What AI models does the agent use?

The agent has access to Claude, DeepSeek, Gemini, and other top models. It automatically routes to the best model for each task — you never have to think about API keys or token limits.

Yes. Each agent runs in an isolated environment. We don't train on your data, and you can export or delete everything at any time. The underlying engine (GoGogot) is open-source, so you can audit exactly how it works.

What can the agent actually do?

Browse the web, process files (CSV, PDF, images), run scheduled tasks, remember context across sessions, and communicate via Telegram or Slack. Think of it as a capable junior employee, not a chatbot.

How does memory work?

The agent maintains persistent memory across sessions. It remembers your preferences, past conversations, and task context. You can also explicitly tell it to remember or forget things.

Can I self-host the agent?

Absolutely. GoGogot is 100% open-source. Run it on your own hardware for free. cowork.ink is the managed version — we handle servers, model costs, updates, and uptime so you don't have to.

Is there a free trial?

We offer a 7-day money-back guarantee. Spin up an agent, give it real tasks, and if it doesn't save you time, we'll refund you — no questions asked.

What is the AI agent protocol stack?

The AI agent protocol stack is a layered set of open standards that let autonomous agents connect to tools (MCP), delegate tasks to other agents (A2A), and discover each other across the open internet (ANP). Together they are the infrastructure layer for multi-agent systems — what TCP/IP is to the web.

What is the difference between MCP and A2A?

MCP connects a single agent to external tools and data sources — think of it as the agent's USB port. A2A connects one agent to another, enabling task delegation and multi-agent collaboration across vendor boundaries. They are complementary, not competing. See our full [MCP vs A2A comparison](/blog/mcp-vs-a2a/) for details.

Did ACP merge into A2A?

Yes. In August 2025, IBM's Agent Communication Protocol (ACP) formally merged into A2A under the Linux Foundation's Agentic AI Foundation (AAIF). IBM's ACP team joined the A2A Technical Steering Committee and the BeeAI platform migrated from ACP to A2A.

Who governs MCP and A2A today?

Both are governed by the Agentic AI Foundation (AAIF), a Linux Foundation project launched in December 2025. Co-founders include Anthropic, OpenAI, Google, Microsoft, AWS, and Block — making both protocols truly vendor-neutral.

Which AI agent protocol should I use?

Use MCP whenever an agent needs to access tools, APIs, or data. Use A2A whenever agents need to delegate tasks or collaborate with other agents. In most production systems you will use both. ANP is best suited for experimental open-internet agent discovery scenarios.

AI Agent Protocol Stack: MCP, A2A, ACP & ANP Explained

COMPLETE guide to the AI agent protocol stack. Learn how MCP, A2A, ACP, and ANP work together to power autonomous agent ecosystems. Read now.

Frequently Asked Questions

What is the AI agent protocol stack?: The AI agent protocol stack is a layered set of open standards that let autonomous agents connect to tools (MCP), delegate tasks to other agents (A2A), and discover each other across the open internet (ANP). Together they are the infrastructure layer for multi-agent systems — what TCP/IP is to the web.
What is the difference between MCP and A2A?: MCP connects a single agent to external tools and data sources — think of it as the agent's USB port. A2A connects one agent to another, enabling task delegation and multi-agent collaboration across vendor boundaries. They are complementary, not competing. See our full [MCP vs A2A comparison](/blog/mcp-vs-a2a/) for details.
Did ACP merge into A2A?: Yes. In August 2025, IBM's Agent Communication Protocol (ACP) formally merged into A2A under the Linux Foundation's Agentic AI Foundation (AAIF). IBM's ACP team joined the A2A Technical Steering Committee and the BeeAI platform migrated from ACP to A2A.
Who governs MCP and A2A today?: Both are governed by the Agentic AI Foundation (AAIF), a Linux Foundation project launched in December 2025. Co-founders include Anthropic, OpenAI, Google, Microsoft, AWS, and Block — making both protocols truly vendor-neutral.
Which AI agent protocol should I use?: Use MCP whenever an agent needs to access tools, APIs, or data. Use A2A whenever agents need to delegate tasks or collaborate with other agents. In most production systems you will use both. ANP is best suited for experimental open-internet agent discovery scenarios.