The AI-native data pipeline platform.
Describe your data workflow in plain English. rsync.ai plans, validates, and executes pipelines — generating the connector from the source's API docs when one doesn't already exist — while you stay in control of every step.
One platform, no catalog ceiling. No per-row pricing.
Live on rsync.ai Cloud today — self-hosting on your own infrastructure arrives soon.
One sentence.
A running pipeline.
Watch the agent turn a plain-English request into a running MySQL→Postgres pipeline — discovering the schema, planning the sync, and clearing every validation gate before a row moves. About 15 seconds, start to finish.
Sound familiar? You're not alone.
Three walls every data team hits. Here's how rsync.ai removes each one.
rsync.ai generates the connector from its API docs in minutes. No ticket, no sprint, no waiting.
Describe the change in plain English. The agent handles schema discovery, PII scanning, and approval gates.
No per-row or per-MAR pricing — you're billed on data volume (GB moved): a monthly GB allowance plus a flat per-GB rate beyond it. Start with a free month (10 GB included), and pipelines pause at your cap instead of running up a surprise bill. Managed cloud today; self-hosting in your own VPC is coming soon.
What's inside
rsync.ai
Six surfaces that work together: chat-driven pipeline creation, data exploration, an AI MCP connector builder, schema discovery, live monitoring, and an MCP server generator.
Describe it. Approve it. Done.
Type a request in plain English. The LLM agent parses source, destination, cadence, and PII rules into a Temporal workflow with human-in-the-loop approval gates.
- LLM planner — heuristic + DAG strategies
- Temporal workflow under the hood (durable + resumable)
- Approval gates at every critical step
Everything a data team needs.
Cloud-hosted. Live in minutes.
rsync.ai gives analysts, ops leads, and data heads a full pipeline platform — natural-language setup, real CDC for relational sources, PII detection, and an AI MCP connector builder for any API.
Anyone on your team can build pipelines
Your analyst, ops lead, or PM can create a data pipeline by chatting with rsync.ai. The LLM agent breaks the request into steps — no SQL, no YAML, no DAG editors.
You approve, AI executes
Every critical step — connection, table selection, PII rules, schema changes — pauses for explicit approval via a human-in-the-loop gate. Nothing moves until you say yes.
AI generates MCP connectors for any REST or GraphQL API
Paste an API docs URL or OpenAPI spec. rsync.ai reads it, generates a versioned MCP connector with auth, schema discovery, and pagination, and ships a Docker image in minutes.
Real-time CDC for Postgres, MySQL, SQL Server & MongoDB
Log-based change data capture (Debezium) for Postgres, MySQL, and SQL Server, plus MongoDB change streams, keeps destinations in sync within seconds. SaaS sources sync on a schedule you describe in plain English.
See exactly what's happening, always
Live row counts, run history, error alerts, and OpenTelemetry traces (SigNoz integration included). Replay any past run from the event log to debug.
Chat with your data — in plain English
Ask a question in plain English and rsync.ai writes the SQL for you — schema-aware, on the data you just synced. Drop into the full SQL workbench (CodeMirror 6, autocomplete, click a column to insert it) whenever you want, and export to CSV, TSV, or JSON or send results to Metabase or Superset.
PII caught before a single row moves
rsync.ai scans every column for personal data — emails, phones, IDs, addresses — and asks for per-field rules. Choose mask, hash (SHA-256/HMAC), drop, or pass-through.
Self-hosting in your own VPC
Cloud-first today. Self-hosting is coming soon — run the full stack in your own VPC via Docker Compose, with AES-256 encrypted credentials and Ollama for fully local LLM inference.
Per-pipeline namespace isolation
Each pipeline writes into its own destination schema (e.g., shopify.orders, shopify_brand_b.orders) with collision detection and ownership gating — Fivetran/Airbyte-style multi-tenant safety.
Move any file format between cloud storage
Byte-identical file copy between S3, GCS, and Azure Blob — PDFs, images, Parquet, video, any binary. No parsing, no re-encoding. SHA-256 integrity check on every transfer and a metadata catalog tracking name, size, mime type, and last-modified for incremental re-sync.
Connect what you actually use
Curated connectors for the databases, files, and SaaS tools most teams need — each one an MCP connector any LLM can call as a tool. Need a warehouse or a niche API? The AI Tool Generator builds a versioned MCP connector from any REST, GraphQL, or OpenAPI docs URL in minutes.
Point the AI Tool Generator at any REST, GraphQL, or OpenAPI docs URL and it produces a versioned MCP connector in minutes — auth, schema discovery, cursor pagination, and a Dockerfile included. Any LLM can call it as a tool.
Built for teams that care about security & control
AI doesn't move your data silently. Schema changes are surfaced, PII is flagged, and every plan is reviewed before it executes — on production-grade infrastructure with audit-friendly logging and encryption you can verify.
Real pipelines, built in minutes — not sprints
No connector tickets, no per-row invoices, no DAGs to babysit. Describe the sync and rsync.ai does the engineering.
Your first pipeline,
live in minutes.
Sign up for rsync.ai Cloud and build your first pipeline in plain English — real CDC, PII scanning, and a curated set of MCP connectors (generate any other on demand), with no infrastructure to manage. Prefer your own VPC? Self-hosting is coming soon.