ucsandman/DashClaw

Overview

DashClaw provides remote approvals, policy checks, and execution evidence for unattended AI agents. It is written in TypeScript and targets developers building autonomous agent workflows.

Best for

Best for
Developers building AI agents that need human-in-the-loop oversight.

Use cases

• Gate AI agent actions with remote human approval
• Enforce policy checks before agent execution
• Collect execution evidence for auditing agent runs

How to use

Install

npx dashclaw up      # no account, first caught action in minutes

Tools exposed

• lost_confirmation

Tested with

Claude Desktop, Claude Code

Notes

DashClaw provides remote approvals, policy checks, and execution evidence for unattended AI agents. It is written in TypeScript and targets developers building autonomous agent workflows.

305 stars on GitHub. Last updated 2026-09-15. Licensed MIT.

Use cases

• Gate AI agent actions with remote human approval
• Enforce policy checks before agent execution
• Collect execution evidence for auditing agent runs

Pros

• Covers approval, policy, and audit needs in one tool
• TypeScript codebase fits JS/TS developer ecosystems
• Open source with 305 GitHub stars

Cons

• Requires self-hosting and integration effort
• Community-maintained, no commercial support
• Focused narrowly on unattended agent scenarios

Indexed from awesome-mcp-servers-punkpeye and enriched against its public facts.