v0.1.3 · Open-source release for macOS

OpenYabby

Voice-driven multi-agent execution. On your desktop.

Say "Yabby". Speak a task, approve a plan, and let local agents execute real project work through CLI runners, connectors, review, and QA. MIT-licensed and built in public. Open-source on macOS today, native desktop app for Mac, Windows & Linux coming next.

Get Started View Source
yabby :: voice session
0 CLI runners
0 Connectors
0 Channels
0 Built-in tools
What It Does

Your Mac, fully
autonomous.

Yabby doesn't just chat. It executes. Terminal, browser, files, apps. Everything.

Voice-First. Always.

Bidirectional audio via WebRTC. Wake word “Yabby” with Silero VAD and optional speaker verification. Natural conversation in any language. No wake button, no typing. Speak and Yabby acts instantly.

WebRTC Wake Word Silero VAD Speaker ID Noise Filter

Multi-Agent Teams

Lead agents create managers and sub-agents. Auto-orchestration with cascading task queues: parallel within a phase, sequential across phases. Your project team runs itself.

Full System Access

Terminal, AppleScript, Playwright, file system, browser DOM. Agents never say “I can't”. They find a way and execute it.

Persistent Memory

Mem0 extracts facts from conversation every 6 turns. Qdrant vector search + SQLite. Yabby learns who you are, your preferences, your context. Persistent across every session.

Multi-Runner Support

Claude Code (default), OpenAI Codex, Aider, Goose, Cline, or Continue CLI. Each task spawns a CLI process with its own session, system prompt, and full context.

Real-Time Everything

SSE + WebSocket live feed of tool calls, agent progress, and task completions. Redis pub/sub for inter-agent messaging. Watch your AI workforce in real time.

Multi-OS · Desktop

The app is almost
ready.

The open-source project runs on macOS today. A native desktop app for Mac, Windows, and Linux is coming next. Drop your email and we’ll let you know the day it’s ready to test.

Step 1 of 8

Enter your email to save your spot. We’ll email you the moment it opens up.

How It Works

Voice to execution.
In seconds.

1

You speak

"Yabby, build me a dark mode portfolio with a blog section"

Natural voice via WebRTC. Wake word "Yabby" activates. Client-side VAD + noise filter ignores background sounds. Optional speaker verification ensures only your voice triggers it.

2

Yabby assigns a lead

create_project → Portfolio assign_agent → Marc (lead) talk_to_agent → brief sent

Three tool calls in one response. Yabby creates the project, assigns a single lead agent, and sends the full brief. The lead builds the team autonomously.

3

Lead builds the team & executes

Sofia / UI Design phase 1
Lucia / Frontend phase 2
Karim / Backend API phase 2

The lead submits a plan for your approval, recruits agents, and sequences work: design first, then frontend + backend in parallel. Each agent is a CLI process with full Mac access.

4

Auto-review, QA & delivery

When tasks complete, the orchestrator auto-triggers the lead for review. The lead inspects the sandbox, creates a QA agent, and only marks the project complete when QA passes. You get a voice notification. Zero micromanagement.

Agent Architecture

Three-tier orchestration
that runs itself.

Agents communicate via Redis pub/sub. Completions cascade up automatically.

Lead Agent

Project Director

Full API access. 5-phase workflow: discovery, planning, execution, review, QA. Submits plans for user approval. Reports to you via voice.

is_lead: true plan_review
Manager

CTO

Coordinates dev sub-agents. Auto-triggered review on task completion. 5s debounce.

parent: lead cascade
Manager

CDO

Manages design team. Reviews visual output, ensures consistency.

parent: lead auto-review
Sub-Agent

Frontend

Sub-Agent

Backend

Sub-Agent

UI/UX

Sub-Agent

QA

Integrations

Connected to
everything.

Channels, connectors, and MCP servers. Yabby talks to the tools you already use.

5 Channels

Discord, Slack, Telegram, WhatsApp, Signal. Same tools as voice. Slash commands, group mentions, per-thread agent binding.

37 Connectors

GitHub, Jira, Linear, Notion, Google Drive, Stripe, and more. Built-in or MCP-backed. Project-scoped with encrypted credentials.

MCP Servers

Spawn and manage Model Context Protocol servers. Tool schemas auto-bridged to OpenAI format. Works with any MCP-compatible tool.

Scheduled Tasks

Cron, interval, or manual triggers. The built-in scheduler ticks every 30s, retries on failure, and recovers orphaned runs on startup.

Under the Hood

What makes it
actually work.

7 design decisions that define how Yabby operates.

#1

Voice + action, same response

Speaks and calls tools simultaneously. No "let me do that for you". It's already done.

#2

Full Mac access per agent

Bash, AppleScript, GUI control. Write files, run servers, take screenshots, open apps.

#3

Agents recruit agents

The lead builds its own team via API calls. No human in the loop for team formation.

#4

Plan review & approval

Leads submit plans for your approval before execution. Approve, revise, or cancel via voice or UI modal.

#5

Auto-triggered reviews

Sub-agent finishes → orchestrator re-spawns the lead to inspect and decide. 5s debounce, 10s delayed re-check.

#6

Mandatory QA

No project ships without a QA pass. Corrections loop until clean. Hallucination detector catches false claims.

#7

Live voice notifications

Agents push milestones to SSE + WebSocket. Yabby relays them as speech. Also forwarded to WhatsApp.

Get Started

Running in
two steps.

$ git clone https://github.com/OpenYabby/OpenYabby && cd OpenYabby && npm i && npm run dev
1

Clone & configure

Terminal
git clone https://github.com/OpenYabby/OpenYabby.git
cd OpenYabby
npm install
cp .env.example .env
# Add your API keys
2

Launch

Terminal
npm run dev
# → http://localhost:3000
# Say "Yabby" to start talking

Requires Node.js, PostgreSQL, Redis, Claude CLI, and an OpenAI API key.

Built With

Serious infrastructure.

OpenAI RealtimeVoice I/O
Claude CLIAgent brain
WebRTCAudio stream
PostgreSQLSource of truth
RedisPub/sub + cache
Mem0Memory engine
QdrantVector search
Node.jsRuntime
WhisperTranscription
Silero VADVoice detection
SpeechBrainSpeaker ID
MCPTool protocol
OpenAI RealtimeVoice I/O
Claude CLIAgent brain
WebRTCAudio stream
PostgreSQLSource of truth
RedisPub/sub + cache
Mem0Memory engine
QdrantVector search
Node.jsRuntime
WhisperTranscription
Silero VADVoice detection
SpeechBrainSpeaker ID
MCPTool protocol
Why "Yabby"?

Named after the Australian crayfish.

A yabby (Cherax destructor) is a small freshwater crayfish native to Australia. Tough, resourceful, and surprisingly effective. They thrive in creeks, dams, and rivers across the continent.

Like its namesake, OpenYabby is compact but powerful. Small claws, big results. It burrows into your system, finds what it needs, and gets the job done. Autonomously, relentlessly, without fuss.

🦾
Resourceful Adapts to any environment
💪
Tenacious Never gives up on a task
🌊
Native Lives on your machine

Ready to command
your AI task force?

Open source. Self-hosted. Your machine, your data, your rules.

Star on GitHub Join Discord
Ship now