Loading...
Loading...
Oss
Two-person rule for AI agents: peer review before dangerous commands execute.
Adds safety friction for autonomous agents. Three-tier risk classification (CRITICAL/DANGEROUS/CAUTION), cryptographic command binding with SHA256+HMAC, dynamic quorum based on active agents, and complete audit trails. Integrates with Claude Code hooks and MCP Agent Mail for notifications.
# Install via Go
go install github.com/Dicklesworthstone/simultaneous_launch_button@latest# Request approval for a dangerous command
slb request --command "rm -rf /tmp/build" --risk DANGEROUS
# Approve a pending request (from another agent)
slb approve <request-id>
# List pending requests
slb listGmail for your coding agents. A coordination layer with messaging, file leases, and audit trails.
Multi-agent tmux orchestration. Spawn and coordinate Claude Code, Codex, and Gemini agents.
Meta-runner for language-specific bug scanners, tuned for AI coding agents.
Explore the source code, documentation, and contribute to the project.