Backend for AI agent workflows. Private structured data for trusted agents.
Any agent.
Any workflow.
One backend.
Rowset is the open-source, self-hostable backend for AI agent workflows. Give agents private, searchable structured data through MCP, REST, or CLI—without building another backend.
Built in the open
Open source. Self-hostable.
Run Rowset in our cloud or on your own infrastructure. Inspect the code, shape the roadmap, and keep deployment under your control.
Inside Rowset
See what your agents changed.
Review recent datasets, row counts, schema, and sharing state before the next agent run.
AI agent examples
Give your agent a workflow it can keep up to date.
Simple primitives
A private database for agent-managed work.
Rowset stores structured rows with stable indexes, schema, instructions, and search. Agents access them through MCP, REST, or CLI—without direct credentials to your production database.
- STORE
- Typed, indexed rows
- Stable business keys, generated IDs, descriptions, links, and flexible column types.
- FIND
- Exact and semantic search
- Retrieve a known row or search by meaning with vector embeddings.
- MOVE
- Five export formats
- Take snapshots as CSV, JSONL, XLSX, SQLite, or Parquet.
Three steps to agent-ready data
Connect once. Then ask your agent to build.
01 / CONNECT
Copy the setup prompt
Give a trusted agent the Rowset setup prompt. It can recommend MCP, REST, or CLI and configure access with a bearer API key.
02 / DESCRIBE
Name the workflow
Tell the agent what to track. It creates the dataset, schema, and stable index.
03 / DELEGATE
Let it manage the rows
The agent reads, writes, searches, exports, and shares results through authenticated tools.
Private by default
Your next agent workflow needs somewhere to live.
Start with full product access for 7 days. Keep control with bearer-key authentication, explicit sharing, and exports whenever you want them.
Start your 7-day trial →