OoriData/Toolio

GenAI & agent toolkit for Apple Silicon Mac, implementing JSON schema-steered structured output (3SO) and tool-calling in Python. For more on 3SO: https://huggingface.co/blog/ucheog/llm-power-steering

45
/ 100
Emerging

This project helps developers integrate large language models (LLMs) into their applications, specifically for tasks requiring precise, structured data output or the use of external tools. It takes an MLX-format LLM as input and, with a specified JSON schema, reliably generates structured JSON responses or orchestrates tool calls. Developers working on Apple Silicon Macs would use this to build advanced AI applications with controlled LLM outputs.

132 stars. Available on PyPI.

Use this if you are a developer building AI applications on an Apple Silicon Mac and need to ensure your language model's output strictly adheres to a defined JSON structure or requires the LLM to call specific functions/tools.

Not ideal if you are not a developer, if you are not working on an Apple Silicon Mac, or if your application does not require structured LLM output or tool-calling capabilities.

AI-application-development structured-LLM-output agentic-AI tool-calling local-LLM-deployment
No License
Maintenance 10 / 25
Adoption 10 / 25
Maturity 17 / 25
Community 8 / 25

How are scores calculated?

Stars

132

Forks

6

Language

Python

License

Last pushed

Feb 27, 2026

Commits (30d)

0

Dependencies

7

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/llm-tools/OoriData/Toolio"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.