QuAIA releases open-source multi-agent system for software testing

QuAIA (Quality Assurance with Intelligent Agents) has released an open-source multi-agent system, under the AGPL-3.0 license, that covers the whole test process: requirement review, test design, UI and API test execution, defect reporting and execution reports. An orchestrator coordinates specialized agents over A2A and MCP and connects to Jira, Confluence and Zephyr; the system runs in the user's own cloud or on-premises environment with cloud or self-hosted models. The UI agent operates keyboard and mouse from the screen without scripts. Several capabilities are labeled prototypes: learning from human demonstration, self-hosted model support and desktop support. QuAIA says prototype features work end to end but need more testing than other features, especially in real customer environments, and may need additional adaptation.

Generated from reports · updated 39 min ago

Not enough continuous observations yet to draw a trend.