ai-human

<div align="center">

<h1>🤖 AI Human</h1>

<h3>The World's First Fully Autonomous AI Agent That Operates Your Computer Like a Human Worker — Runs 100% Offline on 4GB RAM</h3>

<p>
  <a href="https://github.com/yourusername/ai-human/stargazers"><img src="https://img.shields.io/github/stars/yourusername/ai-human?style=for-the-badge&logo=github&color=gold" alt="Stars"></a>
  <a href="https://github.com/yourusername/ai-human/network/members"><img src="https://img.shields.io/github/forks/yourusername/ai-human?style=for-the-badge&logo=github&color=blue" alt="Forks"></a>
  <a href="https://github.com/yourusername/ai-human/blob/master/LICENSE"><img src="https://img.shields.io/badge/License-MIT-green?style=for-the-badge" alt="MIT License"></a>
  <a href="https://github.com/yourusername/ai-human/releases"><img src="https://img.shields.io/badge/Python-3.10+-blue?style=for-the-badge&logo=python" alt="Python"></a>
  <img src="https://img.shields.io/badge/Platform-Windows%2010%2F11-0078D6?style=for-the-badge&logo=windows" alt="Windows">
  <img src="https://img.shields.io/badge/LLM-Ollama%20%7C%20Claude%20%7C%20GPT--4%20%7C%20Any-purple?style=for-the-badge" alt="LLM">
  <img src="https://img.shields.io/badge/Hardware-4GB%20RAM%20Minimum-orange?style=for-the-badge" alt="4GB RAM">
</p>

<p>
  <a href="#-quick-start">Quick Start</a> •
  <a href="#-why-ai-human">Why AI Human</a> •
  <a href="#-capabilities">Capabilities</a> •
  <a href="#-architecture">Architecture</a> •
  <a href="#-llm-providers">LLM Providers</a> •
  <a href="#-contributing">Contributing</a>
</p>

---

**⚡ Nothing like this has existed before in AI history.**

AI Human is not a chatbot. It is not a simple script. It is a fully autonomous digital worker that **sees your screen**, **understands what it sees**, **plans multi-step actions**, **executes them with mouse and keyboard**, **learns from every mistake**, and **improves itself over time — including rewriting its own code.**

It works on a $200 laptop. No internet required. No cloud subscription. Completely free.

</div>

---

## 🔥 Why AI Human Is Different From Everything Else

| Feature | **AI Human** | OpenAI Computer Use | Claude Computer Use | AutoGPT | MetaGPT |
|---|:---:|:---:|:---:|:---:|:---:|
| Works offline / no internet | ✅ | ❌ | ❌ | ❌ | ❌ |
| Runs on 4GB RAM | ✅ | ❌ | ❌ | ❌ | ❌ |
| Operates real computer (mouse + keyboard) | ✅ | ✅ | ✅ | ❌ | ❌ |
| Modifies its own source code | ✅ | ❌ | ❌ | ❌ | ❌ |
| Creates new tools at runtime | ✅ | ❌ | ❌ | ❌ | ❌ |
| Learns autonomously while idle | ✅ | ❌ | ❌ | ❌ | ❌ |
| Free & open source | ✅ | ❌ | ❌ | ✅ | ✅ |
| Works with ANY LLM provider | ✅ | ❌ | ❌ | Partial | ❌ |
| Self-heals on failure | ✅ | ❌ | ❌ | Partial | ❌ |
| Peer network (agents share knowledge) | ✅ | ❌ | ❌ | ❌ | ❌ |
| Mobile companion app | ✅ | ❌ | ❌ | ❌ | ❌ |
| Voice-controlled ("Hey AI") | ✅ | ❌ | ❌ | ❌ | ❌ |

> **OpenAI Computer Use costs money, requires internet, and can't learn. AI Human runs free, offline, and gets smarter every day.**

---

## ⚡ What AI Human Can Do Right Now

Tell it a goal in plain English. It does the rest.

```
"Check my emails, summarize the important ones, and draft replies for anything urgent."

"Research competitors in my market, write a report, and save it to my Desktop."

"Find all Python files modified this week, run the tests, and commit the passing ones to GitHub."

"Monitor my screen and alert me if my build breaks."

"Every Monday at 9am: generate a weekly report, email it to my team, and archive last week's."
```

It **sees your screen**, **clicks**, **types**, **opens apps**, **writes code**, **reads files**, **sends emails**, **browses the web**, **manages databases** — everything a human assistant would do.

