Three steps.
One sentence to a running pipeline.
No SQL. No YAML. No DAG editors. Describe what you want — the AI agent handles schema discovery, PII detection, and pipeline execution, pausing at every step for your approval.
The three steps, expanded
Here's exactly what happens from the moment you type to the moment rows are flowing.
Describe it in plain English
Type what you want — the same way you'd ask a teammate in Slack. The LLM agent parses your intent and extracts every parameter it needs:
- Source: Which system to read from (Shopify, MySQL, Stripe…)
- Destination: Where to write (Postgres, BigQuery, S3…)
- Cadence: Hourly, daily, real-time CDC, or on-demand
- PII rules: "mask emails", "exclude phone numbers"
- Table filters: "only the orders and products tables"
If the source isn't in the built-in catalog, the AI Tool Generator builds an MCP connector from any REST or GraphQL docs URL — auth, schema discovery, and pagination included.
YOU
Sync my Shopify orders and products to Postgres hourly. Mask customer emails.
ASSISTANT
Understood: Shopify Admin (GraphQL) → PostgreSQL, hourly batch, masking customer.email. Create and run this pipeline?
Confirm Pipeline
Review the plan, approve each gate
rsync.ai never moves data without your explicit sign-off. Every pipeline passes through four human-in-the-loop gates:
Connection test
Agent verifies it can reach source and destination with the credentials you supplied.
Schema discovery
Agent scans source tables, infers column types, and proposes the destination schema.
PII scan
Every column is checked for emails, phones, IDs, and addresses. You choose: mask, hash (SHA-256 or HMAC), drop, or pass-through — per field.
Final approve
You confirm the table list, cadence, and rules. Only then does the pipeline start.
Pipeline setup gates
Pipeline runs — you watch
Once you approve, rsync.ai kicks off a Temporal workflow. No servers to babysit, no cron jobs to monitor.
Live row counts
Watch rows land in your destination in real time from the executions dashboard.
Checkpointed cursors
Temporal persists state at every checkpoint — a crash mid-sync resumes from exactly where it left off.
Debezium CDC for databases
Postgres and MySQL changes propagate to your destination in seconds via log-based CDC.
Replayable event log
OpenTelemetry traces let you replay any past run. Debug without calling an engineer.
Under the hood
Production-grade infrastructure — not a toy. Every component is open or source-available.
MCP connectors
Connectors implement the Model Context Protocol — the open standard for AI agent tool use. Any LLM (Claude, GPT-4, Ollama) can call them directly.
Debezium CDC
Log-based change data capture for Postgres and MySQL. Row-level inserts and updates reach your destination in seconds.
Temporal workflows
Every pipeline is a durable Temporal workflow with checkpointed state, automatic retries, and full replay.
OpenTelemetry
End-to-end traces for every sync run. Inspect span timings, row counts, and errors without reading logs.
Your VPC. Your data.
One command.
Today rsync.ai runs as a managed Cloud you can start free. From July 2026 you'll also be able to run the entire stack inside your own infrastructure — credentials AES-256 encrypted at rest with a key you control, data never leaving your network.
- Full stack on Docker Compose — agent, Temporal, Debezium, UI
- AES-256 encrypted credentials at rest
- Ollama support for fully local LLM inference
- Source-available under Elastic License 2.0
- No per-row pricing. Flat monthly fee.
Install & run
$ curl install.sh | bash
# or manual quickstart:
$ docker compose up
Services
- rsync-agent
- temporal
- debezium
- kafka
- postgres
- redis
Your stack
- Any LLM (cloud / Ollama)
- Postgres / MySQL source
- Any destination
- Your VPC / bare metal
Ready to try it?
MCP connector generation on every plan. No per-row fees. Cancel any time.