Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
https://github.com/e2b-dev/ai-artifacts
Hackable open-source version of Anthropic's AI Artifacts chat
https://github.com/e2b-dev/ai-artifacts
ai ai-code-generation anthropic claude e2b javascript llm nextjs react typescript
Last synced: about 1 month ago
JSON representation
Hackable open-source version of Anthropic's AI Artifacts chat
- Host: GitHub
- URL: https://github.com/e2b-dev/ai-artifacts
- Owner: e2b-dev
- Created: 2024-07-10T20:31:32.000Z (2 months ago)
- Default Branch: main
- Last Pushed: 2024-07-18T20:12:24.000Z (about 2 months ago)
- Last Synced: 2024-07-21T23:08:22.218Z (about 2 months ago)
- Topics: ai, ai-code-generation, anthropic, claude, e2b, javascript, llm, nextjs, react, typescript
- Language: TypeScript
- Homepage:
- Size: 1.65 MB
- Stars: 389
- Watchers: 5
- Forks: 40
- Open Issues: 4
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
- awesome - e2b-dev/ai-artifacts - Hackable open-source version of Anthropic's Claude Artifacts (TypeScript)
README
# AI Artifacts - Open Source Anthropic Artifacts
This app is an open source version of [Anthropic's Artifacts UI](https://www.anthropic.com/news/claude-3-5-sonnet) in their [Claude chat app](https://claude.ai/).This app is using [E2B](https://e2b.dev/docs)'s [Code Interpreter SDK](https://github.com/e2b-dev/code-interpreter) for AI code execution. E2B provides a cloud sandbox to run AI-generate code securly and can handle installing libraries, running shell commands, run Python, JavaScript, R, and Nextjs apps and more.
![Preview](preview.png)
## Features
- [Anthropic Claude Sonnet 3.5](https://www.anthropic.com/) model for AI code generation
- [Code Interpreter SDK](https://github.com/e2b-dev/code-interpreter) from [E2B](https://e2b.dev) for secure AI code execution using sandboxes
- [Vercel AI SDK](https://sdk.vercel.ai/docs/introduction) for tool calling and streaming responses from the model
- Supported AI-generated code
- ✅ Running AI-generated Python in Jupyter notebook
- ✅ AI-generated Next.js apps
- TODO: vanilla JS/TS, R
- TODO: Stream AI-generated code### 1. Install dependencies
```sh
npm i
```### 2. Set API keys
Create a `.env.local` file and set the following:
```sh
# Get your API key here - https://e2b.dev/
E2B_API_KEY="your-e2b-api-key"
ANTHROPIC_API_KEY="your-anthropic-api-key"
```### 3. Run
```sh
npm run dev
```