Skip to content
Agents tracked: 492 Releases (7d): 545 Agent status: 1 with issuesSince last limit reset: Claude 9d · Codex 7d For AI agents: Markdown Updated Nov 20, 2026

Manus vs QwenPaw

Manus (Butterfly Effect Pte. Ltd. (Manus AI), Singapore) and QwenPaw (AgentScope team (Alibaba)) side by side on public data, as of Nov 20, 2026.

QwenPaw shipped 6 stable releases in the past 90 days.

Which should you choose?

Choose Manus if

  • you want to work from a browser
  • you want to check in from your phone
  • you prefer the more widely used tool, with more docs and answers around (Gid Score 51 against 35)

Choose QwenPaw if

  • you want to start free: it has a free plan, Manus does not
  • you want code you can read, fork or self-host (Apache-2.0)
  • you need to run local models
  • you want to use your own model API key
  • you want to switch between model providers (7 documented against 0)
  • you work in the terminal

Built from documented features, official prices, status pages and usage data on this page; it does not judge output quality.

Side-by-side numbers

Metric ManusQwenPaw
Gid Score5135
Usage data as ofNov 19Nov 19
Rank by Gid Score#39#118
Downloads, last 7 days—16.9K
Downloads, 7-day change—up 57.2%
Downloads, 30-day change—down 12.4%
VS Code installs——
Marketplace rating4.7 / 5 (40,714)—
GitHub stars—38K
Homebrew installs, 30 days110—
Hacker News mentions, 30 days30
Latest stable release—2.3.0.post1 · 2d ago
Stable releases, 90 days—6
Terminal-Bench (best run)——
Price$20/moFree (OSS)
Incidents, last 30 days0—
LicenseProprietaryApache-2.0
First releasedMarch 2025February 2026
InterfacesWeb, Desktop, Mobile, Browser extension, APIDesktop app, Web app, CLI, Messaging apps, Self-hosted
ModelsManus 2.0 model tiers (Max, standard, Lite); underlying third-party LLMs are not publicly specified—

A dash means there is no public data for that metric as of Nov 20, 2026.

Manus

General-purpose autonomous agent that plans and runs multi-step tasks in a cloud sandbox, such as research, slides, websites and data analysis, with web, desktop, mobile and browser-extension clients. Manus 2.0, announced in September 2026, added a new agent harness, dedicated cloud computers and a desktop studio.

Pricing: Plans at $20/month (4,000 credits a month), $40/month (8,000) and $200/month (40,000), each with 300 refresh credits every day; 17% off billed annually; Teams and Enterprise plans on request. The pricing page shows no free plan (read from the archived screenshot of Oct 23, 2026; the page loads its prices for browsers only).

Full Manus profile

QwenPaw

A self-hosted personal assistant built on AgentScope that runs locally, in Docker or in the cloud, with skills, plugins, MCP, multi-agent support, layered memory and scheduled tasks, and connects to chat channels such as DingTalk, Lark, Discord and Telegram. Its desktop app is in beta, the README says.

Pricing: Free Apache-2.0 software that runs local QwenPaw models or your own cloud provider keys.

Latest release 2.3.0.post1:

  • feat(agent): extract third-party agent into plugins
  • feat(console): quote response selections in follow-up drafts
  • fix(console): restore Safari message queue action icons
  • fix(cron): track scheduled agent runs

Full QwenPaw profile

Manus vs QwenPaw: common questions

How do Manus and QwenPaw prices compare?

Manus: $20/mo. QwenPaw: Free (OSS). Prices come from each vendor's pricing page.

Is Manus or QwenPaw open source?

QwenPaw is open source (Apache-2.0); Manus is proprietary.

Which is more popular, Manus or QwenPaw?

Manus has a Gid Score of 51 against 35 for QwenPaw. The score combines package downloads, editor installs, GitHub activity and attention, updated daily.

Do Manus and QwenPaw support local models?

QwenPaw documents support for local models; Manus's documentation does not.

Do Manus and QwenPaw support MCP servers?

QwenPaw documents support for MCP servers; Manus's documentation does not.