Skip to content
| Marketplace
Sign in
Visual Studio Code>Programming Languages>ConoNew to Visual Studio Code? Get it now.
Cono

Cono

Arcanic AI

|
8 installs
| (0) | Free
Autonomous coding agent right in your IDE, capable of creating/editing files, running commands, using the browser, and more with your permission every step of the way.
Installation
Launch VS Code Quick Open (Ctrl+P), paste the following command, and press enter.
Copied to clipboard
More Info

Cono

Cono is an AI coding agent for VS Code that works directly in your editor and terminal to help you build, fix, and ship software faster.

Features

Agentic Task Execution

Describe what you want to build or fix. Cono analyzes your codebase, plans the steps, and executes them — creating files, running commands, and iterating until the task is done. Every file change and terminal command requires your approval.

Edit & Create Files

Cono makes changes directly in your editor with a diff view so you can review, edit, or revert each modification. All changes are recorded in the file Timeline for easy rollback.

Terminal Integration

Cono runs commands in your terminal and reads the output — installing packages, running build scripts, executing tests, and reacting to errors in real time.

Browser Automation

Cono can launch a headless browser, click elements, type, scroll, and capture screenshots. Useful for end-to-end testing, debugging visual bugs, and verifying UI changes without copy-pasting error logs.

MCP Tool Extensions

Via the Model Context Protocol, Cono can create and install custom tools tailored to your workflow — Jira integrations, AWS management, incident tracking, and more.

Context Mentions

  • @file — attach a file's contents directly to the conversation
  • @folder — attach all files in a folder at once
  • @url — fetch a URL and include it as markdown
  • @problems — attach workspace errors from the Problems panel

Checkpoints

Cono snapshots your workspace at each step. Use Compare to diff against the current state, or Restore to roll back to any point in the task.

Multi-Model Support

Works with Anthropic, OpenAI, Google Gemini, AWS Bedrock, Azure, OpenRouter, Groq, Cerebras, LM Studio, Ollama, and any OpenAI-compatible API. Token usage and cost are tracked per request and per task.

License

Apache 2.0

  • Contact us
  • Jobs
  • Privacy
  • Manage cookies
  • Terms of use
  • Trademarks
© 2026 Microsoft