Paraphrased from each maker’s own description. Select a line for the quote.
Capabilities not yet checked for all
DeepSeek Harness
· also Frink and ZCode
DockTerm
· also Frink
Frink
· also ZCode
· also ZCode
· also DockTerm
· also DeepSeek Harness and ZCode
ZCode
· also Frink
· also Frink
· also DeepSeek Harness and Frink
Checked for DeepSeek Harness, DockTerm and Frink, not yet for ZCode: Price (DeepSeek Harness: ; DockTerm: ; Frink: )
Checked for DeepSeek Harness, Frink and ZCode, not yet for DockTerm: Model providers (DeepSeek Harness: ,,,, ; Frink: ,,, ; ZCode: ,,,,,,, )
Checked for DeepSeek Harness and Frink, not yet for DockTerm and ZCode: Bring your own key (DeepSeek Harness: ; Frink: )
Checked for ZCode, not yet for DeepSeek Harness, DockTerm and Frink: Agents it runs ()
Checked for DeepSeek Harness and ZCode, not yet for DockTerm and Frink: Editors and systems (DeepSeek Harness: , ; ZCode: ,, )
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
Plugin-based coding-agent harness with a local web interface
Terminal workspace with side-by-side sessions and prompts in the Mac notch
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