Blogs
Wide Research: Beyond the Context Window
Ever noticed your AI assistant starts fabricating results when researching a long list of items? It's a common frustration known as the 'fabrication threshold,' caused by the inherent limitations of AI context windows. This article dives into why even the largest context windows can't solve this problem and introduces a new architectural paradigm: Wide Research.
Introducing Manus 1.5
We released Manus 1.5: faster, higher quality, unlimited context, and an upgraded builder to create full apps in one prompt with backend, login, databases, AI features, notifications, and analytics.
Introducing Wide Research
Wide Research marks a milestone in our exploration of the scaling laws of AI agents, but it’s just the beginning.
Context Engineering for AI Agents: Lessons from Building Manus
This post shares the local optima Manus arrived at through our own "SGD". If you're building your own AI agent, we hope these principles help you converge faster.
What we saw in the past three months. And what we see in the future.
We're witnessing a fundamental shift in how humans and AI collaborate, moving beyond simple chat interaction to true task delegation and outcome-focused partnership.
Manus is Hiring!
We're hiring across our offices in Singapore, San Mateo (California) and Tokyo.