Codec · macOS · MIT-licensed · Free

Your Mac.
Your AI shortcut layer.

Codec is a Mac-native AI shortcut layer for power users. Hold Cmd+R, speak, paste. Press F5 for live typing. Right-click any text for 8 AI services: proofread, translate, explain, summarize. 88 skills. Vision-based UI clicking (“click the Submit button” actually works). Local LLMs (Qwen, Llama, Mistral via MLX) or cloud (GPT-4o, Claude). Whisper for STT, Kokoro for TTS. Free. MIT-licensed. Your voice. Your computer. Your rules.

~/codec · zsh CODEC v3.2
$ git clone https://github.com/AVADSA25/codec.git
$ cd codec && ./install.sh
✔ macOS 13+ · Apple Silicon
✔ Installed 88 skills · 400 features
2,000+ tests green
✔ Models running locally — nothing leaves this Mac.

# Hold Cmd+R anywhere. Speak. Release.
you> "summarise the doc on screen"
→ skill: screenshot_text
→ model: local · 0 tokens sent
→ text pasted at cursor.

$
In one paragraph

Codec is a macOS AI shortcut layer for power users. Voice-control your Mac, dictate anywhere with Cmd+R, right-click any text for 8 AI services, run a 250K-context chat with 12 agent crews, do vision-based UI clicking. Free. MIT-licensed. No subscription. Install yourself in one command, or have AVA Digital install Codec + an LLM + voice-to-text + text-to-speech for you (personalized installation from €500).

Codec · The film

See how it thinks.

A short tour of what Codec does: the framework behind every AVA agent, running in the open.

368 features 88 skills 940+ tests MIT licensed
400
Features
Shipped across 8 domains
88
Skills
Pluggable, composable
2,000+
Tests
Green on every commit
52K+
Lines
TypeScript + Python
100+
Stars
and counting
MIT
License
Yours to fork, ship, sell
Architecture

Five layers.
Swap any of them.

05

Interface

voice dashboard mcp api chat menu-bar
04

Agent

crews pilot project delegate persona
03

Skills

calendar email voice invoicing social research docs sales + 52 more
02

Runtime

planner tool-router memory guardrails eval
01

Model

anthropic openai gemini local · ollama fallback-router
Every layer is swappable. Don't like our planner? Drop in your own. Want Lucy on local Llama instead of Anthropic? One config line. Prefer to run Intake behind Twilio instead of our SIP? Already there. No forks required.
The Codec suite

One framework. Seven products.

Codec is the runtime. Around it we ship six surfaces (voice, dictation, instant agents, chat, vibe sessions, voice-first) plus an overview surface that ties them together. All open source. All swappable. All shipped from the same monorepo.

01
CODEC Core
Foundation
02
CODEC Dictate
Voice · capture
03
CODEC Instant
Ad-hoc agents
04
CODEC Chat
Long-form
05
CODEC Vibe
Creative flow
06
CODEC Voice
Voice-first
07
CODEC Overview
Orchestration
Coming Q3 2026

CODEC for Mac.
A native app for the seven.

One drag-and-drop install. The full Codec suite, packaged for macOS. Bring your own model. We never resell tokens.

Native Mac app

Built for Apple Silicon. Drag-and-drop install. Menu-bar, hotkeys, system-wide voice. No browser, no Electron tax.

Pick your model

Plug in Anthropic, OpenAI, Gemini, or a local model. Switch per surface. Usage is routed at provider cost × 1.20 — we never resell tokens.

Voice-first

Push-to-talk anywhere. Dictation, conversation, voice agents. The keyboard becomes optional.

Tier 01

CODEC OSS

FreeMIT licensed

Self-host the runtime. Build your own surfaces. We don’t see your traffic.

  • Codec Core, Skills SDK, evals
  • Self-hosted, your cloud, your keys
  • Community support · GitHub Discussions
  • Fork, modify, ship commercial work on top
Buy CODEC — $99/year Star on GitHub

One Mac · one year · renews annually, cancel anytime · your licence key is emailed immediately after payment.

Why we made it open.

We spent two years watching the agent tooling space congeal into closed platforms, each of them trying to be the landlord of your workflows. We don't think that works long-term. The interesting surface area is above the runtime, not inside it.

Codec is our bet that the best agents will be built on open foundations, and the best agencies will be the ones who can run yours end-to-end. You pay us for the people and the playbook. Not the plumbing.

Your data, your box

Self-host on your cloud. We never see customer data unless you ask us to.

No vendor lock-in

Agents and skills are portable. If we disappear tomorrow, you keep running.

Fork & ship

Build your own agent on Codec. Sell it, license it, hide it. No strings.

Read our code

Every skill, every prompt, every eval. If you can't audit the agent, you shouldn't run it.

What Codec replaces

Stop renting. Own the stack.

Every Codec install is a migration out of the SaaS subscriptions that stack up every month. Same tools. Same job. No monthly bill after setup.

You're paying for
Monthly cost
Codec replacement
Cost after setup
ChatGPT Plus
$20/mo
Codec Chat · 250K context, local LLM
$0
SuperWhisper / Whisper apps
$10–15/mo
Codec Dictate · hold, speak, paste
$0
Cursor / Windsurf Pro
$20/mo
Codec Vibe · AI coding IDE + Skill Forge
$0
Grammarly Premium
$12/mo
Codec Instant · right-click AI services
$0
Cloud API costs (OpenAI, etc.)
$50–200/mo
Local Qwen 3.5 35B on Mac Studio
$0
Datadog / monitoring
$15–50/mo
Codec Overview · dashboard + full audit
$0
Total potential savings $125–300+ / month
Path 2 · Personalized installation

We install it for you.

We come to your Mac (or remote-pair) and install Codec end-to-end: your choice of LLM (local Qwen / Llama / Mistral via MLX, or cloud GPT-4o / Claude), Whisper for speech-to-text, Kokoro for text-to-speech, vision UI clicking, Google Workspace OAuth, remote access via Cloudflare Tunnel or Tailscale, audit trail.

Tailored to your workflow. You own the install. We pre-configure every shortcut.

From €500 → Boutique service · tailored to your stack

Your first agent in
about 40 lines.

A working voice receptionist: hooked to your calendar, branded, deployed. Walk through the codec tutorial in under 10 minutes.

skills/weather.py Python · CODEC v3.2
# A CODEC skill: one file, dropped into skills/.
# Voice, chat and any MCP client can call it.

SKILL_NAME = "weather"
SKILL_DESCRIPTION = "current conditions for a city"
SKILL_TRIGGERS = ["weather", "forecast"]
SKILL_MCP_EXPOSE = True

def run(task, context=""):
  city = extract_city(task)
  return forecast(city)

Come build with us
on Codec.

Drop a star, open an issue, ship a skill. The framework is free forever. The agency around it is how we eat.

Try it · interactive demo

Say it. Watch it run.

Pick a voice command and Codec plays its real loop — transcribe, act, confirm — at believable speed, in the framework’s own monospace.

The runtime · live

One voice line, three steps.

Codec hears the words, picks the intent, routes the tools, and reports back. Pick a command — it runs exactly as a deployed agent would.

Try a command
codec · voice-runtime 0.9.4
# codec voice-runtime ready. pick a command on the left. $
Ready when you are

Order online — start this week

Secure Stripe checkout. Confirmation in minutes, kickoff within 24 hours.