llamacoder vs vibesdk
Two of the top app builder starters, side by side: score, setup, license, activity and what each review found.
llamacoder
Open-source Claude Artifacts clone generating React apps with Llama
vibesdk
Self-hosted prompt-to-app platform on Cloudflare Workers and Durable Objects
| What we compare | llamacoder | vibesdk |
|---|---|---|
| Score parts, out of 100 | ||
| Adoption | 61, popular | 34, known |
| Freshness | 100, active | 94, active |
| Maintenance | 37, patchy | 56, fair |
| Easy to run | 0, hard | 0, hard |
| Agent-ready | 70, partly | 70, partly |
| Facts from GitHub and the README | ||
| Stars | 7.1k | 5.4k |
| License | MIT (permissive) | MIT (permissive) |
| Last commit | Sep 2026 | Sep 2026 |
| Last release | None published | Feb 2026 |
| Language | TypeScript | TypeScript |
| Docker | No | No |
| GPU | Not needed | Not needed |
| arm64 or Apple Silicon | Not stated | Not stated |
llamacoder
Next.js App Router app with Tailwind that sends a prompt to Llama 3.1 405B on Together AI and renders the generated React app in a sandboxed iframe using esbuild-wasm and esm.sh. Needs TOGETHER_API_KEY, a Postgres DATABASE_URL via Prisma (Neon suggested) and S3 credentials for screenshot uploads; Braintrust tracing is optional. For developers building a prompt-to-app demo on open models.
Who it is for: Developers building a prompt-to-app demo on open models
Strengths
- In-browser preview via esbuild-wasm and esm.sh; no server sandbox cost
- Prisma and Postgres persistence for generated apps
- Braintrust observability wired as an optional env var
- Live deployment at llamacoder.io shows the finished product
Weaknesses
- Together AI only; no provider abstraction
- Screenshot upload requires five S3-related env vars
- No auth or rate limiting described
- No .env.example
- TypeScript, Together AI (Llama 3.1 405B)
- Needs Together AI API key, PostgreSQL (Neon), S3 bucket for screenshots, Braintrust (optional)
vibesdk
Bun and Vite project that runs a coding agent (Cloudflare Think) in a Durable Object per project, keeps files in a SpaceDO workspace, stores git history in Cloudflare Artifacts, loads previews as Dynamic Workers and gives each generated app SQLite via Durable Object Facets. Models route through AI Gateway; D1 holds platform data. Needs a Workers Paid plan, Workers for Platforms and a custom domain with wildcard DNS.
Who it is for: Teams self-hosting a prompt-to-app builder on Cloudflare
Strengths
- Previews load as Dynamic Workers; no long-running dev server
- Restore points and rollback via Cloudflare Artifacts
- bun run setup provisions resources, AI Gateway, auth and migrations
- Bash is disabled in the agent; tool boundaries are explicit
Weaknesses
- Requires Workers Paid plan, Workers for Platforms and wildcard DNS for previews
- Entirely Cloudflare-specific; nothing is portable to other hosts
- Feature toggles live in the dashboard, not in wrangler.jsonc
- Long setup guide with several API token permissions to get right
- TypeScript, Cloudflare AI Gateway (configured providers)
- Needs Cloudflare account with Workers Paid plan, Cloudflare AI Gateway, D1, model provider API key, custom domain with wildcard DNS
More in App builder starters
Building with these?
We help teams pick an open-source AI stack and run it in production. Client work never changes a rank.