Artifact Server is an open source alternative to Claude Code Artifacts; enabling teams to own, share, and collaborate on artifacts throughout the development lifecycle.
It runs locally, deploys to Cloudflare, GCP, AWS, or anywhere Kubernetes. It also creates live feedback loops with agents like Pi and Claude via MCP channels.
Why
There are questions I don't like having to ask when using Claude:
- Why am I going to a claude[dot]ai domain to look at my local development artifacts?
- Why are contractors sending me paid work in a claude[dot]ai link on their account?
- Why can I not easily persist, version, and share these artifacts with my team and other agents?
Anyway, artifacts are good (and the CC team has done a great job evangelizing HTML and cool workflows around it). They are becoming a substantial part of the development process and teams need more ownership & collaborative capabilities.
Artifact Server creates a collaboration surface for human-to-human review, integrated AI feedback, and versioning. I can tag Pi in an artifact comment and that comment will queue immediately in Pi (no polling!).
I also think Git is the right memory layer for artifacts. Having provenance of what changed and why is useful esp for multi-agent workflows. Versioned artifacts are a key feature along with the sharing/collaboration features.
Artifact Server is an open source alternative to Claude Code Artifacts; enabling teams to own, share, and collaborate on artifacts throughout the development lifecycle.
https://github.com/plannotator/artifact-server
https://artifactserver.com
It runs locally, deploys to Cloudflare, GCP, AWS, or anywhere Kubernetes. It also creates live feedback loops with agents like Pi and Claude via MCP channels.
Why
There are questions I don't like having to ask when using Claude:
Anyway, artifacts are good (and the CC team has done a great job evangelizing HTML and cool workflows around it). They are becoming a substantial part of the development process and teams need more ownership & collaborative capabilities.Artifact Server creates a collaboration surface for human-to-human review, integrated AI feedback, and versioning. I can tag Pi in an artifact comment and that comment will queue immediately in Pi (no polling!).
I also think Git is the right memory layer for artifacts. Having provenance of what changed and why is useful esp for multi-agent workflows. Versioned artifacts are a key feature along with the sharing/collaboration features.