Zug, Switzerland – 28 September 2026 – Acurast, the decentralized compute network powered entirely by upcycled smartphones, today announces a groundbreaking milestone in artificial intelligence: the ability to run Laya, the leading open-source “System 1” decision model, securely and at scale. This deployment provides a decentralized, open alternative to proprietary models like TypeSafe’s Jev, moving AI beyond conversational text generation to executing autonomous, real-time decisions without vendor lock-in.
Instead of asking an AI model to produce an answer, Laya receives a problem space, evaluates the current state, and determines the next action in real time. Developed by Convai Innovations and released under the Apache-2.0 license, Laya is an open “System 1” decision model. It doesn’t write text; it selects from the typed options a given application offers—repeatedly, at machine speed. The results appear in a series of public demos.
Alessandro De Carli, Founder of Acurast, said:
“Today’s AI conversation is constantly dominated by ever-larger models generating ever-more text, but not end results. Proprietary models like Jev show the immense demand for rapid decision-making, but they force developers into closed ecosystems. By running Laya on Acurast, we’ve changed that. We are proving that System 1 AI can run securely and at scale on hardware everyone already owns, providing a truly open, decentralized alternative to centralized cloud lock-in.”
To demonstrate the scale and capabilities of this hardware-software convergence, Acurast has deployed live instances of Laya processing a variety of rapid-fire tasks entirely on decentralized mobile edge nodes, including:
- Real-time Gaming: Playing Snake and Tetris, steering in real time and choosing placements for every falling piece.
- Autonomous Navigation: Playing the classic shooter Doom in the original engine, deciding when to shoot, aim, grab items, and explore.
- Instant Classification: Sorting incoming mail into inbox, spam, or phishing.
- Media Evaluation: Judging headlines as news, satire, clickbait, or manipulation using real RSS feeds.
- Security & Moderation: Defending AI assistants against prompt-injection attempts and instantly flagging toxic live-chat messages.
Users can also submit their own inputs (including letters, headlines, strategies, or adversarial prompts), and watch how the model decides.
Running AI workloads typically requires massive, expensive centralized server farms. Acurast shifts this paradigm by harnessing the untapped processing power of everyday mobile devices. Every Laya decision is executed entirely on an Android smartphone operating as a secure node in the Acurast network.
Utilizing the built-in Trusted Execution Environments (TEEs) of these modern devices, Acurast ensures that compute workloads remain completely confidential and verifiable. Decisions are typically delivered in roughly 0.2 to 1 seconds each, using CPU only. Workloads are assigned dynamically across the globally distributed network, results are accompanied by cryptographic proof, and processors are rewarded in ACU, the network’s native token.
Alessandro De Carli, Founder of Acurast, said:
“Our goal is to open developers’ eyes to the quite incredible opportunities that come from using Acurast compute. This deployment proves that decision-oriented AI can run cheaply, verifiably, and without a data center in sight on a decentralized smartphone network today. As autonomous agents evolve, we want developers to realize that the infrastructure they run on can—and should—be as open and distributed as the software itself.”
Developers do not need to wait for a centralized provider to grant API access or allocate server space. The infrastructure is live, demonstrating the unmatched economic profile of running small, continuously operating System 1 workloads on a permissionless network.
Anyone can test the live Laya instances, challenge the model with custom inputs, and watch the real-time execution natively on Acurast edge devices. To try the demos or instantly deploy your own instance, visit laya.acurast.com.
Disclaimer:
We occasionally work with brands we trust to bring you deeply researched content. This article was developed in collaboration with a trusted partner.
With over half a decade of experience commentating on the cryptocurrency market and even more as a trader and investor, Jay has developed a robust knowledge base that enables him to dive deep into the inner workings of crypto platforms and the broader market to deliver unique, user-focused insight.
Jay's work has spanned public relations firms, crypto projects, affiliate sites, and news outlets.
