Last week I couldn't shake an idea: what if I had an AI that knew everything I know? Not ChatGPT — something on my hardware, holding my knowledge, answering to no one's API bill.
Yesterday I built it. Here's the honest breakdown.
What it does
NEXUS runs on a regular Windows laptop — aging i7, 16GB RAM, no GPU. It:
- Remembers everything. Drop any file in a folder; 60 seconds later it's searchable memory.
- Answers from MY knowledge. "Which of my projects were formally closed and why?" — it answers from my actual records.
- Watches the live web. Every 2 hours it pulls Hacker News and news feeds, learns what's trending, pings my Telegram.
- Reports to my phone. 7 AM daily briefing: what it learned, what's running, what needs me.
The stack — all free, all open source
Ollama runs the models (Llama 3.2, Mistral 7B). Open WebUI is my private ChatGPT. Qdrant stores memory. n8n automates. SearXNG searches privately. PostgreSQL, Redis, and MinIO handle data.
Commercial equivalent: $300–500/month. My cost: electricity.
The memory trick nobody explains simply
- Parse — extract text from any file
- Chunk — split into ~300-word pieces
- Embed — each chunk becomes 768 numbers representing its meaning
- Store — a database that searches by similarity
Your question becomes 768 numbers too, and the database finds memories with similar meaning — not matching keywords. I asked "how do I get clients cheaper" and it found my notes on "reducing customer acquisition cost." Different words. Same meaning. That's the magic.
What surprised me
- A 2GB model is genuinely useful. Llama 3.2 3B answers from my knowledge in seconds, on CPU.
- The automation matters more than the AI. The watched folder + Telegram bot turned a cool demo into a system I actually use.
- Windows is fine. Docker Desktop + WSL2 ran all nine services without drama.
The bill, honestly
- Hardware: $0 (laptop I own)
- Software: $0 (open source)
- APIs: $0 (all local)
- Time: one focused day
The only future cost is a cloud GPU server (~$65/mo) when I outgrow the laptop — and the plan is for the system to pay for that itself.
It already acts
By evening, NEXUS ran its first autonomous research mission: it searched the web, read five industry reports, cross-referenced its own memory, and delivered a cited market analysis to my phone — while I made coffee.
Next: a Writing Agent that drafts in my voice, and a Monitor Agent that hunts opportunities in the feeds it's already collecting.
An intelligence that doesn't just remember — it acts.
I'm documenting the whole build in public — every command, every dollar, every failure.
- The live build log: t.me/theonaia
- Follow on X: @Theonaia
- The system itself: theonaia.org
Ask me anything about the setup in the comments.
Stack: Ollama · Open WebUI · Qdrant · PostgreSQL · Neo4j · n8n · SearXNG · Redis · MinIO · Docker — all open source.
TL;DR
You can build a fully private AI assistant on a regular laptop for $0 using open-source tools. The system (called NEXUS) uses Ollama for local LLMs, Qdrant for semantic memory, and n8n for automation — giving you a personal AI brain that remembers your documents, searches by meaning, watches the web, and reports to your phone. No API costs, no cloud dependency, no data leaving your machine.
Frequently Asked Questions
Can I really run a useful AI model on a laptop with no GPU?
Yes. Llama 3.2 3B runs entirely on CPU with 16 GB of RAM and responds in seconds. It won't match GPT-4 on complex reasoning, but for retrieval-augmented Q&A over your own documents it is genuinely useful. The key is pairing a small model with good memory (vector search) so the model answers from your knowledge, not from scratch.
What is semantic search and how is it different from keyword search?
Semantic search converts text into numerical vectors (embeddings) that represent meaning rather than exact words. When you ask a question, the system finds documents with similar meaning — not just matching keywords. For example, searching "how do I get clients cheaper" retrieves notes about "reducing customer acquisition cost" because the meaning is the same even though the words are different.
What does the full open-source stack include and what does each tool do?
The stack is: Ollama (runs LLM models locally), Open WebUI (private ChatGPT-style interface), Qdrant (vector database for semantic memory), PostgreSQL (relational data), Neo4j (knowledge graph), n8n (workflow automation), SearXNG (private web search), Redis (caching), MinIO (file storage), and Docker to run it all. Every component is free and open source.
How much would this system cost if I used commercial equivalents?
A comparable cloud setup — ChatGPT Plus, vector database hosting, automation platform, and private search — would run approximately $300–500 per month. The local version costs only electricity. The only planned future expense is an optional cloud GPU server (~$65/month) if the workload outgrows the laptop.
Top comments (0)