Welcome to Self-Host Hub. This community is for people building automation infrastructure they own — self-hosted workflows, local AI, and systems you run for yourself or your clients. 📋 ROADMAP (Weekly) Directional focus areas, not delivery guarantees. - 2/9/26 Faceless video workflow end-to-end: script generation → image generation → audio → video assembly, TTS provider integration (ElevenLabs, OpenAI TTS) - 2/16/26 Debug mode: inline step editing, input/output inspection, continue/skip/stop - 2/23/26 Alpha release 📅 UPDATES - 2/8/26 JSON string extraction fix completed. Faceless video pipeline in progress. Deployment testing underway. - 1/22/26 Direction locked: deterministic workflows, structured AI, production-safe execution. - 1/10/26 Community focus narrowed to real deployments and operational tradeoffs. (Updates appended as work progresses.) WHAT IS STUDIO Self-hosted workflow automation platform for AI content pipelines. You own the infrastructure, pick your providers, keep your keys. Custom workflow engine — no n8n, no Temporal, no off-the-shelf runtime. Full control over execution, debugging, and step-level data flow. Four pieces: - App (API + web UI) - Workers (general, video/FFmpeg, ComfyUI/GPU) - Catalog (installable provider/service packages) - Marketplace (templates + premium token-gated packages) Deploy however you want: single Docker container, Docker Compose, Kubernetes, RunPod, VPS + Cloudflare Tunnel, or hybrid GPU setups over Tailscale. ✅ DONE - Custom workflow engine with step-by-step execution, pause/resume, approval gates - Multi-tenant org system with role-based access - Provider/service architecture — install only what you need - 10+ provider integrations (Claude, OpenAI, Gemini, Google, Slack, Notion, Airtable, telegram, trallo, typeform, ComfyUI, JSON2Video, etc.) - ComfyUI GPU worker with model management - Video worker (FFmpeg transcoding, Whisper STT) - Real-time WebSocket updates during workflow runs - 7 Docker images covering every deployment scenario - Marketplace backend with token-gated access - Full documentation suite - 2/1/26 Deployment testing across all 7 Docker scenarios (single container, Compose, K8s, RunPod, VPS + Cloudflare Tunnel, hybrid GPU, all-in-one)

Hello. I've been doing a lot of n8n workflows for myself and others and I have run into two frustrating issues; auto-saving workflows I'm working on and auto-backups of saved workflows. I'm a software developer and site reliability engineer so, naturally, I wrote some apps to handle that. Workflow Auto-Save is a Chrome browser extension. It detects when the Save button is activated on an n8n workflow and based on a time interval you set, it clicks the Save button, automatically. See screenshot for a view of the app. Workflow Auto-Backup is a shell script that detects changes to all your saved workflows. When it detects a change, it creates a backup of the workflow with a timestamp added to the name. They're both available at https://github.com/kickin6/studio-utils. The Workflow Auto-Save Browser Extension has been submitted to the Chrome Web Store for review and hopefully, approval. Cheers

A new community where innovators of all walks of life and business help each other navigate the world of AI automation while reducing, or maybe eliminating, the costs of all those services. What you'll get: - Community. Interact with a diverse group of people willing to help and learn from each other. - n8n, make.com and airtable workflows done-for-you. - Tips, tricks and tools to streamline your funnels. - Access to the latest version of Self-Host Studio pre-built docker images. - Tutorials and workshops for beginners and professionals. - Technical Help when you need it.

This video was made using N8N, Image Creator and Video Creator running on my computer. They directly replace Make.com, Leonardo and JSON2Video respectively.I'll update you when the code is released along with the tutorial video. A little heads-up, if you plan on running Studio on your computer, you'll need 16GB+ of RAM and an Nvidia GPU to do image creation and subtitles. If you don't have that kind of setup, I plan to release a docker image that can build a server on runpod.io, with one click, that will dramatically reduce the cost. Cheers

Hello. This is a little preview of Studio running on n8n. You may recognize the 100% Faceless Videos workflow. - First release replaces make.com and JSON2Video. - Second release will replace LeonardoAI and ElevenLabs (already working, still testing). - Third release will replace Airtable with Self-Host Dashboard. Each workflow I create will have a corresponding page in Dashboard. - Fourth release, if there is one, will replace ChatGPT. Pretty low priority since they are so good and so cheap. I have been running it on my desktop and performance is great. Some services will run on your laptop but the big stuff (images, text-to-speech) will need a GPU and even the Create Video will need more than a few CPU cores. I'm testing on 3 different GPU cloud providers and will have cloud deployment solutions soon. The goal there is to have pre-built disk images so launching the whole system is literally one click. I'll continue to create make.com modules but that has dropped in priority. It's looking really good and it has been a blast working on it. Thanks for your patience and I'll update you when it's ready for launching and the soup to nuts tutorials are ready. Cheers Kawika