Flushnet AI Runner
Flushnet AI Runner
The AI automation Agent that runs your computer and browser.
Run browser, terminal, and AI tasks across your machines and remote nodes from one place.
The fastest way to connect a machine, launch a task, watch execution, and get the result from one operator layer. Use your own machines or secure sandboxes. Run tasks in parallel. Control everything from the dashboard, API, or AI assistant.
Start free
Install agent
View docs
AI that uses your computer & browser
AI Runner turns requests into real actions across desktop, browser, mobile, and connected devices.
Use one AI operator layer to organize files, automate workflows, fill forms, test apps, run programs, manage email and calendars, compare products, create reports, place calls, chat on Telegram or WhatsApp, and control IoT devices.
Built for practical execution: browser automation, terminal tasks, multimodal AI, mobile camera and voice input, call center and conferencing flows, sandbox and virtual machines, RAG memory, third-party app integrations, and support for ChatGPT, Claude, Gemini, Ollama, Hugging Face, and llama.cpp.
Some of the tasks you can ask AI Runner to do
- Organize my computer files
- Automate and run this workflow
- Fill in this online form for me
- Build and test a mobile app
- Run a program on my computer
- Check the last emails from my boss and write a reply with the latest work updates
- Test and debug my app
- Write and post my new event to my Facebook page
- Create a photo gallery of my personal photos
- Book a restaurant reservation
- Search and compare prices for this product
- Search in “My Documents” for statements and write a full report in PDF format
- Schedule an appointment on my calendar
- Dial this telephone number
- Read my Telegram and WhatsApp messages
- Use the mobile phone app or desktop app with live audio voice to open and write an MS Word document
- Use the mobile camera app to send photos and videos to this chat
- Use the mobile app to show my current AI Runner tasks
- Chat with AI Runner from Telegram and WhatsApp in text and audio chat
- Enable all my home IoT smart devices such as sockets, cameras, and robots
More features include
- Windows and Mac installers
- Support for OpenAI ChatGPT models 5.4, 5.3, and 5.2, Anthropic Claude, and Google Gemini
- Full integration with OpenClaw, open-source, and third-party AI agents
- Integration with Ollama, Hugging Face, and llama.cpp
- Full multimodal support and custom multimodal AI models
- Task and workflow optimization
- AI multi-channel support including IoT, WhatsApp, Telegram audio, phone, call center, video call, multi-user conference, and more
- Third-party and open-source app integration
- Sandbox and virtual machine mode
- RAG and persistent long-term AI memory support
- Login verification via access code and 2FA authentication
See real use cases · Open AI Runner Chat · Contact support
Browser tasks
Open a site, click, type, capture a screenshot, or run repeatable browser automation on a connected machine.
Terminal and file tasks
Run commands, inspect output, move files, and validate changes on a real machine or in a safer sandbox first.
AI and batch jobs
Launch compute workflows, repo jobs, or repeated tasks across one node or many machines from the same control layer.
Start here
Beginner, professional, and enterprise step-by-step examples are in the Help page, including custom GPT, sandbox-first, native machine, and rollout workflows.
Open use cases
Pricing
Start free, upgrade for native machine control, larger queues, and broader orchestration when you are ready.
