# AI use cases for Cortico (Pal-AI-Lab/Cortico)

Repo: [Pal-AI-Lab/Cortico](https://github.com/Pal-AI-Lab/Cortico) | Use cases: 5 | Page: https://dedupedai.com/use-cases/pal-ai-lab-cortico/

Cortico is a free, open source TypeScript agent harness for building persistent, always-running AI bots that handle mixed real-time input from chat platforms, live games and other environments.

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

- Run a persona bot locally and chat with it in the WebUI: https://dedupedai.com/use-cases/pal-ai-lab-cortico/run-a-persona-bot-locally/
- Build a Cortico extension by talking to a coding agent: https://dedupedai.com/use-cases/pal-ai-lab-cortico/build-a-cortico-extension-with-cortina/
- Run an AI VTuber with a Live2D model, streaming TTS and OBS overlay: https://dedupedai.com/use-cases/pal-ai-lab-cortico/run-an-ai-vtuber-with-vtube-studio-and-obs/
- Run a bot that reacts to Bilibili live room events: https://dedupedai.com/use-cases/pal-ai-lab-cortico/run-a-bilibili-live-room-bot/
- Run several bot personas from separate deployments: https://dedupedai.com/use-cases/pal-ai-lab-cortico/run-several-personas-from-separate-deployments/

## How to run a persona bot locally and chat with it in the WebUI with Cortico

Repo: [Pal-AI-Lab/Cortico](https://github.com/Pal-AI-Lab/Cortico) | Difficulty: Intermediate | Time: 30 minutes | Basis: From the README

Start Cortico on your machine and talk to the reference bot in a browser console.

**Who it is for:** A developer or hobbyist who wants a working AI persona bot on their own computer before building anything custom.

**The problem:** Setting up an agent runtime, its model connection and a chat interface from scratch takes time before any result appears.

**The outcome:** A running default deployment named mybot with the reference bot cormini, reachable in the WebUI at http://127.0.0.1:7788/, with a configured model endpoint and a first message from the bot.

### Steps

1. Run `corepack pnpm install` in the cloned Cortico folder.
2. Run `pnpm start`.
3. Open http://127.0.0.1:7788/ in your browser.
4. Follow the three onboarding steps: configure a model endpoint, inspect active Worlds, and adjust the system prompt.
5. Click Say hello to let the bot start the conversation.

### Prompt to paste into your agent

```text
In the Cortico repo at <path>, install dependencies and start the default deployment, then configure a model endpoint from the WebUI at http://127.0.0.1:7788/. Report the deployment name and confirm the bot sends a reply after Say hello.
```

### Caveat

The README says a model endpoint must be configured before the bot can reply, so you need your own model access ready before the first run.

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/pal-ai-lab-cortico/run-a-persona-bot-locally/

## How to build a Cortico extension by talking to a coding agent with Cortico

Repo: [Pal-AI-Lab/Cortico](https://github.com/Pal-AI-Lab/Cortico) | Difficulty: Intermediate | Time: 1 hour | Basis: From the README

Use the Cortina workspace and any coding agent to create or port a World extension.

**Who it is for:** A non-developer or developer who wants a new integration for a Cortico bot and does not want to write the extension by hand.

**The problem:** Writing a World extension requires knowing the Cortico extension structure, which is slow to learn for a one-off integration.

**The outcome:** A finished Cortico extension, or an existing implementation moved onto Cortico, published to npm with the cortico-world keyword so it appears on the WebUI Extensions page.

### Steps

1. Clone the Cortina repository with `git clone https://github.com/Pal-AI-Lab/Cortina`. (inferred, check the README)
2. Open that workspace with any coding agent.
3. Say hello and describe the Cortico extension or adaptation you want; Cortina guides you through it in conversation.
4. Finish the extension, then publish it to npm with the cortico-world keyword.

### Prompt to paste into your agent

```text
Open the Cortina workspace cloned from https://github.com/Pal-AI-Lab/Cortina and build a Cortico World extension that <goal>. Expected output: a package folder with a finished extension and npm publish steps. Verify that package.json includes the cortico-world keyword before publishing.
```

### Caveat

The README states Cortina is designed on the TINA spec and needs no coding knowledge, but publishing to npm still requires you to have an npm account you control.

