codec

<p align="center">
  <img src="https://i.imgur.com/RbrQ7Bt.png" alt="CODEC" width="280"/>
</p>

<h1 align="center">CODEC</h1>
<p align="center"><strong>Open-Source Intelligent Command Layer for macOS</strong></p>
<p align="center"><em>Your voice. Your computer. Your rules. No limit.</em></p>
<p align="center">
  <a href="https://opencodec.org">opencodec.org</a> · <a href="https://avadigital.ai">AVA Digital LLC</a> · <a href="#quick-start">Get Started</a> · <a href="#support-the-project">Support</a> · <a href="#professional-setup">Enterprise</a>
</p>

<p align="center">
  <img src="https://img.shields.io/badge/features-189-blue?style=flat-square" alt="189 Features"/>
  <img src="https://img.shields.io/badge/skills-56-orange?style=flat-square" alt="56 Skills"/>
  <img src="https://img.shields.io/badge/tests-312-green?style=flat-square" alt="312 Tests"/>
  <img src="https://img.shields.io/badge/core_lines-10%2C405-purple?style=flat-square" alt="10,405 Lines"/>
  <img src="https://img.shields.io/badge/license-MIT-brightgreen?style=flat-square" alt="MIT License"/>
</p>

---

<p align="center">
  <a href="https://www.youtube.com/watch?v=OEXxvxA0_AE">
    <img src="https://img.youtube.com/vi/OEXxvxA0_AE/maxresdefault.jpg" alt="CODEC Demo" width="660"/>
  </a>
  <br/>
  <em>Watch the full demo</em>
</p>

---

## What Is CODEC

CODEC is a framework that turns a Mac into a voice-controlled AI workstation. Give it a brain (any LLM — local or cloud), ears (Whisper), a voice (Kokoro), and eyes (vision model). The rest is Python.

It listens, sees the screen, speaks back, controls apps, writes code, drafts messages, manages Google Workspace, and when it doesn't know how to do something — it writes its own plugin and learns.

No cloud dependency. No subscription. No data leaving the machine. MIT licensed.

---

## 7 Products. One System.

### CODEC Core — The Command Layer

Always-on voice assistant. Say *"Hey CODEC"* or press F13 to activate. F18 for voice commands. F16 for text input.

56 skills fire instantly: Google Calendar, Gmail, Drive, Docs, Sheets, Tasks, Keep, Chrome automation, web search, Hue lights, timers, Spotify, clipboard, terminal commands, and more. Most skills bypass the LLM entirely — direct action, zero latency.

### Vision Mouse Control — See & Click

**No other open-source voice assistant does this.**

Say *"Hey CODEC, click the Submit button"* — CODEC screenshots the screen, sends it to a local UI-specialist vision model (UI-TARS), gets back pixel coordinates, and moves the mouse to click. Fully voice-controlled. Works on any app. No accessibility API required — pure vision.

| Step | What happens | Speed |
|---|---|---|
| 1 | Whisper transcribes voice command | ~2s |
| 2 | Target extracted from natural speech | instant |
| 3 | Screenshot captured and downscaled | instant |
| 4 | UI-TARS locates the element by pixel coordinates | ~4s |
| 5 | pyautogui moves cursor and clicks | instant |

*"I'm on Cloudflare and can't find the SSL button — click it for me."* That works. CODEC strips the conversational noise, extracts "SSL button", and finds it on screen.

### CODEC Dictate — Hold, Speak, Paste

Hold a key. Say what you mean. Release. Text appears wherever the cursor is. If CODEC detects a message draft, it refines through the LLM — grammar fixed, tone polished, meaning preserved. Works in every app on macOS. A free, open-source SuperWhisper replacement that runs entirely local.

### CODEC Instant — One Right-Click

Select any text, anywhere. Right-click. Eight AI services system-wide: Proofread, Elevate, Explain, Translate, Reply (with `:tone` syntax), Prompt, Read Aloud, Save. Powered by the local LLM.

### CODEC Chat — 250K Context + 12 Agent Crews

Full conversational AI. Long context. File uploads. Image analysis via vision model. Web search. Conversation history.

