december

作者 ntegrals已验证

A fully local Loveable, Replit, Bolt, v0 alternative that you can run with your own LLM. No monthly subscriptions, private by default.

423
Stars
95
Forks
TypeScript
语言
2026/8/23
添加时间

⚠️ 第三方软件声明

本 Skill 为第三方开源软件,独立托管于 GitHub。SkillTip 仅为信息目录,不控制或维护底层仓库。所显示的安全检查为自动化且范围有限,安装前请自行审查源码。

阅读服务条款

安装

添加到你的 Claude Code skills 目录:

# Add to your Claude Code skills
git clone https://github.com/ntegrals/december

快速入门

使用 december 等 Skills 的指南。

安全报告

已验证

上次扫描:—

{
  "status": "PASSED",
  "issues": []
}

README.md

Say hi to December ☃️

December is an open-source alternative to AI-powered development platforms like Loveable, Replit, and Bolt that you can run locally with your own API keys, ensuring complete privacy and significant cost savings.

December lets you build full-stack applications from simple text prompts using AI.

Get started · Report Bug · Request Feature

December Preview

Features

✅ AI-powered project creation from natural language prompts
✅ Containerized Next.js applications with Docker
✅ Live preview with mobile and desktop views
✅ Full-featured Monaco code editor with file management
✅ Real-time chat assistant for development help
✅ Project export and deployment capabilities

Roadmap

🔄 LLM streaming support
🔄 Document & image attachments
🔄 Improved fault tolerance
🔄 Comprehensive test coverage
🔄 Multi-framework support (beyond Next.js)

Get started

  1. Clone the repo

    git clone https://github.com/ntegrals/december
    
  2. Get an API Key from any OpenAI sdk compatible provider (e.g. OpenAI, Claude, Ollama, OpenRouter, etc.) and set it in the config.ts file.

    The start.sh script will automatically copy over the file into the backend folder.

    I highly recommend using Sonnet-4 from Anthropic as it is the best coding model available right now.

     baseUrl: "https://openrouter.ai/api/v1",
    
     apiKey:
       "sk-...",
    
     model: "anthropic/claude-sonnet-4",
     temperature: 0.7,
    
  3. Install docker (Docker Desktop is the easiest way to get started)

    Make sure you have Docker running and the Docker CLI installed before proceeding.

  4. Run the start script to set up the environment

    sh start.sh
    
  5. The application will start in development mode, and you can access it at http://localhost:3000.

    The backend will run on port 4000, and the frontend will run on port 3000.

    You can now start building your applications with December! 🥳

Motivation

AI-powered development platforms have revolutionized how we build applications. They allow developers to go from idea to working application in seconds, but most solutions are closed-source or require expensive subscriptions.

Until recently, building a local alternative that matched the speed and capabilities of platforms like Loveable, Replit, or Bolt seemed challenging. The recent advances in AI and containerization technologies have made it possible to build a fast, local development environment that gives you full control over your code and API usage.

I would love for this repo to become the go-to place for people who want to run their own AI-powered development environment. I've been working on this project for a while now and I'm really excited to share it with you.

Why run December locally?

Building applications shouldn't require expensive subscriptions or sacrificing your privacy. December gives you the power of platforms like Loveable, Replit, and Bolt without the downsides:

  • Full Control & Privacy - Your code, ideas, and projects never leave your machine. No cloud storage, no data mining, no vendor lock-in
  • Your API Keys, Your Costs - Use your own OpenAI API key and pay only for what you use. No monthly subscriptions or usage limits imposed by third parties
  • Complete Feature Access - No paywalls, premium tiers, or artificial limitations. Every feature is available from day one

Most cloud-based AI development platforms charge $20-100+ per month while limiting your usage and storing your intellectual property on their servers. With December, a $5 OpenAI API credit can generate dozens of complete applications, and you keep full ownership of everything you create.

The local-first approach means you can work offline, modify the platform itself, and never worry about service outages or policy changes affecting your projects. Your development environment evolves with your needs, not a company's business model.

December proves that you don't need to choose between powerful AI assistance and maintaining control over your work. Run it locally, use your own API keys, and build without boundaries.

Contact

Hi! Thanks for checking out and using this project. If you are interested in discussing your project, require mentorship, consider hiring me, or just wanna chat - I'm happy to talk.

