OpenHuman vs QwenPaw

Metrics checked · How we measure

OpenHuman: Local-first personal assistant for desktop or headless use. QwenPaw: A personal assistant for messaging and scheduled tasks.

Stars added in 30 days

1,150 vs 2,138

QwenPaw added more stars

Open issues + pull requests

324 vs 1,114

OpenHuman has fewer open items

Health score /100

75 vs 70

OpenHuman scores higher

What OpenHuman does

Give OpenHuman a task and it can search connected information, recall local context and act through browser or desktop tools. Its Rust agent runs with a desktop interface or on a server.

OpenHuman profile Setup guide ↗

What QwenPaw does

Formerly CoPaw, QwenPaw is an AgentScope-based assistant. It can run tasks on a schedule, use tools and respond across messaging channels. Its persona design credits OpenClaw.

QwenPaw profile Setup guide ↗

Side by side

MeasureOpenHumanQwenPaw
Stars added in 30 daysCounts new stars still present at collection.QwenPaw added more stars1,1502,138
Open issues + pull requestsGitHub counts both kinds of open work together.OpenHuman has fewer open items3241,114
Health score /100Higher indicates more points under the Shelldex formula.OpenHuman scores higher7570
StarsMore stars indicate more bookmarks.OpenHuman has more stars42,58437,452
ForksCopies of a repository on GitHub.OpenHuman has more forks4,2143,263
Runs on or connects throughChoose a device or chat channel you use.desktop, server, climessaging, server, desktop
Model optionsCheck the provider, hardware and billing before setup.Local option: Ollama, LM Studio or MLX. Hosted models may bill for usage.Local option: QwenPaw Local, Ollama or LM Studio. Hosted models may bill for usage.
LanguageRelevant if you want to change the code.RustPython
MCP toolsMCP is a common way to connect an agent to tools.DocumentedDocumented
LicenseCheck the terms for your intended use.GPL-3.0Apache-2.0
Latest repository pushDate GitHub last recorded a push (UTC).2026-11-062026-11-06
ReleaseLatest tagged release seen at collection.v0.64.15v2.2.2.post1

How Shelldex measures repository activity. A dash means no figure was available.

When did people add stars?

OpenHuman

Daily star additions

1,150 stars added across 30 days

Daily additions for stars still present · 2026-10-08 to 2026-11-06

OpenHuman daily GitHub stars, 2026-10-08 to 2026-11-06. 1,150 stars still present from 30 reported days. Peak: 115 in one day. 2026-10-08 · 78 stars 2026-10-09 · 72 stars 2026-10-10 · 50 stars 2026-10-11 · 56 stars 2026-10-12 · 72 stars 2026-10-13 · 45 stars 2026-10-14 · 45 stars 2026-10-15 · 115 stars 2026-10-16 · 29 stars 2026-10-17 · 21 stars 2026-10-18 · 27 stars 2026-10-19 · 26 stars 2026-10-20 · 39 stars 2026-10-21 · 19 stars 2026-10-22 · 27 stars 2026-10-23 · 43 stars 2026-10-24 · 49 stars 2026-10-25 · 31 stars 2026-10-26 · 27 stars 2026-10-27 · 22 stars 2026-10-28 · 32 stars 2026-10-29 · 19 stars 2026-10-30 · 19 stars 2026-10-31 · 24 stars 2026-11-01 · 42 stars 2026-11-02 · 22 stars 2026-11-03 · 27 stars 2026-11-04 · 30 stars 2026-11-05 · 25 stars 2026-11-06 · 17 stars

QwenPaw

Daily star additions

2,138 stars added across 30 days

Daily additions for stars still present · 2026-10-08 to 2026-11-06

QwenPaw daily GitHub stars, 2026-10-08 to 2026-11-06. 2,138 stars still present from 30 reported days. Peak: 224 in one day. 2026-10-08 · 33 stars 2026-10-09 · 38 stars 2026-10-10 · 34 stars 2026-10-11 · 43 stars 2026-10-12 · 28 stars 2026-10-13 · 34 stars 2026-10-14 · 51 stars 2026-10-15 · 35 stars 2026-10-16 · 41 stars 2026-10-17 · 47 stars 2026-10-18 · 29 stars 2026-10-19 · 27 stars 2026-10-20 · 37 stars 2026-10-21 · 38 stars 2026-10-22 · 59 stars 2026-10-23 · 60 stars 2026-10-24 · 69 stars 2026-10-25 · 173 stars 2026-10-26 · 224 stars 2026-10-27 · 205 stars 2026-10-28 · 119 stars 2026-10-29 · 168 stars 2026-10-30 · 93 stars 2026-10-31 · 59 stars 2026-11-01 · 100 stars 2026-11-02 · 89 stars 2026-11-03 · 74 stars 2026-11-04 · 54 stars 2026-11-05 · 47 stars 2026-11-06 · 30 stars

Trying these agents

What model can I use?

OpenHuman: Local option: Ollama, LM Studio or MLX. Hosted models may bill for usage. QwenPaw: Local option: QwenPaw Local, Ollama or LM Studio. Hosted models may bill for usage.

How can I try these on the same task?

Give both agents a copy of the same short, non-sensitive task. Check what they produced, what access they requested, and how often you had to step in.