FullstackAgent  by FullstackAgent

AI platform for full-stack web application development

Created 3 weeks ago

New!

649 stars

Top 51.4% on SourcePulse

GitHubView on GitHub
Project Summary

Summary

Fullstack Agent is an AI-powered platform enabling users to create, develop, and deploy full-stack web applications via natural language. Targeting developers and power users, it streamlines the development lifecycle by leveraging advanced AI models within isolated, scalable Kubernetes environments.

How It Works

The platform integrates Claude Code CLI to translate natural language prompts into application code. It provisions isolated Kubernetes sandbox environments for each project, automatically setting up PostgreSQL databases using KubeBlocks. A Next.js frontend manages user interaction and API routes, while GitHub integration handles version control, offering a complete, AI-driven development workflow.

Quick Start & Requirements

  • Primary install: git clone https://github.com/FullstackAgent/FullstackAgent.git, cd FullstackAgent, npm install.
  • Prerequisites: Node.js (20.x+), PostgreSQL, a Kubernetes cluster with KubeBlocks installed, GitHub OAuth application credentials, and an Anthropic API key.
  • Setup: Configure .env.local (Database URL, GitHub OAuth, NextAuth secrets), .secret/.env (Anthropic API key), and .secret/kubeconfig.
  • Run: npm run dev.
  • Links: Repository

Highlighted Details

  • AI-Powered Development: Leverages Claude Code CLI for natural language-driven application generation.
  • Isolated Sandboxes: Each project runs in a dedicated Kubernetes-managed container environment.
  • Automatic Database Provisioning: On-demand PostgreSQL database clusters managed via KubeBlocks.
  • Modern Tech Stack: Built with Next.js 15, Tailwind CSS v4, Shadcn/UI, Prisma, and NextAuth v5.
  • Integrated Web Terminal: ttyd provides direct access to the sandbox environment.

Maintenance & Community

The project acknowledges contributions from Anthropic, Sealos, KubeBlocks, and ttyd. It highlights that 100% of the code was AI-generated, prompted by "fanux". Community support is primarily via GitHub Issues.

Licensing & Compatibility

Licensed under the MIT License, which is permissive for commercial use and integration into closed-source projects.

Limitations & Caveats

Requires a pre-configured Kubernetes cluster with KubeBlocks, posing a significant setup barrier. The platform's functionality is heavily dependent on the Anthropic Claude API. The "100% AI-generated code" nature may imply an experimental or rapidly evolving state.

Health Check
Last Commit

1 week ago

Responsiveness

Inactive

Pull Requests (30d)
14
Issues (30d)
19
Star History
661 stars in the last 24 days

Explore Similar Projects

Starred by Chip Huyen Chip Huyen(Author of "AI Engineering", "Designing Machine Learning Systems"), Vasek Mlejnsky Vasek Mlejnsky(Cofounder of E2B), and
1 more.

pezzo by pezzolabs

0.2%
3k
Open-source LLMOps platform for streamlining AI workflows
Created 2 years ago
Updated 4 months ago
Starred by Joe Walnes Joe Walnes(Head of Experimental Projects at Stripe), Chip Huyen Chip Huyen(Author of "AI Engineering", "Designing Machine Learning Systems"), and
22 more.

E2B by e2b-dev

0.4%
10k
Open-source cloud runtime for AI apps and agents
Created 2 years ago
Updated 1 day ago
Feedback? Help us improve.