Compare plans
Competitive comparison
AI Runner vs Claude Desktop vs Manus AI vs OpenClaw vs OpenHands
Yes = publicly documented
Yes (private/internal) = confirmed available, but not publicly documented
Partial = available in some modes, plans, or indirect workflows
No = not part of the product
Unknown = not enough reliable information
| Feature |
AI Runner |
Claude Desktop |
Manus AI |
OpenClaw |
OpenHands |
| Desktop app / desktop execution | Yes | Yes | Yes | Partial | Partial |
| Browser automation | Yes | Partial | Yes | Yes | Yes |
| Terminal / shell execution | Yes | Partial | Partial | Yes | Yes |
| Local file access | Yes | Yes | Yes | Yes | Yes |
| Sandboxed / isolated environment | Yes | Unknown | Yes | Partial | Yes |
| Remote nodes / execute on another machine | Yes | Unknown | Unknown | Yes | Partial |
| Parallel workflow execution | Yes | Partial | Partial | Partial | Yes |
| Distributed workflow management | Yes | Unknown | Partial | Yes | Partial |
| Telegram support | Yes | No | No | Yes | No |
| WhatsApp support | Yes | No | No | Yes | No |
| Calendar actions | Yes | Partial | Yes | Partial | Unknown |
| Email workflows | Yes | Partial | Yes | Partial | Unknown |
| Phone / call flows | Yes | No | No | Partial | No |
| IoT / connected device control | Yes | No | No | Partial | No |
| IoC integration | Yes | Unknown | Unknown | Partial | Unknown |
| Scheduling / cron / recurring automations | Yes (private/internal) via AICRON | Yes | Yes | Yes | Partial |
| API / programmatic access | Yes | Yes | Yes | Yes | Yes |
| GitHub integration | Yes | Partial | Partial | Partial | Yes |
| Multi-model / model-agnostic | Yes | No | Unknown | Yes | Yes |
| Open source | Unknown | No | Unknown | Yes | Yes |
| Self-hosted | Partial | No | Unknown | Yes | Yes |
| Build scripts | Yes | Partial | Yes | Partial | Yes |
| Build web apps | Yes | Partial | Yes | Partial | Partial |
| Build desktop apps | Yes | Partial | Yes | Partial | Partial |
| Build mobile apps | Yes | Partial | Unknown | Partial | Partial |
| Autonomous agentic long-running tasks | Yes | Yes | Yes | Partial | Yes |
| Built-in slide generation | Unknown | Unknown | Yes | Unknown | No |
| AI Gateway | Yes (private/internal) | No | No | Yes | No |
| AICRON | Yes (private/internal) | No | No | No | No |
Positioning summary
- AI Runner: strongest for operational automation plus autonomous, agentic long-running tasks across desktop, browser, files, messaging, calls, devices, security and investigation workflows like IoC integration, private orchestration, parallel and distributed workflow management, and app or script building.
- Claude Desktop: strongest as a Claude-first desktop assistant with extensions, local workflows, and some agentic computer use.
- Manus AI: strongest for delegated autonomous execution and deliverables like reports, slides, and app or website-style outputs.
- OpenClaw: strongest as an open-source, self-hosted gateway and automation layer with channel integrations and remote execution.
- OpenHands: strongest as an open-source software engineering agent platform for autonomous coding tasks, with CLI, web UI, self-hosting, sandboxed execution, browser plus bash tools, GitHub-oriented workflows, and an agent SDK.
Unique or standout features
- AI Runner: private and internal orchestration layers like AI Gateway and AICRON, cross-channel operations including messaging, calls, IoT, and distributed workflow management.
- Claude Desktop: strongest native Claude-centered desktop assistant experience with Anthropic’s ecosystem and extensions.
- Manus AI: strongest packaged autonomous deliverable flow, especially for slides, reports, and polished end outputs.
- OpenClaw: strongest open-source gateway pattern for connecting channels, automation, and remote execution.
- OpenHands: standout strengths are its software-agent SDK, ephemeral or local workspaces, CLI plus web UI plus cloud/self-hosted deployment mix, and GitHub workflow support for software engineering tasks.
Notes
- For AI Gateway and AICRON, the status is marked Yes (private/internal) because they exist but are not publicly documented.
- IoC integration is included for AI Runner based on confirmed product information.
- Parallel workflow execution and distributed workflow management are included for AI Runner based on confirmed product information.
- GitHub integration is included for AI Runner based on confirmed product information.
- Unknown does not mean a feature is absent. It means there is not enough reliable public information to mark it confidently.
- Partial means the feature exists in some plans, modes, or adjacent tooling, but is not a simple core feature in every setup.