Shotoku
Give your AI agents a budget. Spending limits, human approvals, and a tamper-evident audit trail — enforced locally before the payment happens. No cloud. No custody.
Shotoku at a Glance
- Pricing
- Free
- How you use it
- npm package, TypeScript function, MCP server, local dashboard, or terminal UI
- Who it's for
- Developers building AI agents
- Works with
- MCP Telegram PayPal
Shotoku Key Features
- Audit trail
- Human approval queue
- Policy enforcement
- Spending limits
Can't Find What You're Looking For?
We build custom AI agents tailored to your specific business needs. From ideation to deployment, TinyAI.Tools is your partner in AI innovation.
No commitment required. Let's discuss your ideas.
Shotoku Alternatives
caracal
The identity and authorization layer for AI agents. Agents never hold credentials: every action is policy-approved before it runs, delegation can only narrow, and a tamper-evident audit trail proves what happened.
Velatir
See how AI is being used, control what matters
Agent Ridge
Test the security of your e-commerce sites and web platforms. €500 AI security audit, visual evidence and PDF reports. Local Mac and Windows software.
Open Multi-Agent
Self-hosted TypeScript agent runtime with durable approvals and verifiable run records. Own it, approve it, audit it. - open-multi-agent/open-multi-agent
ARTEMIS
Contribute to Stanford-Trinity/ARTEMIS development by creating an account on GitHub.
AgentGuard
Real-time guardrail that shows token spend & kills runaway LLM/agent loops. - dipampaul17/AgentGuard