Paraphrased from each maker’s own description. Select a line for the quote.
Capabilities not yet checked for all
cmux
· also Happier
· also Happier and ZCode
Frink
· also Happier and ZCode
· also Happier
· also Happier and ZCode
Happier
· also Frink and ZCode
· also cmux
· also Frink
· also cmux and ZCode
· also Frink and ZCode
ZCode
· also Frink and Happier
· also cmux and Happier
· also Frink and Happier
Checked for cmux, Frink and Happier, not yet for ZCode: Price (cmux: ; Frink: ; Happier: )
Checked for Frink, Happier and ZCode, not yet for cmux: Model providers (Frink: ,,, ; Happier: , ; ZCode: ,,,,,,, )
Checked for cmux and Frink, not yet for Happier and ZCode: Bring your own key (cmux: ; Frink: )
Checked for cmux, Happier and ZCode, not yet for Frink: Agents it runs (cmux: ,,,,, ; Happier: ,, ; ZCode: ), Editors and systems (cmux: ,, ; Happier: , ; ZCode: ,, )
Same for all 4 (1): Parallel agents
Parallel agents · · ·
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
Native macOS terminal with agent notifications, split panes and a CLI
Desktop-first, open-source (MIT) application for running parallel agents, and multi-step custom workflows triggered by schedules, webhooks or events from tools like Linear and Sentry, across your already-used providers.
Desktop, web and mobile clients for coding agents with encrypted sessions
Multi-agent coding workspace presented as the harness for GLM-5.3