Agent · xAI · cli

Grok Build

github.com/xai-org/grok-build

21
tools registered
5/6
compared capabilities
it has a tool for

Grok Build registers 21 tools, covering 5 of 6 compared capabilities. It registers no built-in tool for browser.

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
Readread_file13 of 13 have one →
Browserno built-in tool3 of 13 have one →
Web searchweb_search9 of 13 have one →
Code searchgrep · list_dirpartial13 of 13 have one →
Shellbash · monitorpartial13 of 13 have one →
Long-term memorymemory_get · memory_search4 of 13 have one →

All 21 tools

names verbatim, as registered

Not yet compared means registered by Grok Build 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.