ClarAIty brings a fully transparent AI coding agent directly into VS Code. Watch every tool call, trace every decision, and stay in control at every step.
ClarAIty is built on the principle that you should always know exactly what your AI agent is doing and why.
Every file read, every grep, every command -- displayed in real time as a live trace. No black box decisions.
Delegate focused tasks to specialized subagents -- code reviewer, test writer, doc writer -- each with their own isolated context.
Destructive or sensitive operations pause for your approval. Auto-approve categories you trust, review the rest.
Every conversation is persisted. Resume any past session, replay tool traces, and pick up exactly where you left off.
Made a mistake? Undo the last agent turn -- file changes are snapshotted before every edit, so recovery is instant.
Connect any Model Context Protocol server to extend the agent with custom tools, APIs, and data sources.
Build a persistent knowledge graph of your codebase. Architecture, decisions, and invariants survive across sessions.
Built-in beads task system. Create, prioritize, and track work items without leaving the agent chat.
Works with OpenAI, Anthropic, and any OpenAI-compatible endpoint. Configure model per session or per subagent.
No complex setup. Install the extension, add your API key, and start coding with AI that you can actually watch think.
One click from the VS Code Marketplace. The agent backend installs automatically via pip.
Paste your OpenAI or Anthropic key into settings. Keys are stored securely in VS Code SecretStorage -- never in files.
Click the ClarAIty icon in the activity bar. Type your first request and watch the agent get to work.
Review diffs before they land, approve sensitive operations, undo anything, and trace every decision.
Free to install. Works with your existing API keys.