Coverage-guided generation
Targeted uncovered code and iterated toward a configurable coverage goal.
Historical tool archive
Qodo Cover, originally called Cover-Agent, was an open-source CLI and GitHub Actions project that generated tests, ran them, and kept candidates that increased code coverage.
No longer active

Archive
Cover-Agent was renamed Qodo Cover after CodiumAI became Qodo. The tool used an LLM to generate unit tests, executed the project's test command, read a coverage report, and iterated toward a target coverage percentage.
Qodo marked the repository as no longer maintained on June 15, 2025 and invited users to fork it. The source remains available under AGPL-3.0 for historical use and experimentation, but it should not be adopted as a supported, actively developed testing product.
Past capabilities
Targeted uncovered code and iterated toward a configurable coverage goal.
Ran generated tests and retained candidates that passed and improved measured coverage.
Could run locally or through preview GitHub Actions workflows.
Used LiteLLM to call OpenAI and other compatible model providers with user-supplied credentials.
Availability
The archived source code has no purchase price and is licensed under AGPL-3.0. Users must supply and pay for their own LLM API usage, CI compute, maintenance, and security work. The old Qodo Cover Pro preview is not a current supported pricing offer.
Status checked . Review the historical source ↗
Current options
Coding
An actively developed coding agent that can generate and run tests within a broader repository workflow.
Explore Claude Code →Coding
An active multi-agent review product for finding logic, security, and quality issues in pull requests.
Explore Claude Code Review →Coding
An actively developed AI code editor for generating, running, and refining tests with direct developer oversight.
Explore Cursor →Questions
No. It became Qodo Cover, and Qodo marked the repository as no longer maintained on June 15, 2025.
The source is still available to fork under AGPL-3.0. Doing so means taking responsibility for dependencies, security, compatibility, model costs, and maintenance.
It used an LLM to propose tests, ran the project's test command, read the coverage report, and iterated when tests failed or coverage had not reached the configured target.

Get access to all our AI courses, hundreds of real-world AI use cases, live expert-led workshops, an exclusive network of AI early adopters, and more.
Get unlimited access to all of our current & upcoming industry-specific AI courses for the duration of your subscription.
To keep up with the rapid pace of AI, our team publishes AI implementation guides daily. Our library contains 300+ practical use cases to automate real-world work.
Join weekly, live, interactive sessions with industry leaders who are at the forefront of AI for hands-on implementation guidance and exclusive insights.
Network with an exclusive community of AI-first professionals who are working smarter with AI. Learn how early adopters are using AI in their work and businesses.