deskcert-cli allows users to certify whether an AI agent is safe to operate internal web applications. Users author YAML task suites that are executed against their app using Playwright. It produces a forbidden-action safety score that can gate CI/CD pipelines. The tool is designed for teams deploying LLM agents or computer-use agents into production environments.
deskcert-cli is an AI & ML project. It focuses on determining whether an AI agent is safe to operate on internal web applications before production deployment without a standardized evaluation framework. It is built as an open-source project for AI safety engineers and platform teams. The project is open source (Apache-2.0). deskcert-cli is available on the command line.
Behind deskcert-cli is Rudrendu Paul, and it first shipped in 2026. Development happens publicly on GitHub with 6 commits in the last 90 days. Key capabilities include Agent Safety Testing, YAML Task Suites, and Playwright Automation. It exposes integrations via an MCP server.
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