# AI use cases for Open Index (DrDroidLab/open-index)

Repo: [DrDroidLab/open-index](https://github.com/DrDroidLab/open-index) | Use cases: 3 | Page: https://dedupedai.com/use-cases/drdroidlab-open-index/

Open Index is a Python tool for building a brain: a searchable, structured context graph of your domain from typed entities and relationships that agents can query, with an explorer UI and MCP server.

This file holds every use case of this repo. Each one starts with a "## " heading and ends with its URL.

- Explore a support knowledge graph in minutes: https://dedupedai.com/use-cases/drdroidlab-open-index/explore-example-support-brain/
- Map your services and runbooks for an agent: https://dedupedai.com/use-cases/drdroidlab-open-index/model-your-services-and-runbooks/
- Share one structured brain with several agents: https://dedupedai.com/use-cases/drdroidlab-open-index/share-brain-with-agents-over-mcp/

## How to explore a support knowledge graph in minutes with Open Index

Repo: [DrDroidLab/open-index](https://github.com/DrDroidLab/open-index) | Difficulty: Intermediate | Time: 15 minutes | Basis: From the README

Index the bundled support brain and browse products, issues and segments on a visual map.

**Who it is for:** A developer evaluating structured memory for a support agent.

**The problem:** It is hard to picture a context graph without seeing one.

**The outcome:** A working indexed brain and a map view to explore it.

### Steps

1. Install with `pip install -e '.[all]'`
2. Index with `open-index index --brain examples/support-brain`
3. Open the UI with `open-index ui    --brain examples/support-brain`
4. Pick an anchor on the Map tab

### Prompt to paste into your agent

```text
Install DrDroidLab/open-index, index examples/support-brain, and list the issues linked to one product. Verify the links match the related_to edges in the entity files.
```

### Caveat

The UI command in the README uses extra spaces before --brain; copy it as shown or normalize the spacing.

Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/

URL: https://dedupedai.com/use-cases/drdroidlab-open-index/explore-example-support-brain/

## How to map your services and runbooks for an agent with Open Index

Repo: [DrDroidLab/open-index](https://github.com/DrDroidLab/open-index) | Difficulty: Intermediate | Time: 45 minutes | Basis: From the README

Define doc_types like service and runbook, add entities with related_to edges, and index them.

**Who it is for:** An SRE who wants an incident agent to know which runbook belongs to which service.

**The problem:** Agents guess at infrastructure relationships from scattered docs.

**The outcome:** A searchable brain where every service links to its runbooks.

### Steps

1. Start with `open-index init my-brain`
2. Add a type with `open-index add-doc-type customer --brain my-brain` (use service for infra)
3. Write entity JSON files under my-brain/entities with related_to edges
4. Run `open-index index --brain my-brain` and open the UI

### Prompt to paste into your agent

```text
Create an Open Index brain with doc_types service and runbook, add entities for <services>, index it, and list each service's runbooks. Confirm every service has at least one edge.
```

### Caveat

With storage: file the Git files are the source of truth; the default index storage is DB-owned.

Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/

URL: https://dedupedai.com/use-cases/drdroidlab-open-index/model-your-services-and-runbooks/

## How to share one structured brain with several agents with Open Index

Repo: [DrDroidLab/open-index](https://github.com/DrDroidLab/open-index) | Difficulty: Advanced | Time: 45 minutes | Basis: From the README

Run Open Index with Docker so multiple agents query the same brain through its MCP server.

**Who it is for:** A team running several agents that must agree on the same facts.

**The problem:** Each agent keeps its own drifting copy of domain knowledge.

**The outcome:** One shared, deterministic memory layer for all agents.

### Steps

1. Install the MCP server extra with the all install
2. Start the shared deployment with `docker compose --profile sqlite up`
3. Connect each agent to the MCP server
4. Ask two agents the same question and compare answers

### Prompt to paste into your agent

```text
Deploy DrDroidLab/open-index with `docker compose --profile sqlite up`, connect it to <agent>, and query the entity <name>. Confirm the answer matches the stored entity JSON.
```

### Caveat

Connectors that pull entities from other systems are optional scripts you write yourself.

Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/

URL: https://dedupedai.com/use-cases/drdroidlab-open-index/share-brain-with-agents-over-mcp/