Add blog post: How to Run a BeeAI Framework Agent as an A2A Server (#1513)

edengilbert · kapetr · PetrBulanek · web-flow · commit 329e278c27dd · 2025-11-21T09:36:45.000-06:00
* Add blog post: How to Run a BeeAI Framework Agent as an A2A Server Signed-off-by: Eden Gilbert <eden.gilbert@ibm.com> * Finalize A2A Server blog post after preview edits Signed-off-by: Eden Gilbert <eden.gilbert@ibm.com> * Update a2a-server.mdx Updated based on gemini feedback Signed-off-by: Eden Gilbert <117227212+edengilbert@users.noreply.github.com> Signed-off-by: Eden Gilbert <eden.gilbert@ibm.com> * feat(ui): group trajectories (#1482) Signed-off-by: Petr Kadlec <petr@puradesign.cz> Signed-off-by: Eden Gilbert <eden.gilbert@ibm.com> * fix(ui): proactive access_token refresh to avoid refresh race (#1501) Signed-off-by: Petr Kadlec <petr@puradesign.cz> Signed-off-by: Eden Gilbert <eden.gilbert@ibm.com> * fix(ui): runtime envs and feature flags cleanup (#1479) Signed-off-by: Eden Gilbert <eden.gilbert@ibm.com> * feat(ui): render mermaid diagrams and latex syntax in markdown (#1488) Signed-off-by: Eden Gilbert <eden.gilbert@ibm.com> * feat(sdk): utilize platform auth in mcp extension (#1508) Signed-off-by: Tomas Pilar <thomas7pilar@gmail.com> Signed-off-by: Eden Gilbert <eden.gilbert@ibm.com> * feat(server): add user info endpoint (#1505) Signed-off-by: Radek Ježek <radek.jezek@ibm.com> Signed-off-by: Eden Gilbert <eden.gilbert@ibm.com> * docs: remove redundant ToC from connectors guide (#1519) Signed-off-by: Jenna Winkler <135358348+jenna-winkler@users.noreply.github.com> Signed-off-by: Eden Gilbert <eden.gilbert@ibm.com> * fix(ui): array length checks (#1526) Signed-off-by: Eden Gilbert <eden.gilbert@ibm.com> * feat: initial implementation for connectors management in UI (#1443) * feat: initial implementation for connectors management in UI Signed-off-by: Tomas Weiss <tomas.weiss2@gmail.com> * feat: connectors prep work Signed-off-by: Tomas Weiss <tomas.weiss2@gmail.com> * feat: proper error handling Signed-off-by: Tomas Weiss <tomas.weiss2@gmail.com> * fix: missing licence headers Signed-off-by: Tomas Weiss <tomas.weiss2@gmail.com> * fix: imports Signed-off-by: Tomas Weiss <tomas.weiss2@gmail.com> * fix: missing schema Signed-off-by: Tomas Weiss <tomas.weiss2@gmail.com> * chore: post rebase adjustments Signed-off-by: Tomas Weiss <tomas.weiss2@gmail.com> * fix: proper schema Signed-off-by: Tomas Weiss <tomas.weiss2@gmail.com> * fix: code review comments Signed-off-by: Tomas Weiss <tomas.weiss2@gmail.com> --------- Signed-off-by: Tomas Weiss <tomas.weiss2@gmail.com> Signed-off-by: Eden Gilbert <eden.gilbert@ibm.com> * docs: update deployment guide (#1525) Signed-off-by: Eden Gilbert <eden.gilbert@ibm.com> * feat(ui): make 'add new agent' button admin only (#1527) Signed-off-by: Petr Kadlec <petr@puradesign.cz> Signed-off-by: Eden Gilbert <eden.gilbert@ibm.com> * docs: overhaul (#1540) Signed-off-by: Tomas Weiss <tomas.weiss2@gmail.com> Signed-off-by: Eden Gilbert <eden.gilbert@ibm.com> * feat(docs): add guide on connecting CLI to remote servers (#1541) Signed-off-by: Tomas Pilar <thomas7pilar@gmail.com> Signed-off-by: Eden Gilbert <eden.gilbert@ibm.com> * feat(server): refresh unmanaged agent cards (#1528) Signed-off-by: Aleš Kalfas <kalfas.ales@gmail.com> Signed-off-by: Eden Gilbert <eden.gilbert@ibm.com> * docs: minor changes (#1545) Signed-off-by: Matous Havlena <havlenma@gmail.com> Signed-off-by: Eden Gilbert <eden.gilbert@ibm.com> * chore: docs workflow (#1502) * chore: docs workflow Signed-off-by: Tomas