Description
Burrito Core is a comprehensive inference harness designed for gpt-oss, providing seamless compatibility with OpenAI and Anthropic APIs. This tool is tailored for developers who require a robust solution for integrating AI capabilities into their applications. Burrito Core supports both native Python and browser tools, making it versatile for various development environments. It leverages llama.cpp or vLLM, ensuring efficient processing and execution of AI models. The tool is ideal for developers looking to implement AI solutions without the need for extensive modifications to existing codebases. By offering a drop-in compatibility, Burrito Core simplifies the integration process, allowing developers to focus on building innovative applications. While the tool does not specify pricing, its open-source nature suggests accessibility for a wide range of users. Burrito Core is particularly beneficial for those in the tech industry, including software developers and AI researchers, who are seeking to enhance their projects with advanced AI functionalities.
- CategoryMachine Learning Platforms
- Pricing ModelOpen source
- DeploymentCloud, Self-hosted
- PlatformsWeb, Windows, macOS
Burrito Core's Core Features
Inference harness for gpt-oss
OpenAI API compatibility
Anthropic API compatibility
Native Python support
Browser tools support
Utilizes llama.cpp
Supports vLLM
Drop-in API compatibility
Getting Started with Burrito Core
Clone: Download the repository
Install dependencies: Set up required packages
Configure: Adjust settings for your environment
Execute: Run the harness for inference
Optimise: Fine-tune for performance
Burrito Core's Use Cases
- AI Integration
- API Compatibility
- Python Development
- Browser Tools
- Model Processing







