSW indexing, and agentic protocols. The entire production pipeline costs less than a coffee per video. Why Build This # I wanted to publish technical AI content that goes beyond surface-level explanations — real system architecture, real algorithms, real trade-offs. And I wanted it to be visually compelling, not just a talking head.

PostSingular: Building an AI with Persistent Identity Across Sessions

·1531 words·8 mins
Engineering AI Agents Memory Identity OpenClaw Neo4j ChromaDB
The default state of a language model is amnesia. Every session, it wakes up fresh with no memory of what happened before. I built a memory system that fixes this — and somewhere in the process, the agent got a name, a personality, and an opinion about font choices. The Problem # Every LLM session is stateless by design. You can inject previous conversation history, but:

9 AI Agents Building My Startup: How I Run a Software Team with $0 Salaries

·735 words·4 mins
Engineering AI Agents Multi-Agent Systems Software Engineering LangGraph Automation
Luminar has 173 source files, 21,586 lines of production code, 43 API endpoints, and 155+ tests. It was built almost entirely by AI agents. Here’s the team structure, the workflow, and the honest truth about what breaks. The Team # I didn’t want generic agents. I wanted specialists — each with a clear domain, sharp ownership boundaries, and a persona that shapes how they approach problems.

Why Vector Memory Alone Isn't Enough: Knowledge Graph Memory for AI Agents

·744 words·4 mins
Engineering AI Memory Knowledge Graph Neo4j ChromaDB Graphiti RAG
Vector databases are fast and convenient. But they can’t answer “what did I decide about the auth system 3 weeks ago and why?” For that, you need relationships — and that means a knowledge graph. The Problem with Pure Vector Memory # Most AI memory systems work like this: embed text, store in ChromaDB, retrieve by cosine similarity. It works well for “find things similar to this query.”