RHEXADocumentation
RHEXA makes programs examinable for AI agents: an agent asks a question, RHEXA analyses the target locally and answers with evidence. This documentation covers installation, first steps, usage and operation.
Development status: RHEXA is not yet published as a
package. It is installed from source. The command and the MCP server are called
rhexa.
Getting startedFrom installation to the first evidence-backed answer in ten minutes.
InstallationPrerequisites, agent layer, engine, connecting your agent.
User manualConcepts, working with the agent, command line, evidence.
OperationUpdating, resources, troubleshooting, security.
FAQFrequent questions about RHEXA, REA and Ghidra.