# AI use cases for Rakazo (elie222/rakazo)

Repo: [elie222/rakazo](https://github.com/elie222/rakazo) | Use cases: 4 | Page: https://dedupedai.com/use-cases/elie222-rakazo/

Rakazo is an open source, self-hosted AI agent platform for persistent bots, available on the web, Electron desktop, iPhone, and Android, where you bring your own model and computer provider.

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

- Run a persistent AI bot on your own computer: https://dedupedai.com/use-cases/elie222-rakazo/run-persistent-bot-on-own-machine/
- Host a shared bot team on a VPS with HTTPS: https://dedupedai.com/use-cases/elie222-rakazo/host-shared-bot-team-on-server/
- Give a bot access to apps through MCP or OpenAPI: https://dedupedai.com/use-cases/elie222-rakazo/connect-tools-and-mcp-to-bot/
- Build and run Rakazo from a source checkout: https://dedupedai.com/use-cases/elie222-rakazo/build-rakazo-from-source/

## How to run a persistent AI bot on your own computer with Rakazo

Repo: [elie222/rakazo](https://github.com/elie222/rakazo) | Difficulty: Intermediate | Time: 30 minutes | Basis: From the README

Install Rakazo with published Docker images and chat with a bot that keeps its own memory.

**Who it is for:** A privacy-minded individual who wants a personal AI assistant on their own machine instead of a hosted chatbot, and is comfortable running Docker.

**The problem:** Hosted AI assistants keep your bots and history on someone else's servers, and you cannot choose the model or sandbox behind them.

**The outcome:** A running local Rakazo instance with an account, a connected model, and a first bot that keeps its own conversations and memory.

### Steps

1. Install Docker Engine and the Compose plugin, and confirm curl and OpenSSL are available.
2. Run `mkdir -p rakazo && cd rakazo && curl -fsSLO https://raw.githubusercontent.com/elie222/rakazo/main/infra/compose/install-images.sh && bash install-images.sh` (inferred, check the README)
3. Open http://127.0.0.1:5173, create an account, and connect a model.
4. Create your first bot and send it a message in its chat.

### Prompt to paste into your agent

```text
In the Rakazo repo at https://github.com/elie222/rakazo, follow the Quick start (published images) section to install Rakazo into a folder named <target-folder> on this machine. Report the local URL and confirm that http://127.0.0.1:5173 loads a sign-in page. Verify that the .env file was created in <target-folder> with random secrets.
```

### Caveat

Rakazo is in beta, and the README says the default image tag is edge, which tracks main builds.

Risk, credentials: Your model API key and the secrets in the generated .env file must be kept private on the machine running Rakazo.

Dual-use notice: only use this on software, sites and systems you own or are authorized to test.

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/elie222-rakazo/run-persistent-bot-on-own-machine/

## How to host a shared bot team on a VPS with HTTPS with Rakazo

Repo: [elie222/rakazo](https://github.com/elie222/rakazo) | Difficulty: Advanced | Time: 90 minutes | Basis: From the README

Keep bots running on a server and connect from desktop, mobile, or browser clients.

**Who it is for:** A small team lead who wants bots and shared Team Computers to stay online without a laptop left running, and who can manage a server and a domain.

**The problem:** Bots on a personal laptop stop when the machine sleeps, so the team cannot count on them to answer or finish work.

**The outcome:** A Rakazo instance on a VPS behind HTTPS, reachable from the desktop app, mobile app, or a browser.

### Steps

1. Run `bash install-images.sh --prepare-only` on the VPS.
2. Edit .env and set SANDBOX_PROVIDER (for example boat, e2b, or daytona) with its API key, and set RAKAZO_HOST to your domain.
3. Run `bash install-images.sh`.
4. Put HTTPS in front of port 5173 using the Caddy setup in docs/self-host.md.
5. In the desktop app, choose Existing instance and enter the https:// address.

