DEDUPED Hot AI repos. Real use cases. What people build. Get the Monday 5

How to ask cited questions across Stripe, GitHub and Linear with Helix Foundry

Connect SaaS sources and ask questions whose answers trace back to the exact record.

Short answer: Start Foundry locally or use the hosted version at foundry.helix-db.com; then connect Stripe, GitHub and Linear; let the agent draft types and links between them, then edit the rules. All steps.

Who it is forA founder who wants to know which paying customers are blocked by open issues.

The problemBilling, code and issue data live in separate tools with no shared view.

The outcomeAnswers that join Stripe, GitHub and Linear data, each value traceable to its source.

What you need first

  • 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

Steps

  1. Start Foundry locally or use the hosted version at foundry.helix-db.com
  2. Connect Stripe, GitHub and Linear
  3. Let the agent draft types and links between them, then edit the rules
  4. Load the version and ask questions in plain language
  5. Follow each value back to its row before acting on an answer

Prompt for your agent

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.

Caveat. This card is written from the HelixDB/helix-foundry README, not from a test run by Deduped. Before you start, make sure you have Docker with Compose v2 to run locally. Check the repo for newer instructions before you rely on these steps.

Use this in your AI agent

Ask your agent

Using the Deduped MCP, get the setup steps for HelixDB/helix-foundry and "Ask cited questions across Stripe, GitHub and Linear"

Add Deduped to Claude Code once

claude mcp add --transport http deduped https://dedupedai.com/mcp

Cursor, ChatGPT, others

Share: X LinkedIn Hacker News Email Copy link

Third-party repos we don't own. AI-written use cases can be wrong. Disclaimer