robotframework-agenteval is an open-source library for Robot Framework that enables automated testing of agentic stacks, including MCP servers, Agent Skills, SubAgents, and Hooks. It supports deterministic, LLM-judged, and coding agent-based evaluation, making it suitable for developers and QA engineers working with AI agents.
robotframework-agenteval sits in PulseGate's Testing & QA category. It focuses on automating and evaluating the testing of agentic stacks and MCP servers using Robot Framework and LLM-based methods. robotframework-agenteval is an open-source project aimed at test automation engineers and AI agent developers. The project is open source (Apache-2.0). robotframework-agenteval is available on the command line.
Behind robotframework-agenteval is manykarim, and the product first shipped in 2026. The project is developed in the open on GitHub with 194 commits in the last 90 days. Among its 5 catalogued features are agentic stack testing, LLM judge integration, and MCP server support. It exposes integrations via an MCP server.
Latest indexed changes and source events
Other apps tracked under the same category.