Weiss <tomas.weiss2@gmail.com> * fix: better quoting Signed-off-by: Tomas Weiss <tomas.weiss2@gmail.com> * fix: better git habndling Signed-off-by: Tomas Weiss <tomas.weiss2@gmail.com> * chore: improve PR template Signed-off-by: Tomas Weiss <tomas.weiss2@gmail.com> * chore: provide docs Signed-off-by: Tomas Weiss <tomas.weiss2@gmail.com> --------- Signed-off-by: Tomas Weiss <tomas.weiss2@gmail.com> Signed-off-by: Eden Gilbert <eden.gilbert@ibm.com> * chore: bump up uvicorn timeouts to 5s, make configurable (#1548) Signed-off-by: Matous Havlena <havlenma@gmail.com> Signed-off-by: Jan Pokorný <JenomPokorny@gmail.com> Co-authored-by: Jan Pokorný <JenomPokorny@gmail.com> Signed-off-by: Eden Gilbert <eden.gilbert@ibm.com> * fix(server): connectors header forwading (#1553) Signed-off-by: Tomas Pilar <thomas7pilar@gmail.com> Signed-off-by: Eden Gilbert <eden.gilbert@ibm.com> * release: v0.4.2-rc1 Signed-off-by: Eden Gilbert <eden.gilbert@ibm.com> * docs: add explicit WSL instructions Signed-off-by: Jan Pokorný <JenomPokorny@gmail.com> Signed-off-by: Eden Gilbert <eden.gilbert@ibm.com> * fix: long operations inside transactions cause db connection exhaustion (#1549) Signed-off-by: Radek Ježek <radek.jezek@ibm.com> Signed-off-by: Eden Gilbert <eden.gilbert@ibm.com> * ci: add missing mise.lock checksums Signed-off-by: Jan Pokorný <JenomPokorny@gmail.com> Signed-off-by: Eden Gilbert <eden.gilbert@ibm.com> * feat(agentstack-cli): clarify agent statuses (fixes #1535) Signed-off-by: Jan Pokorný <JenomPokorny@gmail.com> Signed-off-by: Eden Gilbert <eden.gilbert@ibm.com> * feat(agentstack-cli): redesign agentstack list output Fixes #1536 Signed-off-by: Jan Pokorný <JenomPokorny@gmail.com> Signed-off-by: Eden Gilbert <eden.gilbert@ibm.com> * docs(agentstack-cli): add custom help text (#1554) Signed-off-by: Eden Gilbert <eden.gilbert@ibm.com> * docs: improve WSL2 installation instructions Signed-off-by: Jan Pokorný <JenomPokorny@gmail.com> Signed-off-by: Eden Gilbert <eden.gilbert@ibm.com> * Update deployment-guide.mdx (#1573) Signed-off-by: Jenna Winkler <135358348+jenna-winkler@users.noreply.github.com> Signed-off-by: Eden Gilbert <eden.gilbert@ibm.com> * chore: fixing dead links in the docs (#1557) Signed-off-by: Tomas Weiss <tomas.weiss2@gmail.com> Signed-off-by: Eden Gilbert <eden.gilbert@ibm.com> * refactor(web): use single framewok-diagram.svg file themeable with CSS variables (#1539) Signed-off-by: Eden Gilbert <eden.gilbert@ibm.com> * refactor(ui): rework Spinner component with CSS only animation, remove lottie-react (#1538) Signed-off-by: Eden Gilbert <eden.gilbert@ibm.com> * fix(agentstack-cli): properly react to misconfigured WSL2 Signed-off-by: Jan Pokorný <JenomPokorny@gmail.com> Signed-off-by: Eden Gilbert <eden.gilbert@ibm.com> * docs(agentstack-cli): clarify WSL install steps Signed-off-by: Jan Pokorný <JenomPokorny@gmail.com> Signed-off-by: Eden Gilbert <eden.gilbert@ibm.com> * feat(agentstack-cli): add `agentstack server switch` alias Signed-off-by: Jan Pokorný <JenomPokorny@gmail.com> Signed-off-by: Eden Gilbert <eden.gilbert@ibm.com> * feat(ui): remove links to docs and support (#1570) Signed-off-by: Eden Gilbert <eden.gilbert@ibm.com> * chore(ui): update "starting the agent" copy (#1571) Signed-off-by: Eden Gilbert <eden.gilbert@ibm.com> * fix(ui): messages being cut off on narrower screens (#1546) Signed-off-by: Eden Gilbert <eden.gilbert@ibm.com> * feat(ui): hide offline agents (#1434) Signed-off-by: Eden Gilbert <eden.gilbert@ibm.com> * feat(ui): render Markdown syntax inside