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.
| Capability | The question it answers | Tools | Read from source | Dimensions |
|---|---|---|---|---|
| Read | Nine harnesses read files. What actually differs? | 13 | 9 | 30 |
| Browser | I want my agent to drive a browser. Which one? | 3 | 0 | — |
| Web search | Which harnesses can search the web without an add-on? | 9 | 0 | — |
| Code search | How does each harness find code it has not read yet? | 24 | 0 | — |
| Shell | Every harness runs shell commands. What differs underneath? | 24 | 0 | — |
| Long-term memory | Which agents remember anything between sessions? | 5 | 0 | — |