# AI use cases for Spynel (agent0ai/spynel)

Repo: [agent0ai/spynel](https://github.com/agent0ai/spynel) | Use cases: 3 | Page: https://dedupedai.com/use-cases/agent0ai-spynel/

Spynel is a lightweight terminal program with no AI inside that gives you one chat assistant and uses your existing coding harnesses such as Codex and Claude Code to do the work.

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

- Run one chat assistant across a project folder: https://dedupedai.com/use-cases/agent0ai-spynel/one-chat-assistant-for-a-project/
- Keep project tasks and goals in readable markdown: https://dedupedai.com/use-cases/agent0ai-spynel/durable-markdown-task-tracking/
- Message your project assistant from Telegram or WhatsApp: https://dedupedai.com/use-cases/agent0ai-spynel/reach-your-assistant-from-phone-chat/

## How to run one chat assistant across a project folder with Spynel

Repo: [agent0ai/spynel](https://github.com/agent0ai/spynel) | Difficulty: Intermediate | Time: 30 minutes | Basis: From the README

Install Spynel and talk to one assistant that coordinates your coding harnesses in a single terminal chat.

**Who it is for:** A developer juggling several AI coding chats and projects who wants one place to direct all of their AI work.

**The problem:** Work is spread across separate AI chats, projects, and spaces, so context gets lost and switching costs time.

**The outcome:** A running Spynel terminal chat, scoped to your project directory, that acts as the single assistant for that project's AI work.

### Steps

1. Run `curl -LsSf https://spynel.agent-zero.ai/install.sh | sh` on macOS or Linux, or run `npm install -g spynel` with Node.js 18+.
2. Change into your project directory.
3. Run `spynel` from that directory.
4. Run `/config` in the chat to complete setup.
5. Send your next request to the assistant in the chat instead of opening a new AI chat.

### Prompt to paste into your agent

```text
Using the spynel repo at agent0ai/spynel, install Spynel in <project-directory> and start it with `spynel` from that folder. Expected output: a running Spynel terminal chat bound to <project-directory>. Verify that `/config` opens and that a test message gets a reply from the assistant.
```

### Caveat

Spynel has no AI of its own, so it only works once a coding harness such as Codex or Claude Code is available to do the work.

Risk, remote script: The curl install pipes a remote script directly into sh, so review the script at its URL before running it on a machine that matters.

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/agent0ai-spynel/one-chat-assistant-for-a-project/

## How to keep project tasks and goals in readable markdown with Spynel

Repo: [agent0ai/spynel](https://github.com/agent0ai/spynel) | Difficulty: Intermediate | Time: 45 minutes | Basis: From the README

Store tasks, goals, decisions, and status as markdown that any AI harness can inspect.

**Who it is for:** A team lead or solo builder who needs project progress to survive across sessions and be readable by different AI tools.

**The problem:** Task status and decisions live only in chat history, so a new session or a different AI tool cannot pick up the work reliably.

**The outcome:** A set of markdown task and goal records in your workspace, with a clear picture of how Spynel stores them and how to inspect them.

### Steps

1. Install and start Spynel from your project directory with `spynel`.
2. Open docs/tasks-and-goals.md in the Spynel repo to see how tasks and goals are structured.
3. Use the chat to record your current goals and the tasks under them.
4. Open the workspace files Spynel created and confirm tasks, decisions, evidence, and status are visible in markdown.
5. Point any other AI harness at those markdown files to continue the work.

### Prompt to paste into your agent

```text
Using the spynel repo at agent0ai/spynel, read docs/tasks-and-goals.md and start Spynel in <project-directory>. Expected output: markdown files holding goals, tasks, decisions, and status for that project. Verify that the files open as plain markdown and that a second AI harness can read the current task status from them.
```

### Caveat

The exact file layout and how tasks get recorded are defined in the tasks-and-goals doc, which this summary does not reproduce, so check that doc before relying on a specific structure.

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/agent0ai-spynel/durable-markdown-task-tracking/

## How to message your project assistant from Telegram or WhatsApp with Spynel

Repo: [agent0ai/spynel](https://github.com/agent0ai/spynel) | Difficulty: Advanced | Time: 60 minutes | Basis: From the README

Reach the same Spynel assistant from Telegram or WhatsApp when you are away from the terminal.

**Who it is for:** A builder who starts work at a desk but wants to check on or direct agents from a phone while away.

**The problem:** Agent work stalls when you are away from the terminal, and checking progress means returning to your computer.

**The outcome:** A Telegram or WhatsApp channel connected to your running Spynel assistant, so you can send instructions and get replies from your phone.

### Steps

1. Start Spynel from your project directory with `spynel`.
2. Run `/config` and set up the Telegram or WhatsApp integration.
3. Read docs/integrations.md for the setup details for your chosen channel.
4. Send a test message from Telegram or WhatsApp to the assistant.
5. Confirm the reply comes back and that the work matches what the terminal shows.

### Prompt to paste into your agent

```text
Using the spynel repo at agent0ai/spynel, follow docs/integrations.md to connect <Telegram or WhatsApp> to a Spynel instance running in <project-directory>. Expected output: a test message sent from the phone gets a reply from the same assistant. Verify that the reply matches the state shown in the terminal chat.
```

### Caveat

Telegram and WhatsApp setup details live in docs/integrations.md, and this summary does not describe their exact steps, so follow that doc for them.

Risk, credentials: Connecting Telegram or WhatsApp means linking a messaging account to a local tool, so protect any tokens or account access you set up.

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/agent0ai-spynel/reach-your-assistant-from-phone-chat/
