Skyvern vs Openclaw

Side by side, as alternatives to Manus. Rows that differ are highlighted; the strongest value in a row is marked. Unknown means no source yet.

Also replaces Manus: + DeerFlow + OpenManus + AgenticSeek + Kortix (formerly Suna)+ OWL + Nanobrowser

SkyvernSkyvern-AI/skyvern

Openclawopenclaw/openclaw

Manuspaid product

Cost and coverage

Price

$0 software; you run it

See pricing page source ↗

Autonomous web browsing

Partly

Yes

Deep research reports

Yes

File and code tasks in a sandbox

Yes

Slides generated from a prompt

Yes

Scheduled agent tasks

Partly

Yes

Connectors to your apps

Yes

Jobs covered

1 of 6 jobs

All 6

Popularity and activity (from GitHub)

Stars

23,239

392,686Top

—

Gain this week

Unknown

—

Signal

Building history

—

Commits / 4 wk

228

14,028Top

—

Latest release

v1.0.56 · 2026-10-14

v2026.10.5 · 2026-10-18Top

—

Commits / 12 wk

716

42,127

—

People committing / 12 mo

42+

498+

—

Issues opened / closed, 30 days

17 / 3

5573 / 4501

—

Facts, with sources on each project page

Runs on my machine?Differs

Yes, local server and UI via pip or Docker Compose; also hosted Skyvern Cloud

Yes, self-hosted gateway; hosted or local model providers

Hosted by the vendor

Code licenceDiffers

AGPL-3.0 (copyleft); anti-bot features are cloud-only

MIT

—

Model weights licenceDiffers

No separate model weights; you bring a cloud API key or a local Ollama model

No bundled weights; depends on the hosted or local model you connect

—

Commercial useDiffers

AGPL-3.0; offering a modified version as a network service requires sharing its source

Yes, MIT code

—

Paid services needed?Differs

Nothing paid with a local Ollama model; cloud LLM APIs and Skyvern Cloud (with anti-bot measures) are optional

No OpenClaw paid tier; configured model/provider or hosting costs may apply

Subscription

HardwareDiffers

About 4 GB RAM for 1-2 concurrent browser runs, 8 GB for 3-5, 16 GB for 6-10, 32 GB+ beyond; 2 GB minimum per Kubernetes pod

Gateway with cloud models: minimum 1 GB RAM, 1 core, 500 MB free disk, 64-bit OS; 2 GB+ RAM recommended (Raspberry Pi guide)

—

Operating systemsDiffers

Windows documented (needs Rust and C++ build tools for pip); Docker Compose elsewhere; macOS and Linux not stated

Windows, macOS and Linux installers

—

Setup effortDiffers

Easy to medium; pip install plus skyvern quickstart, or docker compose up with an LLM key in .env

Installer and onboarding wizard; configure model access and channels

—

Stars over time

Switch to Growth % to compare projects of different sizes fairly.

Skyvern
Openclaw

Focus a point, use arrow keys, or tap for its value.

Tracked daily since 16 Oct 2026. Dashed history: estimated from public records of when people starred the repo. Lines connect observations only; gaps contain no measured points.

Growth % starts at each project's first observed point in the shown range. Zero-star starts are unavailable.

Notes for a video or post

A plain summary with today's date and a link to the sources. Check each project page before you publish.

Skyvern vs Openclaw (as alternatives to Manus)
Figures from RepoQuarry, 21 Oct 2026. Sources: https://repoquarry.dev/compare?ids=skyvern,openclaw&product=manus

Manus: See pricing page
Skyvern: free software; does 1 of 6 Manus jobs
Openclaw: free software; does 1 of 6 Manus jobs

- Skyvern: 23,239 GitHub stars, 716 commits in 12 weeks, licence AGPL-3.0 (copyleft); anti-bot features are cloud-only
- Openclaw: 392,686 GitHub stars, 42,127 commits in 12 weeks, licence MIT

Where they differ:
- Runs on my machine?: Skyvern Yes, local server and UI via pip or Docker Compose; also hosted Skyvern Cloud; Openclaw Yes, self-hosted gateway; hosted or local model providers
- Code licence: Skyvern AGPL-3.0 (copyleft); anti-bot features are cloud-only; Openclaw MIT
- Model weights licence: Skyvern No separate model weights; you bring a cloud API key or a local Ollama model; Openclaw No bundled weights; depends on the hosted or local model you connect
- Commercial use: Skyvern AGPL-3.0; offering a modified version as a network service requires sharing its source; Openclaw Yes, MIT code
- Paid services needed?: Skyvern Nothing paid with a local Ollama model; cloud LLM APIs and Skyvern Cloud (with anti-bot measures) are optional; Openclaw No OpenClaw paid tier; configured model/provider or hosting costs may apply
- Hardware: Skyvern About 4 GB RAM for 1-2 concurrent browser runs, 8 GB for 3-5, 16 GB for 6-10, 32 GB+ beyond; 2 GB minimum per Kubernetes pod; Openclaw Gateway with cloud models: minimum 1 GB RAM, 1 core, 500 MB free disk, 64-bit OS; 2 GB+ RAM recommended (Raspberry Pi guide)
- Operating systems: Skyvern Windows documented (needs Rust and C++ build tools for pip); Docker Compose elsewhere; macOS and Linux not stated; Openclaw Windows, macOS and Linux installers
- Setup effort: Skyvern Easy to medium; pip install plus skyvern quickstart, or docker compose up with an LLM key in .env; Openclaw Installer and onboarding wizard; configure model access and channels

Stars show popularity, not quality. Check each project page before publishing.

Want share images and a ready video description? Open a project's creator kit.

Numbers: GitHub, fetched nightly. Facts: read from each project's own documentation, with the source on its page. How we check. Skyvern-AI/skyvern ↗openclaw/openclaw ↗

Skyvern vs Openclaw

Stars over time

Notes for a video or post

Cookie preferences

Report a problem