Manus is a general AI agent that turns your thoughts into actions. It excels at various tasks in work and life, getting everything done while you rest.
This is the 9th launch from Manus. View more
Manus Scheduled Tasks 2.0
Launched this week
Manus now runs scheduled tasks inside the same task context, reuses Project setups, and adds recurring actions to Manus-built web apps.
For knowledge workers and teams automating repeatable workflows in Manus.
Free Options
Launch Team
Manus-built web apps can now run their own scheduled actions. That detail is easy to skim past, but it changes what kind of software Manus can actually produce.
What it is: Scheduled Tasks 2.0 is a system-wide upgrade to recurring work in Manus, covering task continuity, Project configuration inheritance, and embedded scheduling inside Manus-built web apps.
When you build an app with Manus, you are not just generating a static interface. You are building something that could, in principle, maintain itself.
A dashboard that refreshes its own data every morning. A reporting tool that generates its weekly summary without prompting. A client-facing app that sends reminders on a schedule. With this update, those behaviors are configurable inside the app rather than managed externally by the user.
What makes it different: Most agent scheduling tools treat the schedule as something you bolt on from outside. Manus is treating it as something native to the task, Project, or app where the work actually lives. The schedule inherits the context of its environment rather than running in a vacuum.
Key features:
Embedded scheduled actions inside Manus web apps (refreshes, summaries, reminders, script runs)
Same-task continuation mode for recurring work that depends on existing context
Project-level context and configuration inherited by scheduled tasks
Connector support for linked data sources
Skip confirmations for trusted automated pipelines
Calendar, schedule, and history views for run oversight
Benefits:
Apps built with Manus can stay live and updated without the creator manually triggering runs
Recurring analysis and reporting stays coherent across cycles
Easier to manage and audit scheduled work across tasks and Projects
Who it's for: Builders and operators using Manus to create client-facing or internal tools that need to stay current without constant manual input.
A scheduling system embedded in an app-building agent is a different product category than a task scheduler with a cron job underneath. That is the direction Manus is pointing.
P.S. I hunt the latest and greatest launches in tech, SaaS and AI, follow to be notified → @rohanrecommends
Scheduled tasks get much more usable once each run leaves a receipt a human can inspect later. For me that means trigger, owner, tool or capability scope, files or services touched, stop reason, and whether the task finished cleanly or stopped at a guardrail. That is what keeps background automation from becoming mystery work.
The 'same task context' detail is what makes this interesting. Most schedulers fire a fresh run and lose all accumulated state. Reusing context means the agent builds on previous cycles instead of starting blind. How does a mid-run failure get handled? Does it resume or restart cleanly?
Persistent task context is underrated. Most agents still operate like stateless assistants, so recurring workflows with memory and continuity make this feel more operationally useful instead of just experimental.
scheduled tasks that reuse project setup is the feature that separates a useful automation from a demo. having to reconfigure context every time a recurring task runs is exactly the kind of friction that makes people abandon agent tools after the first week. whether this actually holds up across edge cases is a different question