CodeSherpa offers a Python-based code interpreter and ChatGPT plugin, aiming to replicate OpenAI's Code Interpreter functionality. It targets developers and ChatGPT users seeking to execute code, perform data analysis, and visualize results within a conversational AI context, with file persistence and no execution timeouts.

How It Works

CodeSherpa leverages OpenAI's GPT function calling to enable ChatGPT to interpret and execute code. It acts as a backend service that receives code execution requests from ChatGPT, runs the code (supporting Python, C++, and Rust), and returns the output. The system uses a local server and a frontend interface, with an experimental standalone UI now available.

Quick Start & Requirements

• Installation: Clone the repository, copy .env.example to .env.local, install dependencies (pnpm install or npm install), and run the Next.js app (pnpm dev or npm run dev). Alternatively, use Docker: docker pull ghcr.io/iamgreggarcia/codesherpa:latest and docker compose up.
• Prerequisites: Python 3.10, Docker (optional but recommended), an OpenAI API key.
• Setup: Access at http://localhost:3000 (frontend) or localhost:3333 (API).
• Docs: Quickstart Section

Highlighted Details

• Supports multiple programming languages: Python, C++, and Rust.
• Includes a basic standalone UI for direct interaction.
• Offers file upload capabilities via a dedicated endpoint.
• Demonstrates functionality through video examples of data analysis and visualization.

Maintenance & Community

Recent contributions noted from emsi and PeterDaveHello. The project welcomes contributions via pull requests.

Licensing & Compatibility

Licensed under the MIT license, permitting commercial use and integration with closed-source projects.

Limitations & Caveats

The project is explicitly described as "experimental," "very buggy," and "inconsistent." Users are warned to expect "many bugs and shortcomings." The standalone interpreter is also noted as experimental.