Shotoku
AI Agents · Agent Workflow Free & Open Source

Shotoku

Local-first action governance and budget caps framework protecting AI agents from runaways.

User Satisfaction 100%
27 Community Reviews

Free Tier & Quota Rules

Core codebase is fully open source with unlimited local governance and budget caps.

Overview & Core Features

Shotoku is a lightweight, local-first runtime governance and budget ceiling framework designed for autonomous AI agents. As engineering teams empower agents with shell access, local file system mutations, and third-party API integration, the risks of infinite reasoning loops, catastrophic file deletion, and unexpected billing spikes grow exponentially. Shotoku sits transparently between agent planners and tool invocation layers, enforcing strict command sandboxing, path whitelists, and real-time financial expenditure caps. When an agent exhibits hazardous patterns or exceeds predefined thresholds, Shotoku halts execution instantly, keeping autonomous workflows safe and predictable.

Interface Preview & Architecture

🔒 https://www.shotoku.dev
Shotoku interface screenshot

Pros & Limitations

Strengths

  • ✓ Local-first design with zero external cloud dependencies for private policies
  • ✓ Strict budget cap enforcement to prevent catastrophic runaway billing spikes
  • ✓ Declarative configuration for fast sandboxing of shell commands and filesystem I/O

Considerations

  • ✕ Requires custom interceptors for highly intricate multi-agent distributed topologies

Ready to try Shotoku?

Explore features directly on their official platform.

Open Shotoku ↗

Similar Alternatives

💬 Discussion

GitHub Powered