Agent Action Protocol (AAP)
MCP got us started, but is insufficient. AAP: Agent Action Protocol — a portable, composable spec for AI agents taking action in the world. Background: I've been working on agentic guardrails because agents act in expensive/terrible ways and something needs to be able to say "Maybe don't do that" to the agents, but guardrails are almost impossible to enforce with the current way things are built.
Open source
Reactions (1)
Similar products
by description similarity
Fast-agent
github.comCompose MCP enabled Agents and Workflows in minutes
Conduct
github.comopen-source guardrails for LLM and MCP tool calls
AgentTrust
github.comZero-trust security and human approvals for AI agents
Nanobot
nanobot.aiTurn MCP servers into full AI agents
AgentArmor
github.comopen-source 8-layer security framework for AI agents