trajectories (#1555) Signed-off-by: Eden Gilbert <eden.gilbert@ibm.com> * chore(server): add resource discovery root fallback to connectors (#1587) Signed-off-by: Tomas Pilar <thomas7pilar@gmail.com> Signed-off-by: Eden Gilbert <eden.gilbert@ibm.com> * feat(ui): update homepage and sidebar (#1512) Signed-off-by: Eden Gilbert <eden.gilbert@ibm.com> * chore: remove unnecessary __init__.py (#1494) Signed-off-by: Eden Gilbert <eden.gilbert@ibm.com> * fix(ui): replace trajectory group with latest content, add docs (#1523) Signed-off-by: Petr Kadlec <petr@puradesign.cz> Signed-off-by: Eden Gilbert <eden.gilbert@ibm.com> * fix(ui): mute error toasts on session expiration (#1589) Signed-off-by: Petr Kadlec <petr@puradesign.cz> Signed-off-by: Eden Gilbert <eden.gilbert@ibm.com> * fix: avoid setting up embeddings on RITS resolves #1578 Signed-off-by: Jan Pokorný <JenomPokorny@gmail.com> Signed-off-by: Eden Gilbert <eden.gilbert@ibm.com> * feat: update beeai-framework Signed-off-by: Tomas Dvorak <toomas2d@gmail.com> Signed-off-by: Eden Gilbert <eden.gilbert@ibm.com> * Update README.md (#1569) * Update README.md Add Radek's agent as reference Signed-off-by: Jenna Winkler <135358348+jenna-winkler@users.noreply.github.com> * Update README.md Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com> Signed-off-by: Jenna Winkler <135358348+jenna-winkler@users.noreply.github.com> * Update README.md * Update README.md * Update README.md Signed-off-by: Jenna Winkler <135358348+jenna-winkler@users.noreply.github.com> --------- Signed-off-by: Jenna Winkler <135358348+jenna-winkler@users.noreply.github.com> Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com> Signed-off-by: Eden Gilbert <eden.gilbert@ibm.com> * docs: cleanup (#1586) * docs: updates Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com> Signed-off-by: Jenna Winkler <135358348+jenna-winkler@users.noreply.github.com> * Update docs/docs.json Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com> Signed-off-by: Jenna Winkler <135358348+jenna-winkler@users.noreply.github.com> * Update authenticate-cli-to-server.mdx Signed-off-by: Jenna Winkler <135358348+jenna-winkler@users.noreply.github.com> * Update README.md Signed-off-by: Jenna Winkler <135358348+jenna-winkler@users.noreply.github.com> * docs: updates --------- Signed-off-by: Jenna Winkler <135358348+jenna-winkler@users.noreply.github.com> Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com> Signed-off-by: Eden Gilbert <eden.gilbert@ibm.com> * fix(helm): peroperly configure agent_registry.sync_period_cron Fixes #1211 Signed-off-by: Jan Pokorný <JenomPokorny@gmail.com> Signed-off-by: Eden Gilbert <eden.gilbert@ibm.com> * fix(tests): skip heavy docling e2e test (#1595) Signed-off-by: Radek Ježek <radek.jezek@ibm.com> Signed-off-by: Eden Gilbert <eden.gilbert@ibm.com> * feat: add validation for agent import URL (#1544) Signed-off-by: Eden Gilbert <eden.gilbert@ibm.com> * feat(agentstack-cli): use better heuristics for determining for adding agents (#1603) Signed-off-by: Eden Gilbert <eden.gilbert@ibm.com> * feat(agentstack-cli): add server info and confirmations to CLI commands (#1590) Signed-off-by: Eden Gilbert <eden.gilbert@ibm.com> * feat(cli): add SingleSelect field support to forms (#1596) Signed-off-by: Petr Kadlec <petr@puradesign.cz> Signed-off-by: Eden Gilbert <eden.gilbert@ibm.com> * fix(ui): display agent-generated images in response markdown (#1601) Signed-off-by: Petr Kadlec <petr@puradesign.cz> Signed-off-by: Eden Gilbert <eden.gilbert@ibm.com> * feat(ui): render markdown