Plus 12 autonomous agent crews — not single prompts, full multi-step workflows. Say *"research the latest AI agent frameworks and write a report."* Minutes later there's a formatted Google Doc in Drive with sources, images, and recommendations.

| Crew | Output |
|---|---|
| Deep Research | 10,000-word illustrated report → Google Docs |
| Daily Briefing | Morning news + calendar → Google Docs |
| Competitor Analysis | SWOT + positioning → Google Docs |
| Trip Planner | Full itinerary → Google Docs |
| Email Handler | Triage inbox, draft replies |
| Social Media | Posts for Twitter, LinkedIn, Instagram |
| Code Review | Bugs + security + clean code |
| Data Analysis | Trends + insights report |
| Content Writer | Blog posts, articles, copy |
| Meeting Summarizer | Action items from transcripts |
| Invoice Generator | Professional invoices |
| Custom Agent | Define your own role, tools, task |

Schedule any crew: *"Run competitor analysis every Monday at 9am"*

The multi-agent framework is under 800 lines. Zero dependencies. No CrewAI. No LangChain.

### CODEC Vibe — AI Coding IDE + Skill Forge

Split-screen in the browser. Monaco editor on the left (same engine as VS Code). AI chat on the right. Describe what's needed — CODEC writes it, click Apply, run it, live preview in browser.

Skill Forge takes it further: describe a new capability in plain English, CODEC converts it into a working plugin. The framework writes its own extensions.

### CODEC Voice — Live Voice Calls

Real-time voice-to-voice conversations with the AI. WebSocket pipeline — no Pipecat, no external dependencies. Call CODEC from a phone, talk naturally, and mid-call say *"check my screen"* — it takes a screenshot, analyzes it, and speaks the result back.

Full transcript saved to memory. Every conversation becomes searchable context for future sessions.

### CODEC Overview — Dashboard Anywhere

Private dashboard accessible from any device, anywhere. Cloudflare Tunnel or Tailscale VPN — no port forwarding, no third-party relay. Send commands, view the screen, launch voice calls, manage agents — all from a browser.

---

## Screenshots

<p align="center">
  <img src="docs/screenshots/quick-chat.png" alt="Quick Chat" width="720"/><br/>
  <em>Chat — ask anything, drag & drop files, full conversation history</em>
</p>

<p align="center">
  <img src="docs/screenshots/chat-analysis.png" alt="Chat with File Analysis" width="720"/><br/>
  <em>Deep Chat — upload files, select agents, get structured analysis</em>
</p>

<p align="center">
  <img src="docs/screenshots/voice-call.png" alt="Voice Call" width="720"/><br/>
  <em>Voice Call — real-time conversation with live transcript</em>
</p>

<p align="center">
  <img src="docs/screenshots/vibe-code.png" alt="Vibe Code" width="720"/><br/>
  <em>Vibe Code — describe what you want, get working code with live preview</em>
</p>

<p align="center">
  <img src="docs/screenshots/deep-research.png" alt="Deep Research Report" width="720"/><br/>
  <em>Deep Research — multi-agent reports delivered to Google Docs</em>
</p>

<p align="center">
  <img src="docs/screenshots/tasks.png" alt="Tasks & Schedules" width="720"/><br/>
  <em>Scheduled automations — morning briefings, competitor analysis, on cron</em>
</p>

<details>
<summary><strong>More screenshots</strong></summary>
<br/>
<p align="center">
  <img src="docs/screenshots/settings.png" alt="Settings" width="720"/><br/>
  <em>Settings — LLM, TTS, STT, hotkeys, wake word configuration</em>
</p>
<p align="center">
  <img src="docs/screenshots/agent-options.png" alt="Agent Options" width="420"/><br/>
  <em>12 specialized agent crews</em>
</p>
<p align="center">
  <img src="docs/screenshots/login-auth.png" alt="Authentication" width="320"/><br/>
  <em>Touch ID + PIN + 2FA authentication</em>
</p>
<p align="center">
  <img src="docs/screenshots/right-click-menu.png" alt="Right-Click Menu" width="300"/><br/>
  <em>Right-click integration — CODEC in every app</em>
</p>
<p align="center">
  <img src="docs/screenshots/terminal.png" alt="Terminal" width="400"/><br/>
  <em>50+ skills loaded at startup</em>
</p>
</details>

---

## What Makes

[truncated…]