What do you want to do?
3 use cases
-
Turn your company's databases and docs into one queryable graph
Run Foundry locally, connect a database, let the agent draft an ontology and load it into HelixDB.
- REPO
HelixDB/helix-foundry - Data and analytics
- Intermediate
View prompt
Run HelixDB/helix-foundry locally with Docker Compose, connect <database>, review the ontology the agent drafts, load it, and ask: <question>. Show the cited rows behind the answer.
- REPO
-
Ask cited questions across Stripe, GitHub and Linear
Connect SaaS sources and ask questions whose answers trace back to the exact record.
- REPO
HelixDB/helix-foundry - Data and analytics
- Intermediate
View prompt
In HelixDB/helix-foundry, connect Stripe, GitHub and Linear, load a graph linking customers, repos and issues, and answer: which customers paying over <amount> have open bugs? Cite each record.
- REPO
-
Load PDFs, Markdown and CSV files into a graph you can question
Upload documents and table files into Foundry so they join the same graph as your databases.
View prompt
Use HelixDB/helix-foundry to load <folder of PDFs and CSVs>, draft an ontology that links them, and answer <question> with quotes from the source documents.
Quick start with Helix Foundry
- Check you have what it needs: Docker with Compose v2 to run locally; Optional: ANTHROPIC_API_KEY or OPENAI_API_KEY in the shell for Claude or OpenAI; Node 24 and pnpm only for developing the site.
- Open HelixDB/helix-foundry on GitHub and read the README and license.
- Run
git clone https://github.com/helixdb/helix-foundry.gitandcd helix-foundry - Start it with
docker compose up -d --wait(export ANTHROPIC_API_KEY or OPENAI_API_KEY first if you want Claude or OpenAI) - Open http://localhost:3000; there is no sign-in
- Connect PostgreSQL or another source, or choose Use the sample for the Acme Corp demo
These steps come from our top use case, Turn your company's databases and docs into one queryable graph, which also has a copy-paste agent prompt.
Use this in your AI agent
Ask your agent
Using the Deduped MCP, get the setup steps for HelixDB/helix-foundry
Add Deduped to Claude Code once
claude mcp add --transport http deduped https://dedupedai.com/mcp
Every Monday: the 5 hottest repos and exactly how to use them. Free, one email a week, unsubscribe anytime.
Get them freeAbout this repo
- Who it is forData and ops teams who want one queryable graph over scattered company data with answers that cite their source.
- Why it is hot1.9k stars, launched 25 days ago, talked about in 3 AI sources we track
- LanguageTypeScript
- Sourcegithub.com/HelixDB/helix-foundry · Back to Hot repos
Requirements
- Docker with Compose v2 to run locally
- Optional: ANTHROPIC_API_KEY or OPENAI_API_KEY in the shell for Claude or OpenAI
- Node 24 and pnpm only for developing the site
Add this badge to your README
Maintain Helix Foundry? Show readers where to find these use cases.
Markdown
[](https://dedupedai.com/use-cases/helixdb-helix-foundry/?utm_source=github&utm_medium=badge&utm_campaign=HelixDB-helix-foundry)
HTML
<a href="https://dedupedai.com/use-cases/helixdb-helix-foundry/?utm_source=github&utm_medium=badge&utm_campaign=HelixDB-helix-foundry"><img src="https://dedupedai.com/badge/HelixDB/helix-foundry.svg" alt="Use cases on Deduped" height="20"></a>
A static image, no tracking script. About the badge
Questions about Helix Foundry
What is Helix Foundry?
Helix Foundry connects your company's data (PostgreSQL, MySQL, S3, Stripe, PostHog, GitHub, Linear and more, plus documents and table files), lets an agent draft an ontology over it, and loads it into HelixDB as one connected graph. You explore it as a graph or records, trace every value back to its row or quote, and ask questions with cited answers. It runs hosted or locally with Docker Compose. It is an open-source project on GitHub: https://github.com/HelixDB/helix-foundry.
How do I use Helix Foundry?
Run git clone https://github.com/helixdb/helix-foundry.git and cd helix-foundry; then start it with docker compose up -d --wait (export ANTHROPIC_API_KEY or OPENAI_API_KEY first if you want Claude or OpenAI); open http://localhost:3000; there is no sign-in. The use cases on this page give the full steps and a copy-paste agent prompt for each job.
Who is Helix Foundry for?
Data and ops teams who want one queryable graph over scattered company data with answers that cite their source.
What can I do with Helix Foundry?
3 use cases so far, for example: Turn your company's databases and docs into one queryable graph; Ask cited questions across Stripe, GitHub and Linear; Load PDFs, Markdown and CSV files into a graph you can question. Each has steps and a copy-paste agent prompt.
What do I need to run Helix Foundry?
Docker with Compose v2 to run locally; Optional: ANTHROPIC_API_KEY or OPENAI_API_KEY in the shell for Claude or OpenAI; Node 24 and pnpm only for developing the site.
What are alternatives to Helix Foundry?
Other hot AI repos in Data and analytics: Chronos Forecasting, Apify MCP Server, Crawlee Python, DLT, Timesfm.
Is Helix Foundry safe to run?
Deduped does not own, audit or vouch for it. Read the README and license, run it on your own systems first and review every command before you run it.