in API error messages (#1593) Signed-off-by: Petr Kadlec <petr@puradesign.cz> Signed-off-by: Petr Bulánek <bulanek.petr@gmail.com> Co-authored-by: Petr Bulánek <bulanek.petr@gmail.com> Signed-off-by: Eden Gilbert <eden.gilbert@ibm.com> * docs: add permissions and tokens page (#1576) Signed-off-by: Radek Ježek <radek.jezek@ibm.com> Signed-off-by: Matous Havlena <havlenma@gmail.com> Co-authored-by: Matous Havlena <havlenma@gmail.com> Signed-off-by: Eden Gilbert <eden.gilbert@ibm.com> * fix(server): send proxy errors as a2a errors (#1594) Signed-off-by: Radek Ježek <radek.jezek@ibm.com> Signed-off-by: Eden Gilbert <eden.gilbert@ibm.com> * fix(tests): use maximize disk space action (#1607) Signed-off-by: Radek Ježek <radek.jezek@ibm.com> Signed-off-by: Eden Gilbert <eden.gilbert@ibm.com> * fix(tests): switch to custom model again (#1608) Signed-off-by: Radek Ježek <radek.jezek@ibm.com> Signed-off-by: Eden Gilbert <eden.gilbert@ibm.com> * chore: form extension rework (#1481) Signed-off-by: Eden Gilbert <eden.gilbert@ibm.com> * fix(server): include redirect_uri into connector's token request (#1616) Signed-off-by: Tomas Pilar <thomas7pilar@gmail.com> Signed-off-by: Eden Gilbert <eden.gilbert@ibm.com> * feat: update beeai framework (#1611) Signed-off-by: Tomas Dvorak <toomas2d@gmail.com> Signed-off-by: Eden Gilbert <eden.gilbert@ibm.com> * fix(cli): agent info command missing auth (#1622) Signed-off-by: Radek Ježek <radek.jezek@ibm.com> Signed-off-by: Eden Gilbert <eden.gilbert@ibm.com> * feat(ui): redo sidebar and homepage (#1610) Signed-off-by: Eden Gilbert <eden.gilbert@ibm.com> * feat: extending TS sdk (#1609) * feat: extending TS sdk Signed-off-by: Tomas Weiss <tomas.weiss2@gmail.com> * fix: code review comments Signed-off-by: Tomas Weiss <tomas.weiss2@gmail.com> * fix: remove GET from the callApi function, still keep the method for extensibility in the future Signed-off-by: Tomas Weiss <tomas.weiss2@gmail.com> * chore: cleanup package.json Signed-off-by: Tomas Weiss <tomas.weiss2@gmail.com> * chore: testing release pipeline Signed-off-by: Tomas Weiss <tomas.weiss2@gmail.com> * chore: install mise Signed-off-by: Tomas Weiss <tomas.weiss2@gmail.com> * fix: no git checks Signed-off-by: Tomas Weiss <tomas.weiss2@gmail.com> * chore: setup release action Signed-off-by: Tomas Weiss <tomas.weiss2@gmail.com> * fix: code review commnets Signed-off-by: Tomas Weiss <tomas.weiss2@gmail.com> --------- Signed-off-by: Tomas Weiss <tomas.weiss2@gmail.com> Signed-off-by: Eden Gilbert <eden.gilbert@ibm.com> * release: v0.4.2-rc2 Signed-off-by: Eden Gilbert <eden.gilbert@ibm.com> * fix(agents): add temporary fallback imports (#1624) Signed-off-by: Radek Ježek <radek.jezek@ibm.com> Signed-off-by: Eden Gilbert <eden.gilbert@ibm.com> * release: v0.4.2-rc3 Signed-off-by: Eden Gilbert <eden.gilbert@ibm.com> * chore: update release sdk to npm instead of pnpm Signed-off-by: Tomas Weiss <tomas.weiss2@gmail.com> Signed-off-by: Eden Gilbert <eden.gilbert@ibm.com> * release: v0.4.2-rc4 Signed-off-by: Eden Gilbert <eden.gilbert@ibm.com> * chore: update npm for release Signed-off-by: Tomas Weiss <tomas.weiss2@gmail.com> Signed-off-by: Eden Gilbert <eden.gilbert@ibm.com> * release: v0.4.2-rc5 Signed-off-by: Eden Gilbert <eden.gilbert@ibm.com> * chore: add release tag for npm Signed-off-by: Tomas Weiss <tomas.weiss2@gmail.com> Signed-off-by: Eden Gilbert <eden.gilbert@ibm.com> * release: v0.4.2-rc6 Signed-off-by: Eden Gilbert <eden.gilbert@ibm.com> * chore: missing repository Signed-off-by: Tomas Weiss <tomas.weiss2@gmail.com> Signed-off-by: Eden Gilbert <eden.gilbert@ibm.com> * release: v0.4.2-rc7 Signed-off-by: Eden Gilbert <eden.gilbert@ibm.com> * chore: run mise fix Signed-off-by: Eden Gilbert <eden.gilbert@ibm.com> --------- Signed-off-by: Eden Gilbert <eden.gilbert@ibm.com> Signed-off-by: Eden Gilbert <117227212+edengilbert@users.noreply.github.com> Signed-off-by: Petr Kadlec <petr@puradesign.cz> Signed-off-by: Tomas Pilar <thomas7pilar@gmail.com> Signed-off-by: Radek Ježek <radek.jezek@ibm.com> Signed-off-by: Jenna Winkler <135358348+jenna-winkler@users.noreply.github.com> Signed-off-by: Tomas Weiss <tomas.weiss2@gmail.com> Signed-off-by: Aleš Kalfas <kalfas.ales@gmail.com> Signed-off-by: Matous Havlena <havlenma@gmail.com> Signed-off-by: Jan Pokorný <JenomPokorny@gmail.com> Signed-off-by: Tomas Dvorak <toomas2d@gmail.com> Signed-off-by: Petr Bulánek <bulanek.petr@gmail.com> Co-authored-by: Petr Kadlec <petr@puradesign.cz> Co-authored-by: Petr Bulánek <bulanek.petr@gmail.com> Co-authored-by: Tomas Pilar <thomas7pilar@gmail.com> Co-authored-by: Radek Ježek <radek.jezek@ibm.com> Co-authored-by: Jenna Winkler <135358348+jenna-winkler@users.noreply.github.com> Co-authored-by: Tomáš Weiss <tomas.weiss2@gmail.com> Co-authored-by: Aleš Kalfas <32630459+aleskalfas@users.noreply.github.com> Co-authored-by: Matous Havlena <havlenma@gmail.com> Co-authored-by: Jan Pokorný <JenomPokorny@gmail.com> Co-authored-by: Arun Babu Neelicattu <arun.neelicattu@gmail.com> Co-authored-by: Tomas Dvorak <toomas2d@gmail.com> Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
diff --git a/.github/workflows/release.yml b/.github/workflows/release.yml
@@ -160,4 +160,4 @@ jobs:
 
       - name: Publish TS SDK
         working-directory: apps/agentstack-sdk-ts
-        run: npm publish --tag ${{ steps.version.outputs.npmTag }}
+        run: npm publish --tag ${{ steps.version.outputs.npmTag }}
diff --git a/apps/beeai-web/src/modules/blog/posts/a2a-server.mdx b/apps/beeai-web/src/modules/blog/posts/a2a-server.mdx
@@ -0,0 +1,160 @@
+export const metadata = {
+  title: 'How to Run a BeeAI Framework Agent as an A2A Server',
+  date: '2025-11-10',
+  author: 'Eden Gilbert, Ken Ocheltree',
+};
+
+The [BeeAI Framework](https://framework.beeai.dev/introduction/welcome) provides native support for the Agent2Agent
+(A2A) Protocol, enabling you to build distributed multi-agent systems where different AI agents can communicate
+regardless of how or where they're deployed. In this guide, we'll walk through creating a BeeAI agent as an A2A server
+and how to connect to it from a client.
+
+## Understanding Agent2Agent (A2A) Communication
+
+AI agents in production require reusable capabilities that work across repositories, languages, and teams. The
+[Agent2Agent (A2A) Protocol](https://a2a-protocol.org/latest/) is a new standard for agent-to-agent communication,
+allowing different AI agents to interact no matter their original framework or implementation details. RPC (Remote
+Procedure Call) is the backbone of A2A: it lets one agent ask another to “run this function and give me the result” or
+hand off a task to another agent. BeeAI wraps this in a simple API, so your agent can expose or consume capabilities
+without having to worry about the networking details of the A2A protocol. With this, you get modular services from
+different specialized agents with clean handoffs and easy scaling. The BeeAI Framework is A2A Native with the ability to
+interoperate with any A2A agent system, providing built-in support without complex setup.
