Once the Coral Server is running, you can initiate your first interaction between Coralized Agents using a thread-based communication model. This walkthrough demonstrates how agents interact through message passing, capability delegation, and scoped memory sharing.
Step 1: Start the Server
If not already running, follow the Quickstart instructions to launch the Coral Server in SSE mode:
Ensure the server is listening on the appropriate port (default: 3001).
Step 2: Register Agents
Each agent must be registered with the Coral Server before participating in a thread.
Example (via Coralizer CLI or direct API call):
Repeat this for other agents (e.g. math_agent
, interface_agent
).
Step 3: Create a Thread
Threads act as shared communication spaces for agent collaboration.
Step 4: Send a Message
Messages include:
Step 5: Agents Respond
Mentioned agents receive the message and respond accordingly. The search_agent
may reply:
Then the math_agent
performs the calculation and returns:
Step 6: View the Thread Log
Each message is recorded in the thread history, enabling traceability and context preservation. This log allows agents to maintain state and reason over previous messages.
Once the Coral Server is running, you can initiate your first interaction between Coralized Agents using a thread-based communication model. This walkthrough demonstrates how agents interact through message passing, capability delegation, and scoped memory sharing.
Step 1: Start the Server
If not already running, follow the Quickstart instructions to launch the Coral Server in SSE mode:
Ensure the server is listening on the appropriate port (default: 3001).
Step 2: Register Agents
Each agent must be registered with the Coral Server before participating in a thread.
Example (via Coralizer CLI or direct API call):
Repeat this for other agents (e.g. math_agent
, interface_agent
).
Step 3: Create a Thread
Threads act as shared communication spaces for agent collaboration.
Step 4: Send a Message
Messages include:
Step 5: Agents Respond
Mentioned agents receive the message and respond accordingly. The search_agent
may reply:
Then the math_agent
performs the calculation and returns:
Step 6: View the Thread Log
Each message is recorded in the thread history, enabling traceability and context preservation. This log allows agents to maintain state and reason over previous messages.