[recipes] Local Docker Open Brain — Postgres + pgvector + AWS Bedrock

[tomotvos]

Contribution Type

• Recipe (/recipes)
• Schema (/schemas)
• Dashboard (/dashboards)
• Integration (/integrations)
• Skill (/skills)
• Repo improvement (docs, CI, templates)

What does this do?

Adds a self-contained Docker stack that runs Open Brain entirely on the user's own machine — Postgres + pgvector as the store, a Node.js MCP server in a sibling container, and AWS Bedrock for embeddings (Titan V2) and metadata extraction (Claude Haiku 4.5). Designed for environments under data-privacy constraints where cloud-hosted databases like Supabase are not permitted. Includes a Chrome bookmarklet, AutoHotkey global hotkey, PowerShell script, and standalone search UI for human capture from outside an AI session.

Requirements

• Docker Desktop
• AWS account with Bedrock model access for amazon.titan-embed-text-v2:0 and us.anthropic.claude-haiku-4-5-20251001-v1:0
• AWS CLI configured with a profile that has bedrock:InvokeModel permissions
• An AI client that supports HTTP-based MCP servers (Claude Code, Claude Desktop, GitHub Copilot, etc.)

The recipe README documents the credential bind-mount (read-only) and the rationale for hand-parsing ~/.aws/credentials instead of using the AWS SDK's default credential chain — the SDK chain caches credentials in memory and fails when SSO/assume-role tokens rotate.

Notes

A companion Qdrant-backed variant of this recipe is in a separate PR ([recipes] Local Docker Open Brain (Qdrant)). The two are independent and can run side-by-side on different ports.

Checklist

• I've read CONTRIBUTING.md
• My contribution has a README.md with prerequisites, step-by-step instructions, and expected outcome
• My metadata.json has all required fields
• If my contribution depends on a skill or primitive, I declared it in metadata.json and linked it in the README (no such dependency in this recipe)
• I tested this on my own Open Brain instance
• No credentials, API keys, or secrets are included

[github-actions]

Hey @tomotvos — welcome to Open Brain Source! 👋

Thanks for submitting your first PR. The automated review will run shortly and check things like metadata, folder structure, and README completeness. If anything needs fixing, the review comment will tell you exactly what.

Once the automated checks pass, a human admin will review for quality and clarity. Expect a response within a few days.

If you have questions, check out CONTRIBUTING.md or open an issue.