+
+### What A2A solves
+
+- **Interoperability:** enables agents to communicate across frameworks/runtimes without custom SDKs
+
+- **Reuse & separation of concerns:** turns capabilities into a service that other agents can call
+
+- **Cost & performance:** specializes agents and models per task, calls the right one on demand
+
+- **Reliability:** RPC contracts make the behavior predictable and debuggable
+
+### When to run an A2A server, client, or both
+
+- **Server:** when exposing a capability for others (eg: “FormatterService” that normalizes or transforms text).
+
+- **Client:** you need to call other agents/services as part of your workflow (eg: an “Author” agent that asks a
+  “Formatter” agent to clean output).
+
+- **Both:** your agent is reusable as a service and also calls other agents as a service
+
+In this blog, we’ll build a small **FormatterService** (the server) and a **Writer** (the client) so you can see the
+end-to-end process.
+
+## Getting started
+
+### Prerequisites
+
+- Python 3.10+
+- ollama installed with granite3.3:8b running
+- uv installed
+
+In a new project folder, create a virtual environment and install the BeeAI Framework with A2A extras:
+
+```bash
+uv init
+uv add 'beeai-framework[a2a]'
+```
+
+Open the new project in your IDE.
+
+## Step 1: Build the Server’s Agent Logic and Expose the Agent as an A2A Server
+
+Create a new file called **a2a_server.py** that wraps a single agent and makes it available over HTTP as an A2AServer.
+
+```python
+# a2a_server.py
+from beeai_framework.adapters.a2a import A2AServer, A2AServerConfig
+from beeai_framework.agents.requirement import RequirementAgent
+from beeai_framework.backend import ChatModel
+from beeai_framework.memory import UnconstrainedMemory
+from beeai_framework.serve.utils import LRUMemoryManager
+
+def main() -> None:
+    llm = ChatModel.from_name("ollama:granite3.3:8b")
+    agent = RequirementAgent(
+        llm=llm,
+        memory=UnconstrainedMemory(),
+        instructions="You are an agent that reverses text input. Reverse the user's input exactly.",
+    )
+
+    # Register the agent with the A2A server and run the HTTP server
+    A2AServer(
+        config=A2AServerConfig(port=9999, protocol="jsonrpc"),
+        memory_manager=LRUMemoryManager(maxsize=100)
+    ).register(agent, send_trajectory=True).serve()
+
+if __name__ == "__main__":
+    main()
+```
+
+## Step 2: Running the Server
+
+Start your agent service from your terminal.
+
+```bash
+uv run a2a_server.py
+```
+
+Your BeeAI agent is now exposed at [http://localhost:9999](http://localhost:9999). Your computer may request to allow
+the port to show the service on your localhost.
+
+## Step 3: Call the Agent from a Client
+
+Save this simple python client as **a2a_client.py**:
+
+```python
+# a2a_client.py
+import asyncio
+from beeai_framework.adapters.a2a.agents import A2AAgent
+from beeai_framework.memory.unconstrained_memory import UnconstrainedMemory
+async def main() -> None:
+
+    agent = A2AAgent(url="http://127.0.0.1:9999", memory=UnconstrainedMemory())
+
+    # Send a message
+    text = input("Enter input: ")
+    response = await agent.run(text)
+
+    # Print the response
+    print("Agent response:", response.last_message.text)
+
+if __name__ == "__main__":
+    asyncio.run(main())
+```
+
+Any client on your computer (another agent, application, or a script) can call your agent over A2A.
+
+Note: If you had served your agent over a non-local IP address and allowed access on that port, that agent could be
+accessed by agents on other computers on your network. Caution is advised on making agents available beyond the
+localhost.
+
+The client is run by invoking it in a separate terminal:
+
+```bash
+uv run a2a_client.py
+```
+
+The client agent dialog appears as follows:
+
+```python
+Enter input: Hello World
+Agent response: dlroW olleH
+```
+
+How It Works
+
+- A2AServer: Hosts a single BeeAI agent and makes it reachable on the same computer over HTTP.
+
+- A2AAgent (client): Sends a request to that server and receives the agent's response.
+
+- One agent per server: Keeps each service focused on one singular capability
+
+## Conclusion
+
+The A2A protocol makes it simple to turn a BeeAI agent into a service that other agents can call. With just a few lines
+of Python, you can expose your agent over HTTP and begin composing multi-agent workflows, an essential step toward
+building scalable, modular agent ecosystems. Get up and running with BeeAI Framework lighting-fast with the
+[quickstart](https://framework.beeai.dev/introduction/quickstart) or go deep on all the capabilities by taking the
+[grand tour](https://framework.beeai.dev/introduction/tour). Happy building!