### Prompt to paste into your agent

```text
In the Rakazo repo at https://github.com/elie222/rakazo, follow the Run on a server section and docs/self-host.md to prepare a VPS for <your-domain>. Report the sandbox provider chosen and the public https:// address. Verify that the health check for the instance succeeds over HTTPS before reporting completion.
```

### Caveat

The README says public servers must use HTTPS, and the self-hosting guide covers the Caddy setup and host hardening you need to add.

Risk, credentials: The sandbox provider API key and model keys stored in .env on a public server must be protected with server hardening.

Risk, remote script: The installer is downloaded from the internet and run with bash, so review the script before running it on a server.

Dual-use notice: only use this on software, sites and systems you own or are authorized to test.

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/elie222-rakazo/host-shared-bot-team-on-server/

## How to give a bot access to apps through MCP or OpenAPI with Rakazo

Repo: [elie222/rakazo](https://github.com/elie222/rakazo) | Difficulty: Intermediate | Time: 45 minutes | Basis: From the README

Add your own HTTPS MCP server, Treg endpoint, or OpenAPI document as a tool source for a bot.

**Who it is for:** A developer or operator who already runs an MCP server or has an OpenAPI description of an internal service and wants a bot to call it.

**The problem:** A bot cannot act on your own services unless it has a tool source that describes what those services can do.

**The outcome:** A bot that can call a connected HTTPS MCP server or OpenAPI-described API through Integrations.

### Steps

1. Start a running Rakazo instance using the Quick start or a source checkout.
2. Sign in and open Integrations.
3. Add an HTTPS MCP server or an OpenAPI JSON document as a tool source.
4. Attach the tool source to a bot and send it a request that needs that tool.

### Prompt to paste into your agent

```text
In the Rakazo repo at https://github.com/elie222/rakazo, use the Integrations area of a running instance at <instance-url> to add the HTTPS MCP server <mcp-url> as a tool source. Report the tool source name and one tool it exposes. Verify that a test bot request uses the tool and returns a result.
```

### Caveat

Treg is usage-metered, self-hosters must supply their own Treg token, and hosted resale requires a written agreement under Treg's integration terms.

Risk, credentials: Tool sources may need tokens or keys, and the README says connector credentials are encrypted on the server and never returned by the API, so store them only through Rakazo.

Dual-use notice: only use this on software, sites and systems you own or are authorized to test.

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/elie222-rakazo/connect-tools-and-mcp-to-bot/

## How to build and run Rakazo from a source checkout with Rakazo

Repo: [elie222/rakazo](https://github.com/elie222/rakazo) | Difficulty: Advanced | Time: 60 minutes | Basis: From the README

Clone the repo, set up the database, and start the dev stack to change the code.

**Who it is for:** A developer who wants to read, modify, or contribute to the Rakazo codebase in TypeScript.

**The problem:** The published images are fixed builds, so changing the apps or packages needs a local development setup.

**The outcome:** A local development stack running from source with PostgreSQL migrated and the web app at http://127.0.0.1:5173.

### Steps

1. Install Node.js 22.22.2 or newer in the 22.x line, Node.js 24.x, or Node.js 26+, plus pnpm 9 and Docker.
2. Run `git clone https://github.com/elie222/rakazo.git` and `cd rakazo`, then run `cp .env.example .env`.
3. Set POSTGRES_PASSWORD, DATABASE_URL, BETTER_AUTH_SECRET, ENCRYPTION_KEY, and SCREEN_PROXY_SECRET in .env as the README describes.
4. Run `pnpm install`, `pnpm db:generate`, `pnpm db:migrate`, and `pnpm sandbox:build`.
5. Run `pnpm dev` and open http://127.0.0.1:5173.

### Prompt to paste into your agent

```text
In the Rakazo repo at https://github.com/elie222/rakazo, follow the Local development (source checkout) section to get the dev stack running on this machine. Report the Node.js and pnpm versions used and whether pnpm dev started. Verify that http://127.0.0.1:5173 responds before reporting success.
```

### Caveat

The README says Node.js 23.x and 25.x are not supported, so pick a supported Node.js version before running pnpm install.

Dual-use notice: only use this on software, sites and systems you own or are authorized to test.

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/elie222-rakazo/build-rakazo-from-source/