You can send me an email to get in touch: j.schoen@mail.com or message me on Twitter: @julianschoen

Thanks and have an awesome day 👋

Disclaimer

December, is an experimental application and is provided "as-is" without any warranty, express or implied. By using this software, you agree to assume all risks associated with its use, including but not limited to data loss, system failure, or any other issues that may arise.

The developers and contributors of this project do not accept any responsibility or liability for any losses, damages, or other consequences that may occur as a result of using this software. You are solely responsible for any decisions and actions taken based on the information provided by December.

Please note that the use of the large language models can be expensive due to its token usage. By utilizing this project, you acknowledge that you are responsible for monitoring and managing your own token usage and the associated costs. It is highly recommended to check your API usage regularly and set up any necessary limits or alerts to prevent unexpected charges.

By using December, you agree to indemnify, defend, and hold harmless the developers, contributors, and any affiliated parties from and against any and all claims, damages, losses, liabilities, costs, and expenses (including reasonable attorneys' fees) arising from your use of this software or your violation of these terms.

License

Distributed under the MIT License. See LICENSE for more information.

常见问题

What is december?

december is an open-source ai agents skill for AI coding assistants such as Claude Code, Codex CLI, and ChatGPT, built by ntegrals. A fully local Loveable, Replit, Bolt, v0 alternative that you can run with your own LLM. No monthly subscriptions, private by default. It has 423 GitHub stars.

Is december safe to use?

Yes. december passed SkillsLLM's automated security scan — a dependency vulnerability audit plus prompt-injection heuristics — with no high-severity issues. You can read the full report in the Security Report section on this page.

How do I install december?

Clone the repository with "git clone https://github.com/ntegrals/december" and add it to your Claude Code skills directory (see the Installation section above).

What programming language is december written in?

december is primarily written in TypeScript. It is open-source under ntegrals on GitHub, so you can review or fork the full source.

Are there alternatives to december?

Yes. SkillsLLM lists many other AI Agents skills you can browse and compare side by side. Open the AI Agents category from the badge at the top of this page, or use the Related Skills and comparison links further down to weigh december against similar tools.

评论 (0)

暂无评论,成为第一个分享想法的人!

ECC

by affaan-m

10

The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.

242,21936,702JavaScript
AI 智能体ai-agentsanthropicclaude-code
查看详情
15

An agentic skills framework & software development methodology that works.

234,96620,863Shell
AI 智能体ai-agentsbrainstorming
查看详情

hermes-agent

by NousResearch

10

The agent that grows with you

234,43747,175Python
AI 智能体ai-agentsagent-orchestration
查看详情

The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.

185,94028,768JavaScript
AI 智能体ai-agentsanthropicclaude-code
查看详情

cc-switch

by farion1231

3

A cross-platform desktop All-in-One assistant for Claude Code, Codex, OpenCode, OpenClaw, Grok Build & Hermes Agent. Only official website: ccswitch.io

128,8688,826Rust
AI 智能体claude-codeai-tools
查看详情

claude-code

by anthropics

Claude Code is an agentic coding tool that lives in your terminal, understands your codebase, and helps you code faster by executing routine tasks, explaining complex code, and handling git workflows - all through natural language commands.

120,03119,897Shell
AI 智能体
查看详情

开发者还喜欢

基于喜欢此 Skill 的开发者投票和收藏

ECC

by affaan-m

10

The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.

242,21936,702JavaScript
AI 智能体ai-agentsanthropicclaude-code
查看详情
15

An agentic skills framework & software development methodology that works.

234,96620,863Shell
AI 智能体ai-agentsbrainstorming
查看详情

hermes-agent

by NousResearch

10

The agent that grows with you

234,43747,175Python
AI 智能体ai-agentsagent-orchestration
查看详情

n8n

by n8n-io

12

Fair-code workflow automation platform with native AI capabilities. Combine visual building with custom code, self-host or cloud, 400+ integrations.

201,88160,308TypeScript
MCP 服务器apisai-tools
查看详情

The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.

185,94028,768JavaScript
AI 智能体ai-agentsanthropicclaude-code
查看详情

cc-switch

by farion1231

3

A cross-platform desktop All-in-One assistant for Claude Code, Codex, OpenCode, OpenClaw, Grok Build & Hermes Agent. Only official website: ccswitch.io

128,8688,826Rust
AI 智能体claude-codeai-tools
查看详情