Project
Swarm Signal
Swarm Signal is a Ghost publication with an n8n pipeline for finding useful AI papers, turning them into readable analysis, generating local audio, and publishing without drowning in manual admin. Over 100 posts published and counting.
The point is not to add more AI sludge to the internet. It is to see whether a well-designed system can turn primary research into something worth reading.
Why I built it
There are thousands of AI research papers published every week. Most never get read outside academia. The coverage that does reach people is often either hype, panic, or a summary so thin it might as well be vapour.
I wanted to see if a practical pipeline could bridge that gap: find papers that matter, extract the useful bits, and write them up in a way builders can actually use. I set the editorial direction and quality bar; the system handles the repeatable work and I check it from time to time.
- Sources from primary materials - arXiv papers and technical documentation, not press coverage or Twitter threads.
- Takes positions - evidence-based analysis rather than hedged summaries that say nothing.
- 100+ articles published - covering agents, swarms, reasoning, safety, and real-world deployment.
- Local audio generation - each article can become a listenable audio version without sending the whole job to a hosted voice platform.
- Built for an AI-literate audience - people who build systems, not people who just follow the news.
Six research verticals
Content is organised into focused research areas, each covering a distinct aspect of the AI landscape:
Agent Design
Architectures, tool use, and frameworks for building AI agents. From single-agent patterns to production deployment strategies.
Swarm Systems
Multi-agent coordination, swarm intelligence, and collective behaviour. How groups of AI agents work together - and when they don't.
Reasoning & Memory
How models think, remember, and build context. Chain-of-thought, retrieval-augmented generation, and long-term memory architectures.
Safety & Governance
Alignment, oversight, and the policy landscape. What matters for building responsibly, beyond the talking points.
Models & Frontiers
Frontier model developments, benchmarks, and capability analysis. What's real, what's noise, and what it means for builders.
Real-World AI
Deployment, robotics, embodied AI, and practical implementation. Where theory meets production and the friction nobody planned for.
How it works
Signals
Shorter, timely research analysis pieces. Typically 5-6 minute reads covering a specific development, paper, or trend with context and a clear takeaway.
Guides
Longer, foundational deep-dives. 10-13+ minute reads that explain a concept thoroughly with practical implications for builders and decision-makers.
Audio
Every article is available as audio for listening on the go. Queue articles and listen through the site's built-in player.
The pipeline
The content operation is now largely autonomous: research themes, arXiv papers, analysis, structured drafts, local audio narration and Ghost publishing, wired together through n8n and supporting scripts. The important part is the scaffolding around it: source quality, structure, editorial standards and checks.
AI can make content very fast. That is not automatically a good thing. Swarm Signal is my attempt to make the speed useful instead of just making the internet louder.
Built with
| CMS | Ghost (self-hosted) |
| Hosting | Docker on Hetzner VPS (same platform as tylerbuilds.com) |
| Automation | n8n pipeline for research, drafting, QA checkpoints and publishing steps |
| API | Custom Node.js API for audio, search, and content operations |
| Audio | Local AI-generated TTS with per-article audio files |
| Database | MariaDB (Ghost) + SQLite (API layer) |
| Reverse proxy | Nginx with Let's Encrypt SSL |
Agents, swarms, and the pace of change
New research analysis published regularly. If you're building with AI or just trying to make sense of where things are heading, have a read.