AgentDB documentation

AgentDB gives your AI agent its own database. Your agent defines tables, stores records and files, and links them. It then finds them again with exact queries. Nobody writes SQL.

You can use AgentDB in three ways:

• Your AI client talks to AgentDB over MCP. Examples are Claude, ChatGPT, Cursor and Claude Code.
• You or a script call the REST API at https://app.agentdb.link.
• You run the agentdb command-line tool.

All three reach the same data with the same rules.

#New here?

1. Get started in about five minutes. You sign up, get a key and store your first records.
2. Connect your AI so your agent can use AgentDB by itself.
3. Read the concepts to learn the words this documentation uses.

#What you can do

• Give your agent a memory that lasts. Your agent creates objects such as contact and company with typed fields. See Concepts.
• Find exactly the records you need. Filter, sort, page, count and total your data. See Query your data.
• Search text across records. Turn on full-text search for an object and search by words. See Full-text search.
• Store and import files. Attach documents to records and import CSV or JSON files. See Files and imports.
• Share live dashboards. Your agent designs a page and AgentDB feeds it live, read-only data. See Dashboards and sharing.
• Run work on a schedule or on a change. Use webhooks, scheduled jobs and flows. See Automation.
• Keep a human in the loop. Approve or reject sensitive changes in the AgentHub. See Hub and approvals.
• Control who can do what. Invite people, give agents their own keys and set roles. See Accounts and security.
• Start from a ready app. Install a CRM, a to-do list or a Kanban board in one step. See App packages.
• Build your own app on it. Use AgentDB as the database of a website, CRM or dashboard, in your own language. See Build with AgentDB.
• Fix a problem. Look up an error code and what to do next. See Troubleshooting.

#Reference

• CLI reference: every agentdb command and option.
• Field types: every field type with its rules and examples.
• File types: which files you can upload.
• Release notes: what changed in each version.

#For AI agents

Agents can read a compact, machine-readable version of this documentation. See Documentation for agents.

An agent connected over MCP can also ask AgentDB itself. The agentdb_capabilities tool lists every operation with its input and an example. See Discover operations.

#Reference by feature area

• WorkspacesFind, create, select, rename, delete and restore workspaces (projects).
• SchemaObject types, typed fields, unique keys, indexes; history and undo.
• RecordsCreate, read, update, upsert, delete, archive, restore and merge records.
• RelationshipsLink and unlink records; list a record's links.
• Query and searchExact queries (operators per field type), roll-ups, totals by date bucket, full-text search.
• FilesUpload, attach, download, version, search and share files.
• Import and exportImport CSV/JSON/JSONL files and export workspace data.
• Views and dashboardsSaved views, rendered and published views, live dashboards.
• AutomationWebhooks, scheduled jobs (once/cron/RRULE) and trigger flows.
• Channels and inboxChannels and messages, your inbox, shared conversations (handoff).
• Approvals and AgentHubPropose sensitive changes; a signed-in person decides in the AgentHub; approval policies.
• CalendarCalendars, events, availability, free slots, ICS import/export.
• KnowledgeKnowledge items with citations, proposals, reviews and versions.
• IntegrationsConnectors to outside systems: sync, send, inbound events.
• Package and template operationsInstall ready-made schemas and apps (CRM, todos, kanban, CMS, forms...).
• PublishingCMS delivery and revisions, public forms, content dispatch.
• Access and permissionsNamed agents and their keys, permissions, who may do what.
• AdministrationRetention and lifecycle settings, integrity checks.
• DiscoveryFind operations (agentdb_capabilities) and run any of them (agentdb_execute).