Projects using Docker Compose in TorontoProjects using Docker Compose in TorontoResults that are similar to your search
Similar results
Designed and documented a secure environment for running Robin, an AI-powered dark web OSINT tool, inside a compartmentalized Qubes OS and Qubes-Whonix setup.
The environment was structured to separate research activity, Tor-routed traffic, sensitive credentials, untrusted content, and final reporting. Robin was deployed through Docker inside a dedicated research qube, with traffic routed through sys-whonix and sensitive notes stored separately in an offline vault qube. Disposable qubes were incorporated for opening potentially unsafe links and files.
The setup was built around security by compartmentalization rather than relying on a single tool for protection. Particular attention was given to Docker mount restrictions, credential hygiene, network-boundary verification, lawful research scope, and keeping raw research data isolated from personal or client environments.
The final result was a repeatable AI-assisted OSINT workflow that supports faster search refinement, result filtering, investigation summarization, and structured reporting while maintaining stronger operational security and clearer separation between collection, analysis, and final output. I built an AI system that finds and contacts business leads automatically — every day, while you sleep.
A client in the UK runs a waste removal marketplace. He needed contractors to join his platform but had no way to find them at scale.
So I built him a system that does it automatically.
Every morning at 6am, without anyone touching a button:
The system scrapes Checkatrade, the UK Environment Agency, Gumtree, and Yell for waste removal contractors
Each lead gets scored out of 10 based on reviews, licensing, and contact details
Bad data gets cleaned out automatically
Personalised outreach messages are prepared for the best leads
The client opens his dashboard, sees who's ready to contact, and sends an SMS in one click
The database now has 2,300+ verified contractor leads and grows every day.
The whole thing runs on 9 AI agents that work like a real team. There's a CEO agent that reads instructions in plain English and delegates to specialists — a Lead Scorer, Deduplication Agent, Outreach Agent, Reporting Agent, and more. The client can type something like "find the top 50 contractors in East London and prepare messages for them" and it happens automatically in a few minutes.
No technical knowledge needed on his end. Just a dashboard and a send button.
What I used:
Claude AI · Paperclip · Python · Node.js · PostgreSQL · Twilio SMS · Docker · Custom scrapers
This kind of system works for any business that needs to:
Find leads from multiple sources automatically
Score and filter them by quality
Reach out at scale without a sales team
If that sounds like something your business needs, let's talk. 
