Helix Foundry for CTOs

Helix Foundry connects your databases, tools and documents into one ontology in HelixDB, and answers questions with citations to the records it used. It is open source under Apache 2.0, runs on Helix Cloud, your Kubernetes or on-prem, and works with the AI models you choose, or none of ours.

Book a meeting

How it works

  • One graph, not a stack of stores. Each load writes the ontology into HelixDB, a graph database with native vector and full-text search, so there is no separate vector store or search cluster to keep in sync.
  • No schema project first. Connect a source and an agent drafts the ontology. Your team reviews and edits it, and every version is kept.
  • Ontology as code. Versioned, and editable by hand, by agent or through the API.
  • Read-only connectors. Connectors read your systems and never write back. Later syncs read only what changed.

Where it runs

  • Helix Cloud. Managed for you, with scheduled syncs and workspaces for your team.
  • Your infrastructure. Your Kubernetes in your own cloud account, or on-prem, with high availability and failover.
  • One computer. Free for one person, started with one Docker Compose command.

Models and agents

  • Your choice of model. Self-hosted, use Amazon Bedrock, Azure OpenAI, Claude, OpenAI, Ollama or any OpenAI-compatible server on your own keys. On Helix Cloud, Helix runs Claude for you, or your own Anthropic key on Pro and Max.
  • Or none of ours. Your own agents query the graph over MCP in SQL, Cypher or JSON.
  • Agents act as their user. Through the Helix MCP, an agent has its user's role, and every change to your setup needs that user's confirmation.

Lock-in and cost

  • Apache 2.0. Helix Foundry and HelixDB are open source, and Helix Cloud runs the same open-source build.
  • Proof before procurement. Run a proof of concept on your own data before you talk to anyone.
  • Plans per workspace. Helix Cloud costs Free $0, Pro $100 and Max $500 a month, differing mostly in how often sources sync, with AI spend capped each month. Enterprise is priced for your scale.

FAQ

Is Helix Foundry an open-source alternative to Palantir Foundry?

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

Which systems does it connect to?

Databases such as PostgreSQL (including Neon and Supabase) and MySQL (including PlanetScale), files in Amazon S3, uploaded documents and API sources, and tools such as Stripe, PostHog, WorkOS, GitHub, Linear, Slack, Notion, Google Workspace, Granola and Cal.com.

How do our own agents and apps use it?

Agents connect through the Helix MCP with their user's role, or query the graph directly in SQL, Cypher or JSON. The ontology itself can be edited through the API.

What do we have to run ourselves?

Nothing on Helix Cloud, which runs the same open-source build for you. Self-hosted, Foundry deploys on your own Kubernetes, in your cloud account or on-prem, with high availability. Enterprise plans include a named contact.

How do we evaluate it?

Try it free on your own data first: on Helix Cloud's free plan, or on one computer with Docker Compose. Then book a meeting to plan a deployment in your infrastructure.