safety-tooling

by safety-research · Agent Tool · ★ 122

About safety-tooling

safety-tooling This is a repo designed to be shared across many AI Safety projects. It has built up since Summer 2023 during projects with Ethan Perez. The code primarily provides an LLM API with a common interface for OpenAI, Anthropic and Google models. The aim is that this repo continues to grow and evolve as more collaborators start to use it, ultimately speeding up new AI Safety researchers that join the cohort in the future.

Quick Facts

Stars122
Forks38
LanguagePython
CategoryAgent Tool
LicenseMIT
Quality Score72.3401528466902/100
Open Issues31
Last Updated2026-05-29
Created2024-12-11
Platformspython
Est. Tokens~237k

Compatible Skills

These tools work well together with safety-tooling for enhanced workflows:

More Agent Tool Tools

Explore other popular agent tool tools:

View all Agent Tool tools →

Popular Python Agent Tools

Frequently Asked Questions

What is safety-tooling?

safety-tooling is Inference API for many LLMs and other useful tools for empirical research. It is categorized as a Agent Tool with 122 GitHub stars.

What programming language is safety-tooling written in?

safety-tooling is primarily written in Python.

How do I install or use safety-tooling?

You can find installation instructions and usage details in the safety-tooling GitHub repository at github.com/safety-research/safety-tooling. The project has 122 stars and 38 forks, indicating an active community.

What license does safety-tooling use?

safety-tooling is released under the MIT license, making it free to use and modify according to the license terms.

View on GitHub → Browse Agent Tool tools