chat.nvim

chat.nvim is a lightweight, extensible chat plugin for Neovim with AI integration. Chat with AI assistants directly in your editor using a clean, floating window interface. It supports 20+ AI providers, a three-tier memory system, 45+ built-in tools, MCP protocol, IM integrations, and an HTTP API for external access. Full documentation is available at nvim.chat.

• ✨ Features
• 📦 Installation
• 🔧 Configuration
• ⚙️ Basic Usage
• 🧠 Memory System
• 🛠️ Tools
• 🔌 MCP Support
• 💬 IM Integration
• 🌐 HTTP API
• 📣 Self-Promotion
• 💬 Feedback
• 📄 License

✨ Features

• 🤖 20+ AI Providers - DeepSeek, OpenAI, Anthropic, GitHub Models, Gemini, Ollama, Baidu, Xiaomi, Alibaba Cloud, Moonshot, Tencent, and more
• 🧠 Three-Tier Memory - Working, daily, and long-term memory with automatic extraction and priority-based retrieval
• 🛠️ 45+ Built-in Tools - File operations, Git integration, web search and fetch, email, scheduling, user profiles
• 🧩 Slash Commands - Built-in skills (/model, /provider, /cwd, /pin, /title, /retry, ...) with custom skill registration
• 🔍 Lazy Tool Discovery - Only essential tools are sent with each request; other tools are activated on demand via a built-in catalog
• 🔄 Parallel Sessions - Multiple conversations with different models simultaneously
• 🔌 MCP Protocol - Native Model Context Protocol support via stdio and HTTP transports
• 💬 IM Integration - Discord, Telegram, Slack, Lark, DingTalk, WeCom, WeChat
• 🌐 HTTP API - Built-in server for external integration with API key authentication
• 👤 User Profiles - Per-user preferences and skills for personalized assistance
• ⏰ Scheduled Tasks - One-time or recurring tasks that persist across Neovim restarts
• ⚡ Streaming Responses - Real-time AI responses with cancellation and token tracking

📦 Installation

chat.nvim works with all major Neovim plugin managers.

• Using lazy.nvim

  {
    'wsdjeg/chat.nvim',
    dependencies = {
      'wsdjeg/job.nvim', -- Required
      'wsdjeg/picker.nvim', -- Optional but recommended
    },
  }
  

• Using nvim-plug

  require('plug').add({
    {
      'wsdjeg/chat.nvim',
      depends = {
        'wsdjeg/job.nvim',
        'wsdjeg/picker.nvim',
      },
    },
  })
  

• Using luarocks

  luarocks install chat.nvim
  

🔧 Configuration

The following is the default configuration of chat.nvim. See the Configuration Guide for full details.

require('chat').setup({
  -- window options
  width = 0.8,
  height = 0.8,
  auto_scroll = true,
  border = 'rounded',
  -- default AI provider and model
  provider = 'deepseek',
  model = 'deepseek-v4-flash',
  -- time display format
  strftime = '%m-%d %H:%M:%S',
  -- display names for the AI and user, used in the chat window
  -- and on role badges in the HTML preview
  names = {
    bot = 'Bot',
    user = 'You',
  },
  -- enable RenderMarkdown for result buffer
  render_markdown = true,
  -- default system prompt
  system_prompt = '',
  -- restrict file tool access to specific paths (string or list of strings)
  allowed_path = '',
  -- HTTP server for external integration
  http = {
    host = '127.0.0.1',
    port = 7777,
    api_key = '', -- set to non-empty to enable
  },
  -- API keys for providers
  api_key = {
    deepseek = 'your-deepseek-api-key',
    openai = 'your-openai-api-key',
    -- ...
  },
})

⚙️ Basic Usage

Open the chat window:

:Chat

Switch provider or model with slash commands (in the prompt window):

/provider openai
/model gpt-4o

Or use picker.nvim keybindings (in the input window):

Key Binding	Action
<Leader>fp	Switch provider via picker
<Leader>fm	Switch model via picker
<Leader>fr	Browse session history via picker

Navigate and manage sessions:

:Chat new      " create a new session
:Chat prev     " previous session
:Chat next     " next session
:Chat delete   " delete the current session
:Chat save f   " save the session to a file
:Chat load f   " load a session from a file or URL
:Chat share    " share the session to a pastebin
:Chat preview  " open the HTML preview in your browser

See the Usage Guide for all commands and keybindings.

🧠 Memory System

chat.nvim implements a three-tier memory system:

Type	Lifetime	Purpose
Working	Session	Current context, decisions, active tasks
Daily	7-30 days	Tasks, reminders, schedules
Long-term	Permanent	Preferences, facts, skills

Memories are automatically extracted during conversations and retrieved with priority-based ranking. See the Memory Guide for details.

🛠️ Tools

45+ built-in tools are available for AI assistants to interact with your environment:

• File Operations - Read, write, copy, move, and search files and directories
• Git Integration - Status, diff, log, commit, push, branch, rebase, stash, tag
• Web Search - Search the web via Firecrawl, Google, or SerpAPI
• Web Fetch - Fetch URLs and convert HTML to markdown
• Email - Send emails via the system mail command
• Mastodon - Read-only Mastodon: fetch toots, threads, and timelines
• Memory Management - Extract and recall memories
• Scheduled Tasks - One-time or recurring tasks, persisted across restarts
• User Profiles - Manage per-user preferences and skills
• Task Plans - Create and manage task plans
• Office Documents - View Excel files with multiple modes
• Development - Run make targets, check LSP diagnostics, get weather/time, convert images via ffmpeg

Tools are lazy-loaded by default: only the essential tools plus a find_tool discovery catalog are sent with each request to save prompt tokens, and other tools are activated on demand for the current turn. Set tools.lazy = false to send all tools with every request.

See the Tools Guide for the full list and usage.

🔌 MCP Support

Native Model Context Protocol support for extended tool capabilities:

require('chat').setup({
  mcp = {
    mcpServers = {
      -- stdio transport
      filesystem = {
        command = 'npx',
        args = { '-y', '@modelcontextprotocol/server-filesystem', '/path/to/dir' },
      },
      -- HTTP transport
      remote = {
        url = 'http://localhost:3000/mcp',
      },
    },
  },
})

See the MCP Guide for details.

💬 IM Integration

Connect messaging platforms for remote AI interaction:

• Discord - Chat with AI via Discord bot
• Telegram - Send messages and receive AI responses
• Slack - Slash command integration
• Lark - Feishu/Lark bot support
• DingTalk - DingTalk robot integration
• WeCom - WeChat Work integration
• WeChat - WeChat official account support

See the Integrations Guide for setup instructions.

🌐 HTTP API

The built-in HTTP server allows external applications to send messages to chat.nvim:

curl -X POST http://127.0.0.1:7777/ \
  -H "Content-Type: application/json" \
  -H "X-API-Key: your-secret-api-key" \
  -d '{"content":"Hello","session":"default"}'

See the API Guide for all endpoints.

📣 Self-Promotion

If you like this plugin, please star it on GitHub. Also check out my other Neovim plugins:

• nvim-plug - Asynchronous plugin manager
• picker.nvim - Fuzzy picker
• job.nvim - Async job execution
• flygrep.nvim - Asynchronous grep

💬 Feedback

If you encounter any bugs or have suggestions, please file an issue in the issue tracker

📄 License

Licensed under GPL-3.0.