ACP: one REST interface for agents built on different frameworks
- Source
- x.com
- Date
New Course: ACP: Agent Communication Protocol Learn to build agents that communicate and collaborate across different frameworks using ACP in this short course built with @IBMResearch's BeeAI, and taught by @sandi_besen, AI Research Engineer & Ecosystem Lead at IBM, and @nicholasrenotte, Head of AI Developer Advocacy at IBM. Building a multi-agent system with agents built or used by different teams and organizations can become challenging. You may need to write custom integrations each time a team updates their agent design or changes their choice of agentic orchestration framework. The Agent Communication Protocol (ACP) is an open protocol that addresses this challenge by standardizing how agents communicate, using a unified RESTful interface that works across frameworks. In this protocol, you host an agent inside an ACP server, which handles requests from an ACP client and passes them to the appropriate agent. Using a standardized client-server interface allows multiple teams to reuse agents across projects. It also makes it easier to switch between frameworks, replace an agent with a new version, or update a multi-agent system without refactoring the entire system. In this…
Context
The June 2025 ACP course announcement addresses a coordination problem: teams may build agents with different software frameworks but still need those agents to exchange requests. ACP placed an behind a server with a standardized web interface; a client sent requests through that interface. This was intended to make agents reusable without exposing every internal implementation choice.
The course also combined agent communication with MCP-based tool access. The protocol history matters: a subsequent publisher update says the ACP team joined the A2A effort beginning September 1, 2025, and that the course would be replaced with A2A material.
- AI agent — An AI system that doesn't just answer once but works toward a goal in a loop — taking actions, reading the results, and deciding what to do next.
- MCP — The Model Context Protocol — an open standard that lets any AI assistant plug into any tool or data source without custom integration code.
- multi-agent — Using several AI agents on one problem — splitting work in parallel, checking each other, or filling different roles like planner and reviewer.
Checking sign-in…
Loading comments…