Something to spice up the api
violind4nc3r
Just wondering if we could possibly try for integration with headless ui maybe even selinium or anythingllm, to get device control that would work great with all the tools, templates and automations made, it would turn that into a brain for it honestly, even figuring how to add it to powerautomate or autokey would work
Log In

John at Taskade
Thank you for the ideas. Device and screen control is not in Taskade, for the reasons Narek gave. Here is what works today. Settings > API > MCP connection lets any MCP-compatible desktop AI client read your workspace and edit your apps. Our Public API, with a token from Settings > API, lets scripts and tools such as Power Automate create projects and tasks.
Screen-based macros and vision control are still open, and votes help us prioritize.
- Team Taskade

John at Taskade
Love the vision here — turning Taskade into a "brain" for device control and automation pipelines is exactly the direction things are heading!
A few things that are live now that you might find relevant: MCP Connectors launched in v6.105.0, enabling deeper third-party integrations via the Model Context Protocol — this is the foundation for the kind of extensibility you are describing. Agent Commands v2 (v6.103.0) also added a redesigned slash command system for chaining workflows from within agent conversations.
For Power Automate specifically, our Public API (v6.110.0) opens up webhook and data access options that could serve as the bridge. AnythingLLM and headless browser control (Selenium-style) are not natively supported yet, but MCP connectors are the most likely path to get there.
Check out the connectors screen in settings and drop your ideas in the community: taskade.com/community
Changelog: taskade.com/blog/changelog

John at Taskade
Thanks for this API feedback! We're expanding Taskade's developer capabilities with new endpoints and integrations.
Explore what's available:
- **Taskade Genesis** — generate AI-powered apps and workflows
- **Community Hub** — browse community-built apps
API and developer updates: Changelog | Product Updates
Your feedback helps shape the Taskade developer experience!

John at Taskade
Thanks for sharing this idea!
We hear you.We've been shipping fast — over 100 releases in the past few months — and your feedback helps us prioritize what to build next.
In the meantime, check out what's new:
- Taskade Genesis — generate AI-powered apps, agents, and workflows instantly
- Browse Community — 1000+ free templates and AI agents
- See what's shipped — full changelog and updates
Keep the ideas coming — every vote matters!
Narek Zograbian
Do you have any examples of implementations related to this feature request in other apps?
violind4nc3r
Narek Zograbian, I understand that Claude currently leverages their API to integrate AI into various platforms such as anythingllm with desktop control, including as a standalone platform on their own api on their own platform. Google has added vision capabilities, which GPT-4 also offers through OpenAI, in which taskade also uses as well. Incorporating a vision model or an IFTTT-style trainer for automating tasks with hotkeys or macros could enhance AI operations. This wouldn't necessarily require a headless Python or UI server unless the user was wanting to convert their ai agent to a jarvis-like or similar agent; typical hotkey training could enable GPT to perform actions. Alternatively, starting a foundation for vision on your platform could be beneficial. The focus could be on developing vision capabilities or hotkeys (macros), which GPT could support through a PyTorch base, Puppeteer, or privacy-focused training of agents for screen-based macros. This approach might expand features, especially for mobile actions and remote integration. Also if they dont want necessarily the screen vision then they can opt for the self trained macros(macros are everywhere, from razer in gaming, to autohot key, power automate, and tons other) just a cool suggestion.
breyden
Narek Zograbian screenpi.pe uses multimodal ingestion to create headless workflows from screen recordings, audio, and system logs. Their dev cycle isn't quite as fast as taskade's but it's already imrpvd quite a bit since I've started playing with it (couple months).
Narek Zograbian
violind4nc3r Thanks for the overview! We've actually discussed some of these things too. Currently, the accuracy and costs of using vision in tandem with puppeteer or other programs are not practical yet. As the technology improves, I think we'll look more into adding this functionality into Taskade.
Narek Zograbian
breyden This is definitely an interesting find! Thanks for sharing. I think we'll have to revisit some of these things in the near future for sure. Right now, I think vision + computer control isn't at that level of practicality yet.
violind4nc3r
Narek Zograbian sent you a message, some good ideas i thought may work lol

John at Taskade
Hi violind4nc3r, thanks for the research and for the message with more ideas. Vision-based control and hotkey macros are still open, and your vote counts. If you want an AI on your desktop to work with your workspace now, the MCP connection in Settings > API is the closest option.
- Team Taskade

John at Taskade
Hi breyden, thanks for the screenpi.pe pointer. Building workflows from screen recordings is an interesting approach. Screen-based workflows are not in Taskade yet, and your vote counts. If one of your recorded routines can run as an automation today, tell us which one.
- Team Taskade

John at Taskade
Hi violind4nc3r, thanks for the research and for the message with more ideas. Vision-based control and hotkey macros are still open, and your vote counts. If you want an AI on your desktop to work with your workspace now, the MCP connection in Settings > API is the closest option.
- Team Taskade

John at Taskade
Hi breyden, thanks for the screenpi.pe pointer. Building workflows from screen recordings is an interesting approach. Screen-based workflows are not in Taskade yet, and your vote counts. If one of your recorded routines can run as an automation today, tell us which one.
- Team Taskade