OpenYabby

The AI that actually commands your machine.

Say "Yabby" and watch autonomous agent teams plan, code, design, and deploy — with full system access. No buttons. No typing. Just your voice.

yabby — voice session
0 Voice Tools
0 Agent Tiers
0 System Access
0 Buttons Needed

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 smart VAD. Natural conversation in any language. No wake button, no typing, no menus. Speak and Yabby acts — instantly.

WebRTC Wake Word Smart VAD Noise Filter

Multi-Agent Teams

Lead agents create managers and sub-agents. Auto-orchestration handles coordination, reviews, and QA. 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. Qdrant vector search + SQLite. Yabby learns who you are, your preferences, your context — across every session.

Claude-Powered Agents

Each task spawns a Claude CLI process with unique session, system prompt, and full context. Parallel execution with structured logs.

Real-Time Everything

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

Voice to execution.
In seconds.

1

You speak

"Yabby, crée-moi un portfolio dark mode avec une section blog"

Natural voice via WebRTC. Wake word "Yabby" activates. Client-side VAD + noise filter ignores background sounds.

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 — Designer UI phase 1
Lucia — Intégration phase 2
Karim — Backend API phase 2

The lead creates PLAN.md, recruits agents via curl API calls, and sequences work: design first, then frontend + backend in parallel. Each agent is a Claude 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.

Three-tier orchestration
that runs itself.

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

Lead Agent

Project Director

Full API access. Creates teams, 3-phase strategy: plan, review, QA. Reports to you via voice.

is_lead: true phase: planning
Manager

CTO

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

parent: lead debounce: 5s
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

What makes it
actually work.

6 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 curl. No human in the loop.

#4

Auto-triggered reviews

Sub-agent finishes → orchestrator re-spawns the lead to inspect and decide.

#5

Mandatory QA

No project ships without a QA pass. Corrections loop until clean.

#6

Live voice notifications

Agents push milestones. Yabby relays them as speech. Zero polling.

Running in
two steps.

$ git clone https://github.com/openyabby/yabby && cd yabby && npm start
1

Clone & install

Terminal
git clone https://github.com/openyabby/yabby.git
cd yabby
npm install
2

Configure & launch

Terminal
cp .env.example .env
# Add your API keys
npm start

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

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
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

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.