eth-sri/ToolFuzz

ToolFuzz is a fuzzing framework designed to test your LLM Agent tools.

33
/ 100
Emerging

Combines LLM-based prompt generation with two specialized testers—`RuntimeErrorTester` detects crashes and `CorrectnessTester` validates output correctness—while maintaining framework agnosticism through abstract `TestingAgentExecutor` and `ToolExtractor` interfaces. Includes built-in support for LangChain, AutoGen, LlamaIndex, and CrewAI, with results exported as interactive HTML and JSON reports. Uses OpenAI models for fuzzing and evaluation, with extensibility for custom agents and tools via interface implementation.

No commits in the last 6 months.

Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 7 / 25
Maturity 16 / 25
Community 8 / 25

How are scores calculated?

Stars

37

Forks

3

Language

Python

License

MIT

Last pushed

Jul 20, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/agents/eth-sri/ToolFuzz"

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