other / agent
fullstack-agent
A Claude Code wizard that sets up an AI agent with memory, voice and an on-screen face, plus optional webcam hand control, on your machine.
At a glance
- Purpose
- A Claude Code wizard that sets up an AI agent with memory, voice and an on-screen face, plus optional webcam hand control, on your machine.
- Runs in
- Local agent with shell
- Operating systems
- macOS, Linux, Windows
- Needs
- Runtime: Python 3 for mind/face; Chrome for hands; Needs internet: Not stated; Needs accounts or API keys beyond your agent: Not stated
- Files and data
- Reads files: Yes; Writes files: Yes; Sends data to other services: Not stated
- Tool type
- Agent
- Delivery
- From GitHub
- Version
- Latest on the main branch
- Access
- Code on GitHub
- Compatibility
- According to the README: Claude Code only, with a Claude subscription. Mac, Linux and Windows are named. Mac and Linux also use git, and on Windows the installer sets up git. The voice needs a microphone, the hands need a webcam and Chrome, and the mind and face need Python 3. The README says Python 3 ships with macOS and most Linux distributions but not with Windows.
- External costs
- The README requires Claude Code with a Claude subscription. The README describes the repository as free to use and offers a tip link. Your coding agent or model provider may charge for usage.
- Permissions
- The README's Mac and Linux command creates ~/my-agent, clones the repository there and starts Claude Code with the prompt “set me up.” The README's Windows PowerShell command downloads and extracts a repository ZIP, copies its files into the installation folder and removes temporary extraction and ZIP files. The README says the wizard installs and configures the selected components, sets up Git on Windows and creates Desktop shortcuts. The README says existing vaults remain at their current paths and hand-built voice or visualizer setups are retired in place when replaced. The README describes microphone access for voice, webcam and Chrome use for hands, and a first-run download of about 1 GB of voice models. The README says setup instructs the agent to use the troubleshooting guides to fix problems.
- Usage terms
- GNU Affero General Public License v3.0, as stated in the repository. See its LICENSE file for the exact terms. The README says the licence is version 3 or later (AGPL-3.0-or-later). It asks you to credit the author when you build on it, and it gives an email address for closed-source commercial use.
Code on GitHub
jaredrhod/fullstack-agent
AGPL-3.0Give your AI a full stack: memory, voice, face, and hands. This is the "I want an AI agent" shortcut. It sets up the entire jaredrhod stack for you with an installation wizard. Select which pieces you want or do it all!
Public GitHub data fetched · 0 days old
View on GitHub ↗What it does
According to the README, fullstack-agent assembles memory, voice, a visual face and optional webcam hand control for an agent, rather than being an agent for writing full-stack code. The README says it runs on Claude Code and uses a Claude Code installation wizard.The README names ai-memory-vault for plain-text memory, backtalk for voice conversation, ai-visualizer for conversation-linked visuals and barehands for moving notes and images through a webcam. The README says every piece is optional and that the wizard asks which pieces to install.
The README says the wizard asks for an agent name, personality and notes location, performs installation and configuration, and leaves Chat, Talk and Barehands shortcuts on the Desktop.
Who it is for
People who use Claude Code and want a guided setup for a personal AI agent with memory, voice and a visual face.Example tasks
Run the setup wizard in Claude Code and choose which pieces to install.Name your agent and choose its personality, or use the author's ready-made agent, Jarvis.
Open the Chat shortcut to start a typed session.
Open the Talk shortcut to start the voice and the face.
Update everything with ./fullstack-agent/update.sh on macOS.