Star us on GitHub Open source Self-hosted MCP-native

Agents get the data.
You keep control.

Datris is the open-source data control plane for AI agents. Your agents ask for data; Datris acquires it, validates it, and lands it in the stores you already run — credentials brokered through Vault, every action policy-gated, and every landed row traceable to the run, the commit, and the source.


See how the Assistant works
Datris Assistant online
I'm looking for corporate earnings data.
Happy to set that up. Before I build anything, two quick questions so I don't guess:
— Source: SEC EDGAR (free, official), Polygon.io, or Alpha Vantage?
— Scope: which tickers, and how far back?
SEC EDGAR, Mag 7, last 2 years.
▸🔑Inspecting secret sec-edgar✓
▸✨Creating pipeline corporate-earnings → mongodb✓
▸✨Creating tap corporate-earnings✓
Test run looks good — flat fact records flowing across all 7 tickers. Running the real load now.
▸▶Running tap corporate-earnings✓
Done. 24,217 fact records for the Mag 7 loaded into datris.corporate-earnings in ~4 seconds.
Provenance
Pipeline corporate-earnings · Run f3a91e2c
Script commit a3f19c2 · As-of 2026-08-25 14:32 UTC
24,217 rows written · 0 quarantined · 0 duplicates
One thing to flag for the recurring runs: each weekly run currently appends all matching facts. If you'd rather upsert, I can set keyFields on the pipeline.
→ Open tap corporate-earnings
Describe the data you want to ingest… Send

01

From a sentence to a scheduled pipeline

Describe the data you want. Datris generates the tap, the schema, and the validation rules, runs it, confirms the rows landed, and puts it on a schedule. One shape for every source, not ten dialects.

02

The agent never holds a key

Credentials live in HashiCorp Vault and are brokered to the tap at run time. The agent gets a scoped API key with an explicit capability bundle. Agent-written code runs in a sidecar with no platform credentials inside.

03

Every row cites its source

Each landed row is traceable to the pipeline, the run, the script commit, and the source it came from. The chat transcript is never the system of record. The receipt is.


Your agents already do this work. Without a control plane, they do it badly.

The choice isn't Datris vs. an ETL tool. It's whether the agent operates through a governed surface, or improvises against your infrastructure.

Without Datris
Every agent, wired by hand
  • 70+ low-level tool integrations to build and maintain per agent
  • Credentials scattered across agent configs, env vars, and prompts
  • No audit trail — the chat log is the record
  • Chat-only state; every session starts from zero
  • Every one-off question leaves a new table behind
  • Regenerating an agent script quietly loses sync bookmarks
  • Failure diagnostics: raw stack traces you paste into another chat
  • Generated code lives in a database column, no diff, no history
With Datris
One control plane, every agent
  • 70+ capabilities behind one MCP surface — agents learn one door
  • Vault-brokered credentials — the agent never holds a key
  • Every run recorded; every generated script versioned in git
  • Durable pipelines and platform-held sync bookmarks
  • Live Read answers the one-off without landing anything
  • Regenerate a script freely — the state was never in the code
  • AI Error Explanation — root cause in plain English
  • Agent-written code runs in an isolated container with no keys inside


Self-host anywhere you want

Datris runs on-prem, in any cloud, or on your laptop — anywhere Docker runs. Open source under AGPL-3.0, built on proven infrastructure. No proprietary services, no vendor lock-in, no surprise bills. There is no managed service; your deployment lives inside your perimeter.

$ curl -fsSL https://get.datris.ai/install.sh | sh

One command. Then open http://localhost:4200 in your browser. Your first pipeline in under a minute.

Planning a real deployment? See sizing and reference deployments.


Know before it's public.

Release notes and security advisories for self-hosted deployments. No marketing, no cadence promises. Unsubscribe with one click.


Run it tonight. License it when it matters.

Every feature ships in the open-source build. A commercial license adds the contract, the named engineer, and the advisories.


Send us a message

Questions, feedback, or just want to chat — we'd love to hear from you.