Skip to main content

Glossary

Who This Is For

This page is for every author and reader of xAgent documentation.

What It Is

The glossary is the source of standardized terminology for xAgent documentation. Add new terms here when they are introduced.

Core Terms

TermStandard Meaning
AgentThe entity responsible for understanding goals, planning, scheduling Tools, and providing feedback
TaskA goal unit executed by an Agent
ToolThe smallest external capability an Agent can invoke
SkillA reusable set of task methods, constraints, and Tool usage guidance
ConnectorA protocol bridge to an external system and the source of its capability declarations
ProcessSandboxThe platform isolation boundary for untrusted processes, responsible for file mounts, environment, process trees, and resource limits
Runtime AssetsExecution dependencies independently installed and verified by xAgent, then provided read-only to ProcessSandbox
Execution LeaseThe minimal file view, overlapping-write coordination, and file-change commit capability that WorkspaceFileService provides for one process execution
MemoryThe memory system for long-term context
SubAgentAn independent execution unit for long-running tasks
SessionAn interaction context between a user and an Agent
WorkspaceThe space for files, context, and intermediate artifacts used by an Agent during a Task
TriggerA mechanism that turns a future time or external event into a Session Task

When to Use It

User guides, technical references, and maintenance documentation should all follow this glossary. A user guide can explain a term in plain language, but its core meaning must remain consistent.

Writing Rules

When writing documentation:

  • Do not invent synonyms without a reason.
  • Do not describe planned capabilities as implemented.
  • Update this page and related documentation when adding a term.
  • Explain how to use a feature in user-facing pages; reserve internal boundaries for technical references.