In this post, I’m excited to announce a **new version of CleverChatty** that introduces **server mode** — unlocking powerful new capabilities for building AI assistants and agents that can interact over the network.
Previously, CleverChatty functioned only as a **command-line interface (CLI)** for interacting with LLM-based assistants. A typical use case involved a single user chatting with an AI model via the terminal. With this latest update, CleverChatty can now **run as a server**, enabling:
* Concurrent communication with multiple clients
* Background operation on local or cloud environments
* Integration into distributed agent systems
But that’s not all. The biggest leap forward? **Full support for A2A (Agent-to-Agent) protocol**.
[CleverChatty](https://github.com/Gelembjuk/cleverchatty/)
---
## 🌐 A2A Communication: A Two-Way Upgrade
The new A2A support brings two major enhancements:
1. **CleverChatty as an A2A Server**
It can now act as an A2A endpoint, accepting requests from other agents or clients — such as a CleverChatty-powered CLI tool.
2. **CleverChatty as an A2A Client**
It can also **send A2A requests** to other agents. This is implemented similarly to how it uses MCP tools — meaning you can now combine both **MCP and A2A tools** in your AI workflows.
This enables CleverChatty to be a **hub of intelligent interactions** between multiple AI services, memory providers, and knowledge sources.
---
## ✨ Key Features
* **LLM Prompt Handling**: Communicate with supported large language models via prompts and receive responses.
* **MCP Server Support**:
* Seamlessly integrates MCP (Model Context Protocol) servers: `STDIO`, `HTTP`, and `SSE`.
* **A2A Protocol Support**:
* Acts as both **A2A server and client**
* A2A servers can be used like tools, just like MCP tools
* **AI Memory Integration**:
* Compatible with memory systems such as **Mem0**, or any service that speaks MCP or A2A.
* **RAG (Retrieval-Augmented Generation)**:
* Bring in external data sources or knowledge bases to enrich AI responses dynamically.
---
## 🖥️ CleverChatty Server
The **CleverChatty server** is a long-running background service that handles requests via the A2A protocol. It manages your AI models, tools, and memory systems from a centralized interface.
To start the server:
```bash
cleverchatty-server start --directory "../agent-filesystem"
```
The `--directory` option specifies the working directory for logs, config files, and STDIO-based MCP tools.
To stop the server:
```bash
cleverchatty-server stop --directory "../agent-filesystem"
```
This makes it easy to manage your server setup both locally and on cloud instances.
---
## 🧪 CleverChatty CLI (Standalone Mode)
You can still run **CleverChatty CLI** as a **standalone app** — ideal for prototyping, quick tests, or single-session experiments. It includes all the same features as the server but operates in a self-contained process.
Learn how to configure and run the CLI in the [CleverChatty CLI README](https://github.com/Gelembjuk/cleverchatty/blob/main/docs/Cli.md)
---
Stay tuned for more updates — and start building your own multi-agent AI assistant infrastructure today with **CleverChatty Server Mode + A2A support**! 🚀
