# AI use cases for Agenticos (vstorm-co/agenticos)

Repo: [vstorm-co/agenticos](https://github.com/vstorm-co/agenticos) | Use cases: 3 | Page: https://dedupedai.com/use-cases/vstorm-co-agenticos/

AgenticOS is a self-hosted, Apache-2.0 agent layer built on Pydantic AI that gives a team AI teammates in a shared live chat, with RAG, skills, a real browser, MCP servers, an API, budgets, approvals and an audit trail.

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

- Deploy self-hosted AI teammates for your company: https://dedupedai.com/use-cases/vstorm-co-agenticos/deploy-self-hosted-ai-teammates/
- Ground agents in your company's documents: https://dedupedai.com/use-cases/vstorm-co-agenticos/ground-agents-in-company-documents/
- Govern agents with budgets, approvals and audit: https://dedupedai.com/use-cases/vstorm-co-agenticos/govern-agents-with-budgets-and-approvals/

## How to deploy self-hosted AI teammates for your company with Agenticos

Repo: [vstorm-co/agenticos](https://github.com/vstorm-co/agenticos) | Difficulty: Intermediate | Time: 45 minutes | Basis: From the README

Run the quickstart to get a working agent in a shared team chat on your own server.

**Who it is for:** An operations lead asked to pilot AI agents without sending data to a SaaS.

**The problem:** Hosted agent platforms put company data on someone else's servers.

**The outcome:** A running deployment at localhost:3000 with a working agent.

### Steps

1. Check prerequisites with `curl -fsSL https://raw.githubusercontent.com/vstorm-co/agenticos/main/scripts/quickstart.sh | bash -s -- --check`
2. Install with the same script without --check
3. Enter a model provider, key, login and organization name
4. Open http://localhost:3000 and sign in

### Prompt to paste into your agent

```text
Deploy vstorm-co/agenticos with the quickstart on <host>, sign in, and ask the default agent a question. Confirm the run is recorded.
```

### Caveat

On Windows run it inside WSL2 with Docker Desktop's WSL2 integration.

Risk, remote script: The quickstart pipes a script into bash; the README says to read it first.

Risk, credentials: The installer stores your model provider key in the deployment.

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/vstorm-co-agenticos/deploy-self-hosted-ai-teammates/

## How to ground agents in your company's documents with Agenticos

Repo: [vstorm-co/agenticos](https://github.com/vstorm-co/agenticos) | Difficulty: Intermediate | Time: 45 minutes | Basis: From the README

Sync Google Drive, S3, Git, websites, SharePoint or OneDrive into knowledge bases agents can use.

**Who it is for:** A team lead who wants agents to answer from internal docs.

**The problem:** Agents without company knowledge give generic answers.

**The outcome:** Knowledge bases that agents search when answering.

### Steps

1. Deploy AgenticOS
2. Configure a sync source such as Google Drive or a Git repository
3. Attach the knowledge base to an agent
4. Ask questions that need the docs

### Prompt to paste into your agent

```text
In AgenticOS, sync <source> into a knowledge base, attach it to an agent, and ask <question>. Confirm the answer cites a synced document.
```

### Caveat

Sync access uses connector credentials you configure, so scope them narrowly.

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/vstorm-co-agenticos/ground-agents-in-company-documents/

## How to govern agents with budgets, approvals and audit with Agenticos

Repo: [vstorm-co/agenticos](https://github.com/vstorm-co/agenticos) | Difficulty: Advanced | Time: 1 hour | Basis: From the README

Set budgets and approval steps so agents act under rules with a recorded run.

**Who it is for:** An IT manager responsible for what AI agents do with company tools.

**The problem:** Ungoverned agents can overspend or act without sign-off.

**The outcome:** Agents that respect budgets, wait for approvals and leave an audit trail.

### Steps

1. Deploy AgenticOS
2. Set budgets per team or agent
3. Require approvals for sensitive tools
4. Review recorded runs

### Prompt to paste into your agent

```text
Configure an AgenticOS agent with a budget and an approval step for <tool>, trigger it, and confirm it waited for approval and logged the run.
```

### Caveat

It supports 28 model providers, including local models through Ollama and vLLM.

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/vstorm-co-agenticos/govern-agents-with-budgets-and-approvals/