Valved

Agent-native data engineering, from natural language to production pipelines. A control plane plus an AI harness over independently-versioned dlt + dbt + sql — self-hosted, Apache 2.0.

Get started View on GitHub

From intent to a reviewable pull request

Valved takes a goal in plain English — “make stg_orders incremental”, “ingest the Stripe charges API into a Snowflake table” — turns it into a reviewable plan, and, when you approve, materializes the working code and opens a pull request in your repo: dbt models, Python dlt sources, SQL, tests, schema docs.

It verifies its work by executing it (dlt pipeline run, dbt build) until green — not by guessing. Then the control plane schedules, runs, and monitors those pipelines on a durable job queue.

valved plan "ingest the Stripe charges API into raw_stripe, then a staging model stg_charges"
valved build <plan_id>          # writes the dlt source, the dbt model, pipelines/<name>.toml
valved run <pipeline> --watch   # execute on demand; data lands in your warehouse
valved deploy <pipeline>        # open a reviewable PR with the built code

AI harness for data work

A Claude-Code-style agentic engine — a main orchestrator that delegates to domain subagents (a DLT engineer, a dbt engineer, a pipeline engineer, a recovery engineer, an explorer), armed with terminal-grade tools, running behind a permission gate, that verifies by executing.

A narrow control plane

Scheduled execution of dlt + dbt + sql pipelines over a Postgres job queue: multi-worker claiming, crash-recovery, retries, structured logs, and alerts. Deliberately not a general-purpose orchestrator.

Headless by default

Every action is available four ways with full parity: the valved CLI, a FastAPI REST API, an auto-generated MCP server (drive it from Claude Desktop / Cursor / Claude Code), and a static HTML UI.

Bring your own, or build with AI

Build-with-Valved (agents author components into your repos) or orchestration-only (bring existing dlt/dbt/sql; Valved just composes, schedules, and monitors). Both are first-class.

Start here

IntroductionWhat Valved is and who it's for.

InstallationInstall the CLI and stand up the Postgres state store.

Quickstartinit → plan → build → run → deploy in a few minutes.

The core loopIntent → Plan → Build → Run → Deploy → Schedule → Observe.

Open source & governance. Valved is Apache 2.0 and feature-complete for single-team self-hosters — no API endpoints or MCP tools are gated behind any commercial offering. See OSS_COMMITMENT.md for what’s permanently open.