Capabilities

Six comparisons, one per thing worth comparing

A capability here is the unit of a comparison page, not a slot in a taxonomy. The test for adding one is whether you can write the question its page answers. The tool matrix records plenty of finer-grained functions — todo lists, subagent spawning, approval flows — and those stay ordinary tools until there is a comparison worth reading.

CapabilityThe question it answersToolsRead from sourceDimensions
ReadNine harnesses read files. What actually differs?13930
BrowserI want my agent to drive a browser. Which one?30
Web searchWhich harnesses can search the web without an add-on?90
Code searchHow does each harness find code it has not read yet?240
ShellEvery harness runs shell commands. What differs underneath?240
Long-term memoryWhich agents remember anything between sessions?50