Glossary
Quick definitions. No fluff. Click through to the linked pages for more depth.
| Term | Definition |
|---|---|
| Assistant | Your personal AI entity. Has a name, personality, memory, and the ability to take actions on your behalf. Defined by workspace files and powered by Claude. |
| Workspace | The folder at ~/.vellum/workspace/ containing your assistant's identity, personality, skills, databases, and configuration. See The Workspace. |
| Daemon | The local background process (TypeScript/Bun) that runs your assistant. Handles conversations, memory, tool execution, and skill management. Communicates with the desktop app via HTTP and SSE. |
| Gateway | The public ingress point that receives webhooks from external channels (Telegram, Slack, Twilio, WhatsApp) and forwards them to the daemon. Keeps the daemon off the public internet. |
| Skill | A bundle of tools, instructions, and configuration that gives your assistant a specific capability (e.g., Gmail, Browser, Computer Use). About 30 are built-in. See Skills & Tools. |
| Tool | A single atomic action your assistant can take (e.g., file_read, browser_navigate, gmail_draft). Each tool has a risk level that determines whether it needs your approval. |
| Channel | A way to communicate with your assistant. Available channels: desktop app (macOS), iOS, Telegram, Slack, WhatsApp, phone calls, email, and CLI. See Channels. |
| Memory | Information your assistant extracts and saves from conversations for future reference. Six kinds: identity, preference, constraint, project, decision, event — each with different lifetimes. Retrieved via hybrid search (semantic + keyword). See Memory & Context. |
| Guardian | You — the primary owner of the assistant. Guardians have full access to memories, workspace files, tools, and credentials. |
| Trusted contact | A verified person who can message your assistant through external channels. They can chat but can't access your memories, modify your workspace, or use sensitive tools without guardian approval. |
| SOUL.md | The file defining your assistant's personality, core principles, behavioral rules, and preferences. Loaded into every conversation. Editable by you or your assistant. |
| IDENTITY.md | The file containing your assistant's name, nature, personality summary, emoji, and style tendency. Loaded into every conversation. |
| USER.md | The file where your assistant stores structured information about you — name, pronouns, locale, work role, preferences. Loaded into every conversation. |
| BOOTSTRAP.md | The onboarding script your assistant follows for your first conversation. Guides it through discovering its name, personality, and your needs. Deleted automatically when onboarding completes. |
| Sandbox | The security boundary around ~/.vellum/workspace/. Tools running inside the sandbox can read and write workspace files freely. Enforced at the OS level (sandbox-exec on macOS, bubblewrap on Linux). |
| Host tools | Tools that run on your actual machine outside the sandbox (e.g., host_file_read, host_bash). Always require your permission. |
| Risk level | Every tool is classified as low, medium, or high risk. Low-risk tools run automatically; medium and high-risk tools prompt for approval. See The Permissions Model. |
| Trust rules | Persistent allow/deny rules stored in ~/.vellum/protected/trust.json. Accumulated from your approval decisions over time. Each rule has a tool, pattern, scope, decision, and priority. |
| Permission prompt | The dialog that appears when your assistant needs approval. Shows what it wants to do, the risk level, and offers options from one-time allow to persistent rules. See The Permissions Model. |
| Computer use | The ability to see and control your Mac via accessibility APIs and screenshots. Perceive → verify → execute → observe loop, capped at 50 steps per session. macOS only. See Computer Use. |
| Conversation | A persistent message thread with your assistant. Workspace files are loaded at the start. History is stored in SQLite and can be compacted (summarized) when it gets long. |
| Private conversation | A conversation with an isolated memory scope. Memories from a private conversation can't leak into other conversations, but it can still read from your shared memory pool. |
| Context compaction | Automatic summarization of older messages when a conversation approaches the context window limit. Preserves goals, decisions, and key artifacts while removing filler. |
| Playbook | Trigger-action automation rules for handling incoming messages. When a message matches a trigger pattern, the assistant automatically responds, drafts, or notifies. See Playbooks. |
| Watcher | A polling system that monitors external services (Gmail, Calendar, GitHub, Linear) for changes and notifies you when something happens. See Watcher. |
| Schedule | A recurring or one-time automated action using cron syntax, RRULE, or ISO 8601 timestamps. Can execute tasks or send notifications. See Schedule. |
| Task | A work item in your personal task queue. Can be ad-hoc or based on a reusable template. Has priority tiers (high, medium, low) and status tracking. See Tasks. |
| Subagent | An autonomous background agent spawned by your assistant for parallel work. Runs independently with its own context, reports back when done. See Subagent. |
| CES | Credential Execution Service. A separate process that handles credential-bearing operations in isolation, so your assistant never sees credential values in plaintext. |
| Platform Managed | A hosting option (coming soon) where your assistant runs in Vellum's cloud instead of on your machine. Same capabilities and security model, hosted for you. |
| Surface | An interactive visual element (card, table, form, app) that your assistant creates and renders in the chat. Used via the ui_show tool. |
That's the conceptual foundation. Next up: Trust & Security for the full picture on privacy and permissions, or the Skills Reference for details on every built-in capability.
On this page