CodeCompanion.nvim
Neovim interface to models and coding agents, with ACP and code-change review · Source
Up to four tools, row by row. We do not guess: a cell we have not verified says so.
Dirac is a fork of Cline: Dirac is a fork of Cline.
raw.githubusercontent.com
Zoo Code is a fork of Roo Code: Zoo Code is a community fork of Roo Code.
zoocode.dev
Paraphrased from each maker’s own description. Select a line for the quote.
Sourced for Dirac, Kilo Code and Zoo Code, not yet for CodeCompanion.nvim: Price (Dirac: ; Kilo Code: · ; Zoo Code: · ), Model providers (Dirac: ; Kilo Code: , , ; Zoo Code: , , , , , , , ), Bring your own key (Dirac: ; Kilo Code: ; Zoo Code: )
Sourced for Kilo Code, not yet for CodeCompanion.nvim, Dirac and Zoo Code: Editors and systems ()
None of these tools has a sourced value yet for: agents it runs.
Dotted values open their quote. A capability not shown is not yet sourced; the tool may still have it.
Neovim interface to models and coding agents, with ACP and code-change review · Source
Coding agent for VS Code, the terminal and ACP-compatible clients · Source
Dirac is an open-source coding agent you can use in VS Code, from the terminal, or through any compatible Agent Client Protocol (ACP) client. It supports dozens of providers and hundreds of models, so you can bring the models and credentials that fit your workflow instead of being locked into one stack.
Coding-agent extensions for VS Code and JetBrains · Source
Use the same open-source agent in VS Code, JetBrains, CLI, and cloud agents.
Editor extension with coding-agent teams and destructive-command protection · Source
Votes can only raise a score: up to 20% of it reflects upvotes, 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. After activation, 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



Watch CodeCompanion.nvim vs Dirac vs Kilo Code vs Zoo Code on YouTube


