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/pal-ai-lab-cortico/build-a-cortico-extension-with-cortina/

## How to run an AI VTuber with a Live2D model, streaming TTS and OBS overlay with Cortico

Repo: [Pal-AI-Lab/Cortico](https://github.com/Pal-AI-Lab/Cortico) | Difficulty: Advanced | Time: 3 hours | Basis: From the README

Use the cortico-world-vtuber project to drive a Live2D avatar, speech and subtitles.

**Who it is for:** A streamer or creator who wants an AI VTuber that speaks and animates on stream.

**The problem:** Connecting a Live2D model, voice output, subtitle timing and a stream overlay into one AI character takes many separate tools.

**The outcome:** A Cortico World that drives a Live2D model through VTube Studio, speaks through streaming TTS, times subtitles with a forced aligner and pushes the overlay into OBS.

### Steps

1. Clone the cortico-world-vtuber repository from https://github.com/Pal-AI-Lab/cortico-world-vtuber, since it is kept outside the Cortico main tree.
2. Install its dependencies following the instructions in that repository. (inferred, check the README)
3. Set up VTube Studio with your Live2D model.
4. Configure the streaming TTS and forced aligner as that repository describes.
5. Add the overlay to OBS and start the bot.

### Prompt to paste into your agent

```text
Clone https://github.com/Pal-AI-Lab/cortico-world-vtuber and set it up as a Cortico World for a Live2D model in VTube Studio. Expected output: a running World that shows subtitles in the OBS overlay. Verify that the subtitle timing lines up with the spoken audio.
```

### Caveat

The VTuber project is released under AGPL-3.0 with a CLA and lives in a separate repository, so review its license before you publish a modified version.

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/pal-ai-lab-cortico/run-an-ai-vtuber-with-vtube-studio-and-obs/

## How to run a bot that reacts to Bilibili live room events with Cortico

Repo: [Pal-AI-Lab/Cortico](https://github.com/Pal-AI-Lab/Cortico) | Difficulty: Intermediate | Time: 1 hour | Basis: From the README

Connect the Bilibili World to answer danmaku, superchats, gifts and guards in a live room.

**Who it is for:** A live streamer on Bilibili who wants an AI companion that responds to viewers in real time.

**The problem:** Watching chat, gifts and paid messages during a live stream while also replying to them is hard to do by hand.

**The outcome:** A bot that receives real-time danmaku, superchats, gifts, guards and viewer traffic events, with a local OBS overlay.

### Steps

1. Run `corepack pnpm install` in the Cortico folder.
2. Run `pnpm start` to open the WebUI.
3. Add the bilibili World to your deployment from the WebUI.
4. Enter your live room settings and credentials in the WebUI or your environment file.
5. Add the local OBS overlay to your stream and check that events arrive.

### Prompt to paste into your agent

```text
In the Cortico repo at <path>, enable the bilibili World for the default deployment and confirm that a test danmaku event reaches the bot. Expected output: a logged event and a bot reply. Verify that credentials are stored only in local configuration and not in committed files.
```

### Caveat

The README lists the bilibili World's events and an OBS overlay but does not describe the exact setup steps, so check the docs for the World before you go live.

Risk, credentials: Bilibili live room settings and any account credentials must stay in local configuration and must not be committed to a shared repository.

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/pal-ai-lab-cortico/run-a-bilibili-live-room-bot/

## How to run several bot personas from separate deployments with Cortico

Repo: [Pal-AI-Lab/Cortico](https://github.com/Pal-AI-Lab/Cortico) | Difficulty: Intermediate | Time: 30 minutes | Basis: From the README

Create isolated deployment folders so each persona has its own config and memory.

**Who it is for:** A creator or developer who runs more than one bot persona and wants them kept apart.

**The problem:** Mixing several personas in one configuration makes settings, endpoints and runtime state hard to keep separate.

**The outcome:** Two or more isolated deployments inside deployments/, each starting on its own with its own endpoints and settings.

### Steps

1. Run `pnpm start --new`.
2. Pick a bot package, a directory name and a display name for the new deployment.
3. Let the new deployment start, then configure its endpoints from the WebUI.
4. Start a specific deployment by name with `pnpm start second` or the name you chose.

### Prompt to paste into your agent

```text
In the Cortico repo at <path>, create a new deployment with `pnpm start --new` and then start it by name. Expected output: a second deployment directory under deployments/ that starts separately. Verify that the first deployment is unchanged after the second one is configured.
```

### Caveat

The README says each deployment is an isolated configuration directory, but you still need a separate model endpoint or shared endpoint settings for each persona.

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/pal-ai-lab-cortico/run-several-personas-from-separate-deployments/