Open source · Apache 2.0

Your company’s data, connected into one ontology

An open-source alternative to Palantir Foundry

Connect your databases, SaaS tools and documents. Foundry turns them into one ontology your agents can query, with a source behind every answer.

Try the sample company
Already signed up? Open Foundry

Foundry is built for a bigger screen: open this page on your computer to start.

Star on GitHub to find it later

Connect your databases, SaaS tools and documents. Foundry turns them into one ontology your agents can query, with a source behind every answer.

The Helix Foundry Explorer showing Acme's customers, invoices and contracts as one connected graph

Connects to the databases, tools and documents you already run

  • PostgreSQL
  • Neon
  • Supabase
  • PlanetScale
  • MySQL
  • Granola
  • Amazon S3
  • Stripe
  • PostHog
  • WorkOS
  • GitHub
  • Linear
  • Slack
  • Notion
  • Google Workspace
  • Cal.com

Ontology

One customer, not three copies of it

Your app database, Stripe and WorkOS each hold part of every customer. Foundry suggests one ontology that matches the same records across them.

  • Matched on keys you already have. Foundry finds the IDs your systems share and says how many rows matched.
  • Unsure matches can wait for review. A name it can't match for sure can go to a person to review instead of being guessed.
  • Every version is kept. Review and edit each draft, and go back to any version.
AccountMerged from 3 sources60 records
  1. PlanetScale · accountsthe anchor table60 of 60
  2. WorkOS · organizationsconfirmed by external_id60 of 62
  3. Stripe · customersconfirmed by metadata.account_id46 of 48

How it works

From scattered systems to one ontology

Connect a source, say what you want to know, and review the ontology Foundry drafts before it loads into HelixDB.

  1. Sync your sourcesConnect databases, tools and documents. Later syncs read only what changed.
  2. Say what you want to knowGive the ontology agent your goal, and it reads your tables and documents.
  3. Draft the ontologyTypes, links and rules, with the tables and documents each one comes from.
  4. Review and make it currentEdit the draft, then make a version current and load it into HelixDB.
  5. Explore and askBrowse the graph in the Explorer, or ask questions for cited answers.
DATAMODELSONTOLOGYANALYTICSWORKFLOWSINTEGRATIONS

Ask

Answers you can check

Ask in plain words. Foundry's agent reads your ontology step by step, and its answer cites each record, row and quote it used.

  • Every step is shown. See what the agent read, and open each step's details.
  • Answers cite their sources. Open each cited record, table row or document quote.
  • Conflicts can wait for review. When documents disagree on a value, it can hold it for you instead of picking one.

How many support tickets came in each month?

Example answer
  1. Read what the load holds its types, links and how many of each
  2. Found the support tickets 119 Support ticket records
  3. Counted them by month a path query over Support ticket

Support tickets grew from 4 in February to 28 in August, and June was the busiest month, with 33[1]. All 119 tickets in the load are counted[2].

  • Feb 4
  • Mar 3
  • Apr 11
  • May 20
  • Jun 33
  • Jul 20
  • Aug 28

Sources

  1. 1Step 3 Count support tickets by month
  2. 2Support ticket 119 records, from S3 · support_tickets.csv

The point

Nobody has to agree on a schema first.

Connect a source and Foundry drafts the ontology. You review and edit it, and every version is kept so you can go back.

Your data, your models

AI runs where your policy allows

On Helix Cloud, Helix runs Claude for you, or your own Anthropic key on Pro and Max. Self-hosted, use Claude, OpenAI, Azure OpenAI, Amazon Bedrock, Ollama or any OpenAI-compatible server.

  • Local with Ollama
  • Azure OpenAI
  • Amazon Bedrock on AWS
  • Claude
  • OpenAI
  • Gemini
  • Grok
  • Google Cloud
01

Sealed credentials

Passwords and API keys are sealed when you enter them. Your agent never sees them.

02

Read-only syncs

Connectors read your systems and never write back. Later syncs read only what changed.

03

Agents act as you

Through the Helix MCP, an agent has your role, and every change to your setup needs your confirmation.

04

Local stays local

Self-hosted, Foundry listens on 127.0.0.1 only, and your data stays on your machine unless you pick a hosted model.

Pricing

Start free. Pay for fresher data.

Plans are per workspace and differ mostly in how often your sources sync. Every plan drafts, loads and answers questions about your ontology.

Helix Cloud

Free

$0 a month

For trying Foundry on your own data.

  • Connectors, documents and API sources
  • Daily syncs
  • Ontology drafts and versions
  • Questions with cited answers
Start free
Helix Cloud

Pro

$100 a month

For teams that work from fresh data.

  • Everything in Free
  • Hourly syncs of what changed
  • Your own Anthropic key
Start free
Helix Cloud

Max

$500 a month

For data that has to stay current.

  • Everything in Free
  • Syncs every 15 minutes
  • Your own Anthropic key
Start free
Self-hosted · Apache 2.0

Your computer

$0 forever

For one person, with Docker. Your data stays on it unless you pick a hosted model.

  • The same build as Helix Cloud
  • Your own AI keys or a local model
  • No sign-in
Install guide

Enterprise: in your infrastructure

Your Kubernetes, your cloud or on-prem, with high availability, directory sync and your own models. See Foundry for enterprise.

Book a call

Each workspace's AI spend is capped each month. Compare plans in the docs, or read them as pricing.md.

FAQ

What is Helix Foundry?

Helix Foundry connects your databases, tools and documents, lets an agent draft an ontology over them, and loads it into HelixDB as one connected graph. You can explore it, see where its values came from, and ask questions whose answers cite their sources.

How is it different from Palantir Foundry?

Helix Foundry is open source under Apache 2.0 and starts free, on Helix Cloud or on your own computer. An agent drafts the ontology from the data you connect, so you can start without modelling everything by hand first.

Where can it run: Helix Cloud, our infrastructure or my computer?

Helix Cloud, at foundry.helix-db.com, is hosted for you, with scheduled syncs and workspaces for your team. For an organisation, Foundry deploys on your own Kubernetes, in your cloud or on-prem, with high availability: see Foundry for enterprise at /foundry/enterprise. The local install is free, for one person on their own computer, and starts with one Docker Compose command. There is no sign-in locally, so never expose it through a proxy, tunnel or port forward.

Can my team share it?

On Helix Cloud, yes. Each workspace has members with roles, and an agent connected through the Helix MCP acts with your role, so it can only do what you could do on the website. The local install is for one person.

Which AI models does it use?

On Helix Cloud, Helix runs Anthropic's Claude models for you, or your own Anthropic key on Pro or Max. On your computer, Foundry uses Claude or OpenAI when it finds an ANTHROPIC_API_KEY or OPENAI_API_KEY, otherwise Ollama, otherwise LM Studio. Settings › AI models switches to Azure OpenAI, Amazon Bedrock or any OpenAI-compatible server.

What does the local install need?

Docker with Compose v2, ports 3000 and 8333 free, and room for a few GB of images on the first start. Your data lives in Compose volumes, which docker compose down keeps. Never run docker compose down -v unless you mean to delete everything.

How does it use HelixDB?

Each load writes your ontology into HelixDB, an open-source graph database with native vector and full-text search, as one connected graph. Every value keeps where it came from: a table row, or a quote in a document. HelixDB is Apache 2.0 too.

Now there is nothing to host.

Helix Cloud runs the same open-source build, so you can connect a source and explore your ontology without standing up HelixDB, DuckDB and Ollama yourself.

Start free
Already signed up? Open Foundry

Foundry is built for a bigger screen: open this page on your computer to start.

Star on GitHub to find it later

Rolling it out to a team? Book a demo