Agent · openclaw · cli

OpenClaw

github.com/openclaw/openclaw

23
tools registered
5/6
compared capabilities
it has a tool for

OpenClaw registers 23 tools, covering 5 of 6 compared capabilities. It reaches code search indirectly, through a tool built for something else. It registers no built-in tool for long-term memory.

How this list was established. Tool list taken from published docs rather than source.

Surface size

tools registered, across the 13 harnesses here

Surface size, not quality. Every registered tool spends context on every request, so a longer bar is a cost as much as a capability — and a harness that reaches a capability through a general tool may register fewer.

Capabilities

what serves each, and where it is compared
CapabilityToolsAcross harnesses
Readread13 of 13 have one →
Browserbrowser3 of 13 have one →
Web searchweb_search9 of 13 have one →
Code searchexecpartial
Serves "Glob / file patterns" indirectly.
13 of 13 have one →
Shellexec · processpartial · terminalpartial13 of 13 have one →
Long-term memoryno built-in tool4 of 13 have one →

All 23 tools

names verbatim, as registered

Not yet compared means registered by OpenClaw but with no comparison page here — todo lists, subagent spawning, approval flows. They become capabilities the day there is a comparison worth reading, and the data does not have to change for that to happen.