A framework for automated unit test generation using large language models with adaptive context and repair mechanisms.
ChatUniTest is worth checking the docs before setup with trust notes worth reviewing. Check agent compatibility and use-case fit before adding it to your workflow.
gh repo view ZJU-ACES-ISE/ChatUniTest --webOpen the official repository or website.
Check the README for package manager, auth, and platform requirements.
Try it in a small test task inside your agent workflow.
ChatUniTest uses AI to automatically create unit tests for your code. It first generates tests, then checks if they work, and fixes any errors. It also picks the most relevant parts of your code to help the AI make better tests.
ChatUniTest is an innovative framework designed to improve automated unit test generation. It utilizes an LLM-based approach enhanced with an 'adaptive focal context' mechanism to encompass valuable context in prompts and adheres to a 'Generation-Validation-Repair' mechanism to rectify errors in generated unit tests. The framework includes ChatUniTest Core, a common library implementing the core workflow, and the ChatUniTest Toolchain, a suite of seamlessly integrated tools that enhance its capabilities. It supports multiple research-backed implementations (e.g., for FSE, ICSE, ASE conferences) and can be used as a Maven plugin with different phase types. The tool aims to reduce the manual effort in writing unit tests and improve test coverage by leveraging large language models.
Looks usable, but maintenance, license, or security notes deserve a closer look.
Last commit was about 317 days ago.
171 GitHub stars indicate community interest.
0 open issues signal maintenance load.
No license detected; review before production use.
Automatically generate unit tests for Java projects using Maven.
Improve test coverage by generating tests for hard-to-reach branches.
Integrate with CI/CD pipelines to generate tests on every build.
Research and compare different LLM-based test generation strategies.
Reduce debugging time by generating correct and executable tests.
Generated tests may not cover all edge cases and should be reviewed.
Use of external LLM APIs may incur costs and require internet access.
Potential for generating tests that pass but are semantically incorrect.
171
Stars
28
Forks
0
Issues
Automatically generates JUnit test suites for Java classes using evolutionary algorithms.
Argos is an open source visual testing platform that detects unintended UI changes to help teams maintain quality.
A platform to chat, inspect, debug, and evaluate MCP servers, MCP apps, and ChatGPT apps.
3 security/trust notes recorded.
Setup difficulty is 3/5.