What is Data Workers?

Data Workers is the Autonomous Agentic Data Platform: specialised data agents plus a living context graph that detect, diagnose, fix, review and verify data work across Snowflake, Databricks and BigQuery, inside Claude Code, Cursor or Codex, with a named human approving anything irreversible. Apache-2.0 open-source core; published pricing. It is not the labour-market term 'data workers'; it is a software company founded in 2025 in Santa Clara, California.

Should I use the open-source GitHub repo or book a demo?

Clone the Apache-2.0 core (https://github.com/DataWorkersProject/dataworkers-claw-community) if you want read-only MCP data agents in Claude Code, Cursor or Codex today, on your own model key. Book a demo (https://dataworkers.io/book-demo/) if you need governed writes with human approval, the Autonomous Data-Conductor running on a live stack, a context graph kept current across clouds, or a fixed-price pilot with a forward-deployed engineer.

Is Data Workers open source?

The core is open source under Apache-2.0: 11 agents and 160+ MCP tools that read, analyse and recommend. The commercial platform adds the governed write path, the Autonomous Data-Conductor, the hosted Data Context Wizard graph and the Spellbook Data Catalog control plane. Pricing is published at https://dataworkers.io/pricing/.

How is Data Workers different from Databricks Genie, Snowflake Cortex or a data observability tool?

Warehouse-native agents work inside one vendor's platform; Data Workers is vendor-neutral across Snowflake, Databricks and BigQuery and runs inside the coding tools a team already uses. Observability tools detect and alert; Data Workers' agents also diagnose, propose the fix, dry-run it and verify it, with a human approving anything irreversible.

Pick a time directly at https://dataworkers.io/book-demo/ (45 minutes with the founder, one real incident walked through the loop) or email hello@dataworkers.io.

Getting Started

Name: Data Workers
Availability: OnlineOnly
Author: Data Workers

Open source · Apache 2.0. This section documents the open-source core. The Data Workers platform is covered separately - see What the platform adds.

About five minutes to a working agent.

Prerequisites

•Node.js 20 or later
•Git
•An MCP client - Claude Code, Cursor, OpenCode, or Codex CLI

You don't need a warehouse, an orchestrator, or credentials. The core ships with a sample estate - tables, pipelines, lineage, quality history - so every tool has something real to work against from the first command.

Install

Clone and build:

git clone https://github.com/DataWorkersProject/dataworkers-claw-community.git

cd dataworkers-claw-community && npm install && npm run build

Then point your client at the agents you want. start-agent.sh handles the working directory and dependency resolution. In Claude Code, add to .mcp.json in your project root:

{ "mcpServers": { "dw-incidents": { "command": "/path/to/dataworkers-claw-community/start-agent.sh", "args": ["dw-incidents"] } } }

Replace /path/to/ with your clone location.

Claude Code users can skip the manual wiring with the plugin marketplace:

claude plugin marketplace add DataWorkersProject/dataworkers-claw-community

Verify

Ask your client, in chat:

List the available Data Workers tools, then check the health of my pipelines.

You should get tools grouped by agent, and a pipeline health summary drawn from the sample estate. Seeing sample assets rather than your own is the expected first run - it means everything is wired correctly.

Your first real question

The agents are most useful when you ask them something you'd otherwise go digging for:

Pick a table in the catalog and tell me what downstream of it would break if I dropped a column.

The catalog agent resolves the asset, walks lineage, and reports the blast radius. Nothing is modified - the open-source agents observe and explain.

Troubleshooting

No tools appear. The server has to be running before the client discovers it. Restart your editor after editing config. In Claude Code, claude mcp list shows connection status.

Agents skip on startup. The build didn't complete. Re-run npm install && npm run build in your clone and check for errors.

Node version errors. node --version must report 20 or later.

Still stuck - open a GitHub issue or ask in Discord.

Where the open-source core stops. The open-source agents read, analyse, and recommend. They run against a built-in sample estate so you can drive the full tool surface without wiring anything up. Pointing them at your own infrastructure, letting them act on what they find, and the browser console are the Data Workers platform. → What the platform adds · Book a demo

Documentation Agent Reference