AGI One
AGI-1
General-purpose agent control system
A cloud-connected desktop agent system for macOS and Windows. Give it a goal in your own language; it understands the active workspace, coordinates the right models, acts across apps and tools, and verifies the result through the AGI-1 cloud backend.
A visible agent, not a static assistant
Enable the optional digital-human mode and the assistant appears as a realtime, audio-synchronized presence. Its face and voice follow the same response that drives the agent system; reasoning, tools, memory, and control stay on the primary path.
This is the actual in-app agent. Digital-human rendering is optional and only starts after you configure its providers.
Audio synchronized
- Wake
- Hear
- Decide
- Act
- Verify
Apple silicon Macs and Windows x64 · your own OpenAI API Key · AGI-1 cloud backend
One spoken sentence, five stages
Every turn runs the same loop. Nothing is faked between stages — if a step can't be verified, it says so instead of claiming success.
- Wake — an offline Vosk model on your Mac listens for the wake word. No audio leaves the machine until you're talking to it.
- Hear — realtime speech, full duplex. Interrupt it mid-sentence and it stops, like a person would.
- Decide — it reads intent from your words, not keywords. Clear instruction: it just does it. Ambiguous or irreversible: it asks first.
- Act — commands first, GUI only when there's no command path. Real cursor and keyboard events, 1:1 logical coordinates.
- Verify — it looks again and checks the result before telling you it's done.
What it does
Talks in real time
Full-duplex speech. Interrupt it mid-sentence and it stops, like a person would. Voice stays live while work is running, so you can ask what's happening or change your mind without waiting.
Acts across the system
The agent selects the fastest available execution path, coordinates tools, handles applications and dialogs, and falls back to the visual interface when needed. Every action stays inside one supervised, verifiable control loop.
Uses your tools
Anything you can do on this Mac, it can do the same way — including the coding tools you already have installed. No integrations to configure: it operates them like you would, and reports back out loud.
Finishes multi-step work
Give it a goal, not a click. It plans, acts, checks the result, and changes approach when a step fails — instead of stopping at the first obstacle or claiming it's done.
Appears as a live digital human
Optional audio-synchronized rendering gives the agent a visible presence with matched speech and motion, without replacing the realtime voice or execution brain.
Thin client, cloud backend
The downloadable app encrypts your OpenAI API Key with the operating system. It sends the key only to the AGI-1 cloud backend while a request is running; orchestration and protected backend logic stay server-side.
Measured, not demoed
Demo videos are easy to cut. So we built a 29-task benchmark — 20 command and file tasks, 9 long-chain GUI tasks — with programmatic checkers. The score is what the checker found on disk and on screen, never what the model said it did.
| Model | Basic 20 | GUI chain 9 | Total | Wall clock | False success |
|---|---|---|---|---|---|
| AGI-1 control route | 20/20 | 9/9 | 29/29 | 9 min | 0 |
| Qwen3.7-Plus | 20/20 | 5/9 | 25/29 | 22 min | 2 |
| Kimi K3 | 18/20 | 4/9 | 22/29 | 95 min | 0 |
GPT-6 powers the primary reasoning and PPAV control route. The desktop shell uses the OpenAI API Key supplied by its owner.
What leaves your machine
Stated plainly, because a thing that watches your screen owes you this.
- Stays local — wake-word detection. The offline model runs on your Mac; microphone audio is not sent anywhere until you've woken it and are speaking to it.
- Goes to AGI-1 while in use — speech, text, screenshots, and task state go to the AGI-1 backend so the cloud agent can understand, plan, execute, meter usage, and verify results.
- Optional digital human — only when you enable it, the android image and assistant output audio go to LemonSlice; synchronized audio/video returns through your configured LiveKit project. Your microphone, screen, and task text are not sent through this path.
- Your OpenAI Key — encrypted by macOS on your computer and sent over TLS only to the AGI-1 backend while processing your request. It is not embedded in the app or published on this website.
The camera is different: it only ever opens when you ask for it out loud, enforced in code against the actual transcript — not left to the model's judgment.
The website's download service keeps limited, privacy-preserving delivery metrics so we can count unique completed downloads and diagnose failed transfers. It never receives your voice, screen, files, API keys, or activity inside the app. Details are in the privacy policy.
Get it
Optional one-time support purchase. The same macOS build is also available as a direct free download.
- AGI-1 for Apple silicon Macs and Windows x64
- Real-time voice interaction
- General-purpose agent control system
- Multi-step task execution
- Screen understanding
- Result verification
- Bring your own OpenAI API Key
- Cloud orchestration with local computer execution
Desktop client build. macOS requires macOS 13 Ventura or later. Windows requires Windows 10 or later on x64. OpenAI bills model usage directly to the API account attached to your key.
Release readiness
| macOS arm64 | Fresh Developer ID signature and Apple notarization pending |
| Windows x64 | Trusted Authenticode signature and timestamp pending |
Two routes: direct download is free. The Polar button is an optional one-time purchase that supports continued development; it does not change the OpenAI usage charged to your own API account.
AGI One 2.0 release candidates are built for Apple silicon Macs and Windows x64. Public downloads remain disabled until the final artifacts pass platform signature, timestamp, integrity, malware scan, clean-machine installation, and update tests. Final SHA-256 values will be published here with the downloads.
Desktop shell -> encrypted OpenAI Key -> AGI-1 cloud backend -> GPT-6 and PPAV.
macOS and Windows release candidates · final platform signing in progress · BYOK desktop shell connected to the AGI-1 cloud backend.