Show HN：Sharpie – 可自行託管、支援本地 LLM 的 AI Prompt 遊樂場

Navigation Menu

Search code, repositories, users, issues, pull requests...

Provide feedback

We read every piece of feedback, and take your input very seriously.

Saved searches

Use saved searches to filter your results more quickly

To see all available qualifiers, see our documentation.

Self-hostable AI prompt playground with local LLM

License

Uh oh!

There was an error while loading. Please reload this page.

heyrtl/sharpie

Folders and files

Latest commit

History

Repository files navigation

Sharpie

Self-hostable AI prompt playground with local LLM support

Build, test, and share AI prompts with zero API costs. Run entirely on your machine with Docker.

Features

Demo

Coming soon

Quick Start

Prerequisites

Installation

That's it! Open http://localhost:5173 in your browser.

First run takes 5-10 minutes to download the Qwen2.5-3B model (~2GB).

Usage

Basic Workflow

Sharing Prompts

Share URLs like http://localhost:5173?p=abc123 with anyone running Sharpie. They can:

Switching Models

Architecture

Configuration

Using Different Models

Pull any Ollama model:

Then select it in Settings.

Environment Variables

Copy .env.example to .env and customize:

GPU Support

GPU is auto-detected. To disable GPU and run CPU-only, remove the deploy section from docker-compose.yml.

Development

Project Structure

Running Locally (without Docker)

Backend:

Frontend:

Make sure Ollama is running separately.

Troubleshooting

Port Already in Use

Change ports in docker-compose.yml:

Ollama Model Not Downloading

Manually pull the model:

GPU Not Detected

Check NVIDIA Docker runtime:

If it fails, you may need to install nvidia-container-toolkit.

Out of Disk Space

The Ollama model requires ~2GB. Free up space or use a smaller model:

Contributing

Contributions are welcome! Here's how:

Development Setup

See CONTRIBUTING.md for detailed setup instructions.

Roadmap

Security

See SECURITY.md for security considerations and best practices.

License

MIT License - see LICENSE for details.

Author

Ratul Rahman (@heyrtl)

Acknowledgments

Star History

If you find this useful, consider giving it a star!

Built with care for the prompt engineering community.

About

Self-hostable AI prompt playground with local LLM

Topics

Resources

License

Contributing

Security policy

Uh oh!

There was an error while loading. Please reload this page.

Stars

Watchers

Forks

Languages

Footer

Footer navigation