OpenYabby
Open-source, voice-driven multi-agent platform that runs your terminal, browser, and Mac apps as autonomous agent teams.
Updated 2026-08-10
Yes. OpenYabby is free to use.
Listed pricing: Free — open-source, self-hosted (bring your own model API keys).
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, a coordinator delegates slices of a workflow to specialized agents that hand off results and act on your actual machine.
It's aimed at developers and power users who already live in the terminal and want hands-free agentic automation without renting it from a SaaS vendor. Self-hosting means the workflow stays on your hardware, and the open-source license means you can read, fork, or extend the agent logic — the real distinction from hosted computer-use agents and the closed "AI employee" platforms, where the orchestration layer is a black box you rent by the seat.
The bet behind its June 2026 launch was voice as the primary interface layered on genuine multi-agent execution. That was a sharper differentiator at launch than it is now: agentic CLIs and vendor computer-use agents have converged on much of the same surface area during 2026, which leaves OpenYabby competing mostly on openness and local control rather than on capability. As of August 2026 there's still no independent reliability record for it, and autonomous agents with live terminal and browser access remain useful and risky in equal measure.
Is OpenYabby free?
Yes. OpenYabby is free to use.
What the free tier covers: Yes — the project launched free and open-source with no paid tier. The practical cost is the model API usage you route through it plus your own hardware. Terms have not been re-verified since launch; check the repository.
Listed pricing: Free — open-source, self-hosted (bring your own model API keys).
Pricing verified . That is the date the plans were last re-checked against the vendor's own pages, not today's date. Confirm on the official site before you pay.
OpenYabby pricing
| Plan | Price | What's included |
|---|---|---|
| Open Source | Free | Full platform, self-hosted on your own Mac. No subscription tier was offered at launch. You supply your own LLM provider API keys, which carry their own usage costs. Check the project repository for current terms. |
Full platform, self-hosted on your own Mac. No subscription tier was offered at launch. You supply your own LLM provider API keys, which carry their own usage costs. Check the project repository for current terms.
Pricing verified . That is the date the plans were last re-checked against the vendor's own pages, not today's date. Confirm on the official site before you pay.
Is OpenYabby worth it?
Worth it for Mac developers and terminal-native power users who want self-hosted, voice-driven agent automation running on their real machine rather than a rented computer-use agent in a vendor sandbox.
You can test that on the free tier before paying anything. The recorded trade-offs are listed below, and any one of them can settle the question on its own.
The 7.4/10 AI Score is an editorial read of published capability, price and shipping pace. Nobody here has hands-on hours with OpenYabby. How we verify.
Worth it if
The strengths recorded against this entry.
- Genuinely open-source and self-hosted — workflows and data stay on your own machine, and the agent logic is readable and forkable
- 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 or per-seat fee; the only recurring cost is the model API usage you choose to route through it
Not worth it if
Any one of these blocks your use case.
- macOS-only — no Windows or Linux support, which rules out a large share of potential users
- Self-hosted setup plus bring-your-own API keys is a real technical barrier; this is not plug-and-play
- Launched June 2026 with no independent reliability or benchmark record as of August 2026, and autonomous agents holding live terminal and browser access carry genuine blast-radius risk
- The voice-plus-agents pitch is less distinctive than it was at launch, now that agentic CLIs and vendor computer-use agents cover much of the same ground
What sets OpenYabby apart
- Voice as the primary interface rather than typed prompts or a chat window
- Open-source and self-hosted, so the orchestration layer itself is inspectable and forkable — hosted computer-use agents are not
- Model-agnostic by design: you bring your own provider API keys instead of being locked to one vendor's model
- No subscription or per-seat tier at all; cost is your own model API usage
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 work through everything sequentially.
Acts across terminal, browser, and apps
Agents operate your actual macOS environment — running shell commands, driving a browser, touching native apps — so workflows execute on your machine rather than inside a vendor sandbox.
Open-source and self-hosted
The stack runs locally under an open-source license, so you can inspect the agent logic, keep data on your own hardware, and swap in whichever model provider you hold keys for.
How it compares
| Tool | Best for | Pricing | Score |
|---|---|---|---|
| OpenYabby | Mac developers and terminal-native power users who want self-hosted, voice-driven agent automation running on their real machine rather than a rented computer-use agent in a vendor sandbox. | Free — open-source, self-hosted (bring your own model API keys) | 7.4/10 |
| n8n | Developer-adjacent ops and engineering teams who want AI agents and internal integrations running on infrastructure they control, with server costs instead of a per-task meter. | Free self-hosted + Cloud from ~$20/mo | 8.7/10 |
| Make vs Make → | Teams building multi-step, branching automations who want to see the whole flow on a canvas rather than describe it as a list of steps. | Free tier with 1,000 credits/mo; paid from $9/mo for 10,000 credits | 8.7/10 |
| Fathom vs Fathom → | Founders, consultants and small sales teams living in Zoom or Google Meet who want unlimited call recording and CRM-synced summaries without a visible bot joining client calls. | Freemium — generous free tier; paid Premium and Team plans priced per seat (check website for current rates) | 8.5/10 |
Compare head-to-head
Comparison explorer Put OpenYabby up against any three tools Opens with OpenYabby already loaded. Add up to three more from the full index and read pricing, features, pros and cons in one table. →Related reading
Claude Riemann Hypothesis Result: 41.6% to 67.2%
Anthropic says an unreleased Claude raised the proven fraction of Riemann zeta zeros on the critical line from 41.6% to 67.2%. Here is what that means.
GPT-5.6-Cyber vs GPT-5.6 Sol: The Daybreak Split
OpenAI's GPT-5.6-Cyber is gated on authorized cybersecurity work. The Daybreak Blue and Red tiers, the 95% claim, and who each model is meant for.
Muse Glimmer and the 30B Open-Weights Ceiling
Meta released Muse Glimmer's 30B weights under Apache 2.0, landing in the same consumer-GPU size class as every other recent open model release.
Ready to try OpenYabby?
Head to the official site to start with OpenYabby — pricing and plans are listed above.
Visit OpenYabby