OpenClaw vs OpenHuman

Metrics checked · How we measure

OpenClaw: Personal assistant you can reach from a chat app. OpenHuman: Local-first personal assistant for desktop or headless use.

Stars added in 30 days

4,546 vs 1,150

OpenClaw added more stars

Open issues + pull requests

7,655 vs 324

OpenHuman has fewer open items

Stars

394,108 vs 42,584

OpenClaw has more stars

Choose OpenClaw if…

You want to reach the same personal assistant from a supported chat app while it runs on a computer you control.

OpenClaw profile Setup guide ↗

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 ↗

Side by side

MeasureOpenClawOpenHuman
Stars added in 30 daysCounts new stars still present at collection.OpenClaw added more stars4,5461,150
Open issues + pull requestsGitHub counts both kinds of open work together.OpenHuman has fewer open items7,655324
Health score /100Higher indicates more points under the Shelldex formula.7575
StarsMore stars indicate more bookmarks.OpenClaw has more stars394,10842,584
ForksCopies of a repository on GitHub.OpenClaw has more forks82,8174,214
Runs on or connects throughChoose a device or chat channel you use.server, messaging, clidesktop, server, cli
Model optionsCheck the provider, hardware and billing before setup.Local option: a supported local model provider. Hosted models may bill for usage.Local option: Ollama, LM Studio or MLX. Hosted models may bill for usage.
LanguageRelevant if you want to change the code.TypeScriptRust
MCP toolsMCP is a common way to connect an agent to tools.DocumentedDocumented
LicenseCheck the terms for your intended use.MITGPL-3.0
Latest repository pushDate GitHub last recorded a push (UTC).2026-11-072026-11-06
ReleaseLatest tagged release seen at collection.v2026.11.1v0.64.15

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

When did people add stars?

OpenClaw

Daily star additions

4,546 stars added across 30 days

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

OpenClaw daily GitHub stars, 2026-10-08 to 2026-11-06. 4,546 stars still present from 30 reported days. Peak: 185 in one day. 2026-10-08 · 131 stars 2026-10-09 · 145 stars 2026-10-10 · 151 stars 2026-10-11 · 159 stars 2026-10-12 · 172 stars 2026-10-13 · 185 stars 2026-10-14 · 166 stars 2026-10-15 · 160 stars 2026-10-16 · 140 stars 2026-10-17 · 140 stars 2026-10-18 · 177 stars 2026-10-19 · 136 stars 2026-10-20 · 184 stars 2026-10-21 · 159 stars 2026-10-22 · 160 stars 2026-10-23 · 142 stars 2026-10-24 · 133 stars 2026-10-25 · 164 stars 2026-10-26 · 156 stars 2026-10-27 · 163 stars 2026-10-28 · 139 stars 2026-10-29 · 149 stars 2026-10-30 · 130 stars 2026-10-31 · 135 stars 2026-11-01 · 151 stars 2026-11-02 · 172 stars 2026-11-03 · 145 stars 2026-11-04 · 133 stars 2026-11-05 · 137 stars 2026-11-06 · 132 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

Trying these agents

What model can I use?

OpenClaw: Local option: a supported local model provider. Hosted models may bill for usage. OpenHuman: Local option: Ollama, LM Studio or MLX. 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.