Glossary
| Term | Definition |
|---|---|
Agent |
A configured run profile of the engine; built-in profiles are
|
Subagent |
An agent of type |
Agent Profile |
The data record for an agent: name, safety tier, agent type and config overrides [vibe/core/agents/models.py:48-94]. |
Agent Loop |
The orchestrator that runs a conversation turn — LLM call plus tool execution — until no tool call remains [vibe/core/agent_loop.py:855-937]. |
Tool |
A |
Tool Permission |
The tier — |
Skill |
A reusable component declared by a |
MCP Server |
An external tool provider reached over the Model Context Protocol
( |
Connector |
A remote tool source registered through the connector registry [vibe/core/tools/connectors/connector_registry.py]. |
Hook |
A TOML-declared shell command run on a lifecycle event such as
|
Session |
A persisted conversation: a folder of |
Compaction |
Summarising the conversation history when the context nears the model’s token threshold [vibe/core/agent_loop.py:1681-1749]. |
Plan Mode |
The read-only |
Teleport |
Handing a local session to a remote Vibe Code workflow [vibe/core/teleport/teleport.py:46-150]. |
Nuage |
The remote cloud workflow backend (French for "cloud") [vibe/core/nuage/client.py:22-100]. |
Trust Folder |
A directory the user has explicitly trusted; only trusted folders load
project |
ACP |
Agent Client Protocol — the JSON-RPC-style protocol the |
VIBE_HOME |
The user-state directory, |
Feedback
Was this page helpful?
Glad to hear it! Please tell us how we can improve.
Sorry to hear that. Please tell us how we can improve.