---

## 🧠 The Capabilities That Have Never Existed Together Before

### 1. Self-Modifying AI — It Rewrites Its Own Code
Tell it to customize itself. It reads its own source files, modifies the code, validates with AST, takes a snapshot, restarts, and auto-rolls back if something breaks. No human in the loop.

### 2. Self-Creating Tools — It Builds Its Own Capabilities
Encounter a task no existing tool handles? The agent generates a new Python tool on the fly, security-validates it, hot-reloads it, and uses it — all in the same session.

### 3. Self-Healing — It Never Gives Up
On failure: diagnoses the error → searches the web for solutions → applies the fix → retries. It keeps trying until it succeeds or escalates to you.

### 4. Runs on 4GB RAM — True Democratization of AI
Auto-detects your hardware. Selects the best model that fits. TinyLlama 1.1B on 4GB. Mistral 7B on 16GB. No manual configuration needed.

### 5. Fully Offline — Your Data Never Leaves Your Machine
All computation happens locally via Ollama. No API keys. No subscriptions. No cloud. Your files, emails, and actions stay on your computer.

### 6. Learns While You Sleep
When idle for 5+ minutes, it autonomously researches knowledge gaps, analyzes past failures, extracts lessons, and stores everything in its permanent vector memory. It wakes up smarter than when it went idle.

### 7. Peer Network — A Swarm of AI Workers
Run AI Human on multiple machines. They discover each other via mDNS, share learned knowledge, and delegate tasks. One agent handles email; another writes code; another monitors the market.

---

## 🚀 Quick Start

### Prerequisites
- Python 3.10+
- Windows 10 or 11
- 4GB RAM minimum (8GB+ recommended)
- [Ollama](https://ollama.com) for offline use (optional if using Claude/OpenAI API)

### Install

```bash
git clone https://github.com/yourusername/ai-human.git
cd ai-human
pip install -r requirements.txt
cp .env.example .env
```

### Configure (choose one)

**Option A — Free, Fully Offline (no API key needed):**
```env
LLM_PROVIDER=ollama
# LLM_MODEL is auto-selected based on your hardware
```
Then install Ollama from https://ollama.com and run `ollama serve`. AI Human pulls the right model automatically.

**Option B — Claude API:**
```env
LLM_PROVIDER=anthropic
ANTHROPIC_API_KEY=sk-ant-...
```

**Option C — OpenAI:**
```env
LLM_PROVIDER=openai
OPENAI_API_KEY=sk-...
```

### Run

```bash
python launcher.py                                       # recommended (auto-restart + watchdog)
python launcher.py --goal "Check my emails and summarize"  # with a starting goal
python main.py --check                                   # hardware report (what model will it use?)
python main.py --no-ui                                   # headless terminal mode
```

Open `http://localhost:8080` in your browser for the live dashboard.

---

## 🔌 LLM Providers

Works with every major LLM provider. Switch anytime by changing one line in `.env`.

| Provider | Offline | Vision | Cost | Setup |
|---|:---:|:---:|---|---|
| **Ollama** (local) | ✅ | llava, moondream | Free | Install Ollama, run `ollama serve` |
| **LM Studio** (local) | ✅ | Via loaded model | Free | Load any GGUF model |
| **Anthropic** (Claude) | ❌ | Claude Sonnet/Opus | Pay per token | Set `ANTHROPIC_API_KEY` |
| **OpenAI** (GPT-4) | ❌ | GPT-4o | Pay per token | Set `OPENAI_API_KEY` |
| **Any OpenAI-compatible** | Depends | Depends | Varies | Set `CUSTOM_BASE_URL` + `CUSTOM_MODEL` |

---

## 💻 Hardware Auto-Detection

AI Human detects your hardware and selects the best model automatically. No configuration needed.

| Your Hardware | Text Model | Vision Model | What It Can Do |
|---|---|---|---|
| 4 GB RAM (CPU only) | TinyLlama 1.1B | Moondream 1.8B | Full automation, all tools |
| 6–15 GB RAM | Llama 3.2 3B | LLaVA 7B | Faster reasoning, richer responses |
| 16+ GB RAM | Mistral 7B | LLaVA 13B | Near-GPT-4 quality locally |
| 8+ GB VRAM (GPU) | Llama 3.1 8B | LLaVA 13B | Full speed, near-instant responses |

Run `python main.py --check` to see your hardware tier and what will be used.

---

## 🛠️ Built-in Tools (100+)

### Core Computer Control
- **Mouse & keyboard**: click, type, drag, scroll, hotkeys
- **Window management**: open, close, focus, resize any a

[truncated…]