Paraphrased from each maker’s own description. Select a line for the quote.
Capabilities not yet checked for all
cmux
· also swe-mux
Conductor
· also ZCode
· also swe-mux
· also ZCode
swe-mux
· also cmux
· also Conductor
ZCode
· also Conductor
· also Conductor
Checked for cmux and swe-mux, not yet for Conductor and ZCode: Price (cmux: ; swe-mux: )
Checked for swe-mux and ZCode, not yet for cmux and Conductor: Model providers (swe-mux: ,,,, ; ZCode: ,,,,,,, )
Checked for cmux and Conductor, not yet for swe-mux and ZCode: Bring your own key (cmux: ; Conductor: )
Checked for cmux, Conductor and ZCode, not yet for swe-mux: Agents it runs (cmux: ,,,,, ; Conductor: ,,, ; ZCode: )
Same for all 4 (2): Parallel agents · Remote session control
Parallel agents · · ·
Remote session control · · ·
Provider names use the same listing as each tool page. Dotted values open their quote. A capability not shown is not yet checked; the tool may still have it.
Already use any of these? Tick it. Several is fine.
Votes can only raise a score: up to 20% of it reflects votes, graded on a curve against the most-voted tool. The square-root curve has a floor of 100 effective votes. Votes decay with a 90-day half-life. Maker self-votes do not count. Counts below 10 are hidden for display only. A vote is a signed-in reader ticking “I use this”. Since votes joined the score on 18 Nov 2026, the score is 80% mindshare plus 20% of the greater of mindshare and the vote score. GitHub stars do not affect the Index score. Mindshare uses a log scale; votes use the square-root curve and a 100-vote floor. Ranks use unrounded scores. Mindshare and adoption bars are log-scaled; the others are linear within this comparison. How the score is built