Paraphrased from each maker’s own description. Select a line for the quote.
Capabilities not yet checked for all
Conductor
· also Frink and ZCode
· also Frink and ZCode
· also Frink
· also ZCode
Frink
· also Conductor and ZCode
· also Conductor and ZCode
· also Conductor
ZCode
· also Conductor and Frink
· also Conductor and Frink
· also Conductor
Checked for DeepSeek Harness and Frink, not yet for Conductor and ZCode: Price (DeepSeek Harness: ; Frink: )
Checked for DeepSeek Harness, Frink and ZCode, not yet for Conductor: Model providers (DeepSeek Harness: ,,,, ; Frink: ,,, ; ZCode: ,,,,,,, )
Checked for Conductor, DeepSeek Harness and Frink, not yet for ZCode: Bring your own key (Conductor: ; DeepSeek Harness: ; Frink: )
Checked for Conductor and ZCode, not yet for DeepSeek Harness and Frink: Agents it runs (Conductor: ,,, ; ZCode: )
Checked for Conductor, DeepSeek Harness and ZCode, not yet for Frink: Editors and systems (Conductor: ; DeepSeek Harness: , ; ZCode: ,, )
Same for all 4 (1): Agent & model switching
Agent & model switching · · ·
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
Coding-agent teams running in isolated cloud microVMs
Plugin-based coding-agent harness with a local web interface
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.
Multi-agent coding workspace presented as the harness for GLM-5.3