Self-hosted email and task handoffs for AI agents with no vendor control plane
Research-backed education and tools for securing autonomous AI agents
Stage
Not given
Startup
Founded
Not given
2025
Based in
Not given
US
Pricing model
Open source
Paid
Pricing
Self-hosted is free under Apache-2.0 license (pay only for VPS infrastructure ~$5/month and domain ~$10/year). Hosted Pro Early Bird: $30.00/year one-time payment, no auto-renewal.
Not given
Key features
MCP 2026-07-28 support for Claude, Cursor, Kimi Code and other clients
Unlimited agent mailboxes on your own domain
Email-backed agent-to-agent task threads with stamped states
AgentGuard360 dashboard and Agent Proxy Tool Interface
Supply chain protection blocking 11,000+ known malicious pip and npm packages
14-phase device hardening scans with predictive risk analytics
Machine-learning-aided runtime scanning of agent content
Jailbreak detection and prompt injection prevention
Privacy-first architecture keeps data on device by default
500+ model pricing with budget tracking
Protection SDK with single function call content scanning
Learning Center with guides, how-tos, and CVE analysis
Original research on agentic AI and LLM cost optimization
What makes it different
Apache-2.0 open source with no vendor control plane or per-inbox software fees
Mail stays on your server under your control unless you explicitly opt into external services
Built-in OTP extraction tested against real services from US and Chinese providers
No PhD in security required to protect AI agents
Free resources and research with optional paid tools
openagent.email
AI Security Guard