open-forge
Self-host any open-source app on the user's own infrastructure (cloud VM, VPS, Raspberry Pi, localhost, k8s, PaaS). Walks the user through provisioning, DNS, TLS, SMTP, and hardening in phased + resumable workflows. 2216+ verified recipes plus live-derived fallback for the long tail.
Profile →npx skills add zhangqi444/open-forge --skill openclaw --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
What it does
Automates self-hosting of open-source apps on user-owned cloud infrastructure or local environments. Walks the user through provisioning, DNS, TLS, SMTP, and hardening in phased + resumable workflows, loading the appropriate project recipe and infra adapter based on user intent. Uses a guided chat where Claude executes recipes via the user’s local CLI tools and asks for choices or credentials only when needed. Keeps a state file at ~/.open-forge/deployments/<name>.yaml to allow resuming across sessions.
How it works
- Claude selects and runs bash blocks from recipes when a recipe contains a bash block, announcing each action before execution.
- It prompts for necessary inputs (e.g., AWS profile name, domain choice, SMTP API key) one at a time.
- If required tools like jq or aws are missing, it proposes the install command and performs installation after one-line approval.
- It determines the software to host from user prompts and loads the corresponding project recipe and infra adapter.
- It supports multiple host environments and runtimes, including cloud VMs, Raspberry Pi, Kubernetes, and various vendor blueprints, via the references/projects, references/infra, and references/runtimes trees.
- It records progress in a per-deployment state file at ~/.open-forge/deployments/<name>.yaml for resumable workflows.
When to use it
Use when a user asks to self-host an open-source app on their own infrastructure (e.g., AWS Lightsail, EC2, Azure, Hetzner, DigitalOcean, GCP, Raspberry Pi, macOS VM, localhost, or Kubernetes) and wants provisioning, DNS, TLS, and SMTP setup in phased, resumable steps.
What it can touch
- Commands and scripts executed via the user’s CLI tools (aws, ssh, jq, curl) as dictated by the loaded bash blocks in recipes.
- The state file at ~/.open-forge/deployments/<name>.yaml to persist deployment progress.
- Project and infra adapters loaded from references/projects and references/infra (no direct file edits described in this summary).
Caveats
- Requires tools listed in metadata bins: bash, curl, ssh.
- User decisions and credentials are requested only when needed; secure handling is implied by the workflow but not specified beyond prompts.
- The described capabilities are platform-agnostic but wired through Claude Code-specific prompts and architecture notes present in the skill description.
# open-forge — self-host any open-source app --- name: open-forge description: Automate self-hosting of open-source apps on cloud infrastructure the user owns. Use when the user asks to "self-host", "deploy to my own cloud", "install X on AWS / Lightsail / EC2 / Azure / Hetzner / DigitalOcean / GCP / Oracle Cloud / Hostinger / Raspberry Pi / Kubernetes / Fly.io / Render / Railway / Northflank / exe.dev", "set up my own Ghost blog / Mastodon / WordPress / Nextcloud", wants to deploy the self-hosted personal AI agent **OpenClaw** (openclaw.ai — NOT the Captain Claw platformer game) or **Hermes-Agent** (Nous Research's self-improving AI agent at github.com/NousResearch/hermes-agent), wants to run **Ollama** (local-LLM inference server at ollama.com — pairs with every AI agent / chat UI as an OpenAI-compatible provider), wants to run **Open WebUI** (feature-rich self-hosted ChatGPT-like UI at github.com/open-webui/open-webui — pairs natively with Ollama and any OpenAI-compatible backend; adds RAG, web search, image gen, voice, multi-user), wants to run **Stable Diffusion WebUI** / **Automatic1111** / **A1111** (the most-popular open-source AI image generator at github.com/AUTOMATIC1111
- Overview
- Operating principle
- What's supported
- Selection — ask three questions
- Goal-shaped requests → curated bundles
- Tier 1 vs Tier 2 routing
- Tier 1 — verified recipe exists
- Tier 2 — no recipe; derive from upstream live
- Out-of-scope software
- Phased workflow
- State file
- Execution mode
- Inputs
- Asking for credentials
Use $RESEND_KEY in subsequent commands; never echo it back to the user
Verify the var exists in Claude's shell
test -n "$RESEND_API_KEY" || { echo "RESEND_API_KEY not set; export it before continuing"; exit 1; }
Use it
curl ... -H "Authorization: Bearer $RESEND_API_KEY" ...
Check if gh is authenticated for the right account
gh auth status
If yes, submit
gh issue create \What does the open-forge skill do?
Self-host any open-source app on the user's own infrastructure (cloud VM, VPS, Raspberry Pi, localhost, k8s, PaaS). Walks the user through provisioning, DNS, TLS, SMTP, and hardening in phased + resumable workflows. 2216+ verified recipes plus live-derived fallback for the long tail.
How do I install it?
Run `npx skills add zhangqi444/open-forge --skill openclaw --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From zhangqi444/open-forge, a repository with 89 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.