The phone layer that gives every AI agent a real device
Estimated monthly website visits
Similarweb estimates for this domain, not active users. Only available observation months are shown; collection date is separate from the traffic period.
Collected Nov 11, 2026
This is our editors' assessment out of 5, not an average of user ratings. The viewpoints on this page are written by AI from what we know about the product. They are not customer reviews.
According to OpenAITools.app telemetry verified on 2026-11-11, Droidrun (droidrun.ai) is an AI platform indexed under AI Agent generating 7.58K monthly visits with a month-over-month traffic delta of -871 (-10.3%). Its primary geographic market is United States (46.4% traffic share), and it operates on a Free Trial, Contact for Pricing pricing model. Top competing alternatives by monthly volume include Activepieces (258.55K visits/mo), n8n (4.52M visits/mo), Dify (819.69K visits/mo).
Finally, an agent framework that can actually tap mobile apps!
Setup takes some tinkering, but the concept is massive.
Cloud device fleets work like a charm.
Documentation could be clearer.
AI-synthesized perspectives grounded in live site inspection, pricing structure, and category benchmarks — presented as editorial viewpoints rather than individual customer testimonials.
Streamed, scalable Android devices that agents control through an API, removing the need to maintain physical handset labs.
An open layer that connects any AI agent to a phone, with strong published results on the AndroidWorld benchmark.
Describe the outcome you want; the agent reads the screen and decides which taps, swipes and text entries to perform.
Run many phones in parallel for testing, data collection or high-volume workflows.
Cloud phones present a genuine identity so mobile services treat agent traffic as normal app usage.
Agents can move between multiple apps to complete multi-step jobs that no single app supports.
Droidrun's core proposition is straightforward: most agent work happens in desktop apps and browsers, but a huge share of real-world tasks — messaging, marketplaces, banking, ride-hailing, field apps — only exist on phones. Droidrun closes that gap by making a phone a first-class interface for AI agents. The company is a GmbH and packages its offering under the mobilerun name.
Two complementary products make this work. The mobilerun framework is an open layer that connects any agent to a phone, letting you describe goals in natural language and have the agent inspect the screen, decide on actions and execute them. The project reports a 91.4% success rate on the AndroidWorld benchmark, which makes it one of the stronger open mobile-automation stacks. The mobilerun cloud then removes the hardware problem: real cloud phones and device fleets that agents control through an API, with live streaming, horizontal scaling and authentic device identity so services treat them as normal phones.
Because it is open and API-driven, Droidrun suits a wide spread of work: automating testing on real devices, extracting data from mobile-only interfaces, running repetitive cross-app workflows, and building consumer-facing agents that need to act inside apps rather than merely advise the user. The site and repository are the best sources for framework install instructions and cloud onboarding.
Drive regression and exploratory test flows on genuine Android hardware or cloud phones without hand-writing fragile selectors.
Collect information from apps and interfaces that expose no API, using an agent that reads and navigates the UI.
Chain steps across several apps — for example receiving a message, looking something up and placing an order.
Use the open framework and cloud API to add mobile capability to an assistant or autonomous agent product.
Side-by-side telemetry comparison of competing AI tools in the same primary category
| Rank | AI Tool | Monthly Visits | MoM Growth | Direct traffic share | Pricing | Head-to-Head |
|---|---|---|---|---|---|---|
| ● | Droidrun | 7.58K | -10.3% | 40% direct | Free Trial, Contact for Pricing | Current |
| 1 | Activepieces | 258.55K | +1.5% | 43% direct | Freemium | vs Activepieces |
| 2 | n8n | 4.52M | -7.4% | 35% direct | Freemium | vs n8n |
| 3 | Dify | 819.69K | -15% | 57% direct | Freemium | vs Dify |
| 4 | Drizz | 40.75K | -19.1% | 29% direct | Free Trial, Paid, Contact for Pricing | vs Drizz |
| 5 | Sim AI | 140.95K | +20.6% | 52% direct | Freemium, Paid (per user/month), and Enterprise with custom pricing; self-hosting free under Apache 2.0 | vs Sim AI |
| 6 | Hermes-Agent | 3.64M | -5.4% | 29% direct | Freemium | vs Hermes-Agent |
Free / Open-sourceOpen-source AI automation that unifies agents, flows and 770+ app integrations
Free / Open-sourceOpen-source AI automation that unifies agents, flows and 770+ app integrations
Free / Open-sourceOpen-source workflow automation built for AI agents and technical teams
Free / Open-sourceOpen-source workflow automation built for AI agents and technical teams
Free / Open-sourceBuild, deploy, and govern production-ready agentic AI workflows
Free / Open-sourceBuild, deploy, and govern production-ready agentic AI workflows
SpecialistDescribe it in plain English, Drizz tests it on real devices
Free / Open-sourceOpen-source workspace to build, deploy and govern AI agents
Free / Open-sourceA free, open-source personal AI agent that learns your projects and works across every messaging app.
Free / Open-sourceA free, open-source personal AI agent that learns your projects and works across every messaging app.
SpecialistRun a team of AI agents on your own computer
Free / Open-sourceOpen-source personal AI assistant that runs on your own machine and works from chat apps
Free / Open-sourceOpen-source personal AI assistant that runs on your own machine and works from chat apps
Free / Open-sourceSelf-driving agent platform you run in your own cloud
Free / Open-sourceThe open-source collaboration OS where people and AI agents work in one shared workspace.
Free / Open-sourceThe open-source collaboration OS where people and AI agents work in one shared workspace.
GenAI-native end-to-end QA agent that plans, writes and heals tests in plain language
Agent automations your whole company can run
Agent automations your whole company can run
