OpenYabby preview
OpenYabby logo
Productivity Free — open-source, self-hosted (bring your own model API keys)

OpenYabby

Open-source, voice-driven multi-agent platform that runs your terminal, browser, and Mac apps as autonomous agent teams.

Updated 2026-06-29

7.7
AI Score / 10
Visit OpenYabby

Overview

OpenYabby is an open-source, voice-driven orchestration layer that spins up teams of AI agents to carry out multi-step tasks across your Mac — driving the terminal, the browser, and native apps from a spoken instruction rather than a typed prompt. Instead of one assistant answering in a chat window, it coordinates several agents that can each take a slice of a workflow, hand off results, and act on your actual machine.

It's aimed at developers, power users, and tinkerers who already live in the terminal and want hands-free, agentic automation without renting it from a SaaS vendor. Because it's self-hosted and runs locally, your workflow stays on your hardware, and the open-source license means you can read, fork, or extend the agent logic — a meaningful difference from closed competitors like Notion AI's assistant or the various hosted "AI employee" platforms.

The pitch that drove its late-June 2026 launch buzz is the combination of voice as the primary interface with genuine multi-agent execution: speak a goal, and a coordinator delegates to specialized agents that operate your existing tools. That's an ambitious surface area, and it's the same surface area that makes the tool hard to evaluate this early — autonomous agents touching a real terminal and browser is powerful and risky in equal measure.

Key features

Voice-first execution

Spoken instructions are the primary interface — you describe a goal out loud and the system plans and runs it, rather than typing prompts into a chat box.

Multi-agent orchestration

A coordinator delegates work to multiple specialized agents that can run in parallel and hand off results, instead of relying on a single assistant to do everything sequentially.

Acts across terminal, browser, and apps

Agents operate your actual macOS environment — running shell commands, driving a browser, and touching native apps — so workflows execute on your machine instead of in a sandbox.

Open-source and self-hosted

The full stack runs locally under an open-source license, so you can inspect the agent logic, keep data on your own hardware, and extend or fork it; there's no per-seat subscription.

Pricing

Free tier: Yes — the project is free and open-source. There is no paid tier; the practical cost is the model API usage you route through it plus your own hardware.

Open Source Free

Full platform, self-hosted on your own Mac. No subscription tier. Expect to supply your own LLM provider API keys, which carry their own usage costs.

Pros & cons

Pros

  • Genuinely open-source and self-hosted — your workflows and data stay on your own machine, and you can read or fork the agent code
  • Voice-first interface enables hands-free, conversational control of multi-step tasks
  • Coordinates multiple agents in parallel rather than serializing everything through one assistant
  • Acts on your real environment — terminal, browser, and native apps — instead of a walled-off sandbox
  • No subscription; the only recurring cost is the model API usage you choose to route through it

Cons

  • ×macOS-only — no Windows or Linux support, which rules out a large share of users
  • ×Self-hosted setup and likely bring-your-own API keys mean a real technical barrier; this is not plug-and-play
  • ×Brand-new (launched late June 2026) — stability, agent reliability, and edge-case behavior are unproven
  • ×Autonomous agents with real terminal and browser access carry genuine risk if a plan goes wrong; oversight is essential

How it compares

Compare head-to-head

Related reading

Ready to try OpenYabby?

Head to the official site to start with OpenYabby — pricing and plans are listed above.

Visit OpenYabby
← More Productivity tools