A general agent you delegate to, or a system that acts on what arrives.
Manus is a polished general AI agent. Multi-surface across web, mobile, desktop, browser, and cloud, with persistent memory and scheduled tasks. You go to Manus, ask it to do something, it does it. this+that is different. It's a comms-forward AI that reads the messages your team receives whether you asked for them or not, scans every email and chat for what needs doing, and runs workflows. Two different shapes of AI for work, not really direct alternatives.
A general personal agent, or a comms-forward AI for your team's messages
AI assistants come in different shapes. We think of three waves: Wave 1 is the general-purpose chat you open and ask (Claude, ChatGPT, Gemini, Copilot). Wave 1.5 is the polished personal agent layered on top of chat. Wave 2 is the fit-for-purpose AI that owns one job end-to-end, with UI tailored to it (more in our essay on AI's second wave).
Manus sits in Wave 1.5, the polished personal-agent tier between raw chat and fit-for-purpose Wave 2 products. It is one of the most ambitious products in the tier: a general agent that runs in your browser, on your desktop through the My Computer app, in a managed Cloud Browser, on mobile, and from the web. Persistent memory carries context across sessions, and Scheduled Tasks 2.0 lets work resume on a recurring cadence inside an existing conversation thread. The product has serious momentum, with a Series B led by Benchmark in 2025 and reported ARR crossing $100M by year-end. Like the rest of Wave 1.5, it is still chat-shaped at the core. You still go to Manus and ask. this+that is one of Wave 2's first products. The agent reads the messages you receive whether you asked for them or not. Every Gmail or Outlook message, Slack thread, Teams chat, Google Chat, and Telegram DM gets scanned for what needs doing, surfaced as tasks for the whole team, and runs through workflows. Most people who use Manus would also benefit from a Wave 2 product handling their team's inbox. They solve different problems.
Feature by feature
How the two products compare across the things that matter most.
| Topic | Manus | this+that |
|---|---|---|
| Category | Wave 1.5. General agent across web, desktop, browser, and cloud surfaces, wrapping general-purpose models. Same shape as OpenClaw, Town, and Hyperagent. | Wave 2. Fit-for-purpose AI that lives inside the work surface, acting on messages that arrive without you asking. |
| Where work starts | With you. You ask Manus to do something, it does it. Scheduled Tasks 2.0 add recurring runs (daily, weekly, monthly) inside an existing conversation thread. | With incoming messages. The agent reads what arrives without being asked and surfaces what needs doing. |
| Surfaces | Web app, mobile, desktop "My Computer" app (can drive your local machine), Browser Operator extension for your local browser, and a managed Cloud Browser. | Web app, browser extension (DoBox for Gmail), and a public MCP server reachable from any AI client. |
| Channels read | None as continuous inputs. Manus reads Gmail, Calendar, Drive, Slack, Notion, HubSpot, GitHub, and Hugging Face through MCP connectors when you ask. | Gmail, Outlook, Slack, Teams, Google Chat, and Telegram. Every message scanned for what needs doing. |
| Task extraction from messages | Not a focus. Tasks come from you delegating to Manus, not from messages arriving for you. | Core capability. DoBox scans every message across every channel for requests, commitments, deadlines, and follow-ups, surfaced as assignable tasks for the team. |
| Memory / knowledge | Persistent cross-session memory implemented as a cloud-based file system of episodic records, checklists, and prior tasks. Single-user. | The brain. A writable team knowledge layer with personal and team spaces. Agents read and write. Pages can be published outward through public artifacts. |
| Workflows / routines | Scheduled Tasks 2.0: daily, weekly, or monthly recurring runs that resume inside an existing conversation thread, carrying instructions, files, and prior results forward. | Plain-language workflow builder. 32 action types. IF/ELSE branching, loops, and sub-agents. Triggered by messages or schedules. |
| Team capabilities | Team plan from $20/seat/mo (2-seat minimum) with SSO, shared credit pool, and 8,000+ credits per seat. Memory remains personal. | Team task assignment, shared task view, and team-request grounding (your agent searches a teammate's brain to draft a suggested reply). |
| Trust controls | Explicit approval before major actions (sending email, placing orders, executing on the local machine). Desktop offers Allow Once / Always Allow. Cloud Browser has Takeover Mode where you handle credentials and payments. | Approval gates on every workflow action. Drafts not sends by default on outbound. Provenance: every task links back to the source message. |
| Integrations | MCP connectors with OAuth: Gmail, Google Calendar, Google Drive, Slack, Notion, HubSpot, Stripe, GitHub, Hugging Face. Custom MCP servers supported for internal tools. | Open MCP standard. Any tool with an MCP server or API plugs in. |
| Pricing | Free (300 daily refresh credits, 1 concurrent task), Standard $20/mo (4,000 credits), Customizable $40/mo (8,000), Extended $200/mo (40,000), Team from $20/seat/mo (2-seat min). Annual saves 17%. | Free during beta. |
- Manus is one of the most ambitious general agents in Wave 1.5. The surface coverage (web, mobile, desktop, browser extension, cloud browser) is wider than most of the field.
- Persistent memory plus Scheduled Tasks 2.0 is a genuinely useful pairing: recurring work picks up inside the original thread with prior context already there.
- Allow Once / Always Allow on the desktop app and Takeover Mode in the Cloud Browser are sensible approval primitives for an agent that can act on real machines.
- Credit-based pricing scales cleanly: a real Free tier for trying, Standard at $20/mo, up to Extended at $200/mo for heavy use. Team plan adds SSO and a shared credit pool.
- MCP connectors with OAuth cover a useful slice (Gmail, Calendar, Drive, Slack, Notion, HubSpot, Stripe, GitHub) plus custom MCP for internal tools.
- Serious momentum: a Series B led by Benchmark in 2025 and reported ARR crossing $100M by year-end. For a single power user delegating across surfaces, Manus is a strong pick.
- A different category. The agent reads the messages you and your team receive across email, Slack, Teams, Google Chat, and Telegram, and acts on them without you asking.
- DoBox: every message scanned for tasks, with the whole team able to see, assign, and track them in one place.
- Plain-language workflow builder triggered by incoming messages. 32 action types, branching, loops, sub-agents.
- The brain is a writable team knowledge layer (not single-user memory) that agents read and update as a side effect of doing real work.
- Open MCP, not a closed integration list — any tool with an MCP server or API plugs in.
- Team-first design: task assignment, shared views, and team-request grounding are first-class capabilities, not personal features.
See what's waiting in your inbox
Connect your inbox and get a free analysis of the tasks, follow-ups, and open commitments this+that would surface across your channels.
Free to use · No credit card required