import { CodeAgent } from '@devclaw/core'; const system = new CodeAgent({ mode: "autonomous" }); // analyzing workspace architecture...
import { CodeAgent } from '@devclaw/core'; const system = new CodeAgent({ mode: "autonomous" }); // analyzing workspace architecture...
## DevClaw Terminal Instance ## DevClaw v2026.4.1 initialized. git add . && git commit -m "AI applied architecture refactor"
## DevClaw Terminal Instance ## DevClaw v2026.4.1 initialized. git add . && git commit -m "AI applied architecture refactor"
function blockCopilot() { return true; } // Loading local Generative Model... try { await executeWorkflow("T3 Stack Migration"); } catch(e) { autoFix(e); }
function blockCopilot() { return true; } // Loading local Generative Model... try { await executeWorkflow("T3 Stack Migration"); } catch(e) { autoFix(e); }
{ "quality": "stable", "nameShort": "DevClaw", "dataFolder": ".devclaw" } // Your data, your control.
{ "quality": "stable", "nameShort": "DevClaw", "dataFolder": ".devclaw" } // Your data, your control.
DevClawDevClaw
Back to Docs

Installation

System Requirements

  • macOS 12 Monterey or later (Apple Silicon recommended; Intel works)
  • 4 GB RAM minimum (8 GB recommended)
  • 500 MB free disk space
  • An AI provider key (OpenAI, Anthropic, etc.) OR a local model server

Download

Grab the latest macOS build from GitHub Releases.

Direct link: DevClaw-latest.dmg

Install

  1. Open the downloaded .dmg file
  2. Drag DevClaw to your Applications folder
  3. Eject the disk image
  4. Launch DevClaw from Applications (or Spotlight)

First launch

On first launch DevClaw will:

  • Create ~/.devclaw/ (config directory)
  • Detect any existing VSCode settings and offer to import them
  • Prompt you to configure your AI provider

Configuring an AI provider

Open Settings → AI Provider and choose one:

  • OpenAI — paste your sk-... API key
  • Anthropic — paste your Claude API key
  • OpenAI-compatible — point at any local or remote endpoint (Ollama, LM Studio, vLLM, etc.)
  • Local model — DevClaw will auto-detect common local servers

Keys are stored in macOS Keychain, not in plain text.

Troubleshooting

"DevClaw can't be opened because it is from an unidentified developer"

Right-click the app in Finder, choose Open, then confirm. macOS will remember your choice for future launches.

Agent windows don't appear

Check Settings → Extensions → make sure the DevClaw Agent extension is enabled. Restart the IDE after toggling.

Build errors with local models

Make sure your local server exposes an OpenAI-compatible endpoint (/v1/chat/completions). Ollama works out of the box.

Uninstall

rm -rf /Applications/DevClaw.app
rm -rf ~/.devclaw

Project files stay where they are.