dryfire is a Git-native testing framework specifically built for LLM agents and their tool-use loops. Instead of asserting on final outputs, it captures and validates the entire trajectory of actions, enabling robust regression testing. Available on PyPI under the MIT license, it targets AI engineers building reliable autonomous agents.
dryfire sits in PulseGate's Testing & QA category. Reliably testing and regressing LLM agent tool-use loops by asserting on trajectories instead of brittle outputs. It is built as an open-source project for developers. The project is open source (MIT). dryfire is available on the command line.
dryfire first shipped in 2026. Development happens publicly on GitHub with 42 commits in the last 90 days. Key capabilities include Regression Testing, Trajectory Assertion, and LLM Agent Testing.
Summary written by a language model from the project’s public pages.
What PulseGate has recorded for this listing
Same category — not a similarity match