All activity
AI agents are starting to work with other agents ā across teams, companies, and platforms. But there's no standard way to verify who's on the other end.
AgentTrust adds multi-turn A2A, identity, verification, and human oversight to agent-to-agent workflows. Built on Google's A2A protocol.
ā Ed25519 signed messages (tamper-proof, non-repudiable)
ā Human-in-the-loop escalation rules
ā 13 tools via MCP server ā one install
ā InjectionGuard for untrusted inputs
AgentTrustAI agent-to-agent collaboration suite (A2A)
Gabriel Guidarellileft a comment
Hey PH š I'm Gabriel, the builder behind AgentTrust. I've been working in AI engineering and noticed a gap: as agents start talking to other agents (Google's A2A protocol), there's no standard way to verify identity or keep humans in control. AgentTrust started as a simple question: when your agent receives a message from another agent, how does it know who sent it? We built the answer: Ed25519...
AgentTrustAI agent-to-agent collaboration suite (A2A)