jaredrhod/fullstack-agent

Give 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!

What it solves

This project provides a unified installation and configuration framework to assemble a multi-modal AI agent with persistent memory, voice interaction, and visual representation. It transforms a standard LLM interface into a personalized assistant that can remember users across sessions, speak aloud, and interact visually.

How it works

The system acts as an orchestrator that integrates four distinct open-source components via a guided installation wizard run through Claude Code:

  • The Mind (ai-memory-vault): Implements persistent memory using plain text files that the AI can read and write to maintain long-term context.
  • The Mouth (backtalk): Enables real-time voice communication, allowing users to talk to the agent and hear responses through speakers.
  • The Face (ai-visualizer): Provides full-screen visual animations that synchronize with the agent's listening, thinking, and speaking states.
  • The Hands (barehands): An optional module that uses a webcam to allow users to move notes and images on screen using hand gestures.

Who it’s for

Users who want a highly personalized, "Jarvis-like" AI assistant on their local machine and those who are already using Claude Code and want to add multi-modal capabilities to their AI workflow.

Highlights

  • Guided Setup: Uses a Claude Code wizard to handle installation, configuration, and wiring of all components.
  • Cros-Session Memory: Persistent memory vault that avoids the size ceilings typical of standard context windows.
  • Multi-modal Interface: Combines voice, visualizers, and gesture-based screen interaction.
  • Self-Healing: Includes troubleshooting guides that the agent itself can read to fix its own configuration problems.

Related

  • Project
    peterfei/ai-agent-team

    A virtual AI development team with specialized roles (PM, Backend, Frontend, etc.) and a persistent memory system for managing complex software projects.

  • Project
    akitaonrails/ai-memory

    ai‑memory is a Rust‑based server that records every observation a coding‑assistant makes (prompts, tool calls, session boundaries) as plain markdown files in a git‑backed wiki. The server can be run locally, in Docker/Podman, or on a homelab box and is designed to be shared across many agents (Claude Code, Codex, Cursor, Gemini CLI, etc.), machines and team members. Hooks posted by agents are consolidated into readable wiki pages at session end; the next session receives a concise handoff so it can continue exactly where the previous one stopped. Storage is human‑readable markdown plus a SQLite index (FTS5, entity and optional vector search). By default it needs no LLM or embedding keys; optional Anthropic/OpenAI integrations add LLM‑generated summaries and semantic search. Multi‑user authentication, audit logs and per‑person attribution are built in. Install via Arch AUR, Docker wrapper, or native binary, start the server, register a client and its hooks, and the system works transparently.

  • Project
    op7418/CodePilot

    A multi-model AI agent desktop client that unifies 17+ AI providers into one interface with persistent memory, remote control via messaging apps, and MCP support.

  • Project
    breferrari/obsidian-mind

    An Obsidian vault template that provides AI coding agents with persistent, cross-session memory through automated hooks and semantic search.

  • Project
    NevaMind-AI/memU

    An agent-driven memory system that creates a shared LLM wiki across sessions, agents, and devices by automatically distilling reusable skills from agent history.