avante.nvim is a Neovim plugin designed to emulate the behaviour of the Cursor AI IDE. It provides users with AI-driven code suggestions and the ability to apply these recommendations directly to their source files with minimal effort.

• AI-Powered Code Assistance: Interact with AI to ask questions about your current code file and receive intelligent suggestions for improvement or modification.
• One-Click Application: Quickly apply the AI's suggested changes to your source code with a single command, streamlining the editing process and saving time.

Install avante.nvim using lazy.nvim:

{
  "yetone/avante.nvim",
  event = "VeryLazy",
  build = "make", -- This is Optional, only if you want to use tiktoken_core to calculate tokens count
  opts = {
    -- add any opts here
  },
  dependencies = {
    "nvim-tree/nvim-web-devicons", -- or echasnovski/mini.icons
    "stevearc/dressing.nvim",
    "nvim-lua/plenary.nvim",
    "MunifTanjim/nui.nvim",
    --- The below is optional, make sure to setup it properly if you have lazy=true
    {
      'MeanderingProgrammer/render-markdown.nvim',
      opts = {
        file_types = { "markdown", "Avante" },
      },
      ft = { "markdown", "Avante" },
    },
  },
}

For Windows users, change the build command to the following:

{
  "yetone/avante.nvim",
  event = "VeryLazy",
  build = "powershell -ExecutionPolicy Bypass -File Build-LuaTiktoken.ps1", -- This is Optional, only if you want to use tiktoken_core to calculate tokens count
  -- rest of the config
}

{
  "MeanderingProgrammer/render-markdown.nvim",
  opts = {
    file_types = { "markdown", "Avante" },
  },
  ft = { "markdown", "Avante" },
}

Default setup configuration:

See config.lua#L9 for the full config

{
  ---@alias Provider "openai" | "claude" | "azure"  | "copilot" | [string]
  provider = "claude",
  claude = {
    endpoint = "https://api.anthropic.com",
    model = "claude-3-5-sonnet-20240620",
    temperature = 0,
    max_tokens = 4096,
  },
  mappings = {
    ask = "<leader>aa",
    edit = "<leader>ae",
    refresh = "<leader>ar",
    --- @class AvanteConflictMappings
    diff = {
      ours = "co",
      theirs = "ct",
      none = "c0",
      both = "cb",
      next = "]x",
      prev = "[x",
    },
    jump = {
      next = "]]",
      prev = "[[",
    },
    submit = {
      normal = "<CR>",
      insert = "<C-s>",
    },
    toggle = {
      debug = "<leader>ad",
      hint = "<leader>ah",
    },
  },
  hints = { enabled = true },
  windows = {
    wrap = true, -- similar to vim.o.wrap
    width = 30, -- default % based on available width
    sidebar_header = {
      align = "center", -- left, center, right for title
      rounded = true,
    },
  },
  highlights = {
    ---@type AvanteConflictHighlights
    diff = {
      current = "DiffText",
      incoming = "DiffAdd",
    },
  },
  --- @class AvanteConflictUserConfig
  diff = {
    debug = false,
    autojump = true,
    ---@type string | fun(): any
    list_opener = "copen",
  },
}

Given its early stage, avante.nvim currently supports the following basic functionalities:

export ANTHROPIC_API_KEY=your-api-key

export OPENAI_API_KEY=your-api-key

export AZURE_OPENAI_API_KEY=your-api-key

1. Open a code file in Neovim.
2. Use the :AvanteAsk command to query the AI about the code.
3. Review the AI's suggestions.
4. Apply the recommended changes directly to your code with a simple command or key binding.

Note: The plugin is still under active development, and both its functionality and interface are subject to significant changes. Expect some rough edges and instability as the project evolves.

The following key bindings are available for use with avante.nvim:

• Leaderaa — show sidebar
• Leaderar — show sidebar
• co — choose ours
• ct — choose theirs
• cb — choose both
• c0 — choose none
• ]x — move to previous conflict
• [x — move to next conflict

• Chat with current file
• Apply diff patch
• Chat with the selected block
• Slash commands
• Edit the selected block
• Smart Tab (Cursor Flow)
• Chat with project
• Chat with selected files

• Enhanced AI Interactions: Improve the depth of AI analysis and recommendations for more complex coding scenarios.
• LSP + Tree-sitter + LLM Integration: Integrate with LSP and Tree-sitter and LLM to provide more accurate and powerful code suggestions and analysis.

Contributions to avante.nvim are welcome! If you're interested in helping out, please feel free to submit pull requests or open issues. Before contributing, ensure that your code has been thoroughly tested.

See wiki for more recipes and tricks.

avante.nvim is licensed under the Apache License. For more details, please refer to the LICENSE file.