Skip to main content
AgentOS exposes endpoints for running agents and managing sessions, memories, knowledge, and evals. The same API powers the control plane and can be used to build your AI products.

​
Endpoints

ResourceOperations
AgentsRun, list, get
TeamsRun, list, get
WorkflowsRun, list, get
SessionsCreate, list, get, update, delete
MemoriesCreate, list, get, update, delete
KnowledgeAdd, search, list, get, delete
EvalsCreate, list, get, update, delete
MetricsGet, refresh
See the API reference for full documentation.

​
Running Agents

curl http://localhost:7777/agents/my-agent/runs \
  -H "Content-Type: application/x-www-form-urlencoded" \
  -d "message=Tell me about Agno" \
  -d "stream=true" \
  -d "[email protected]" \
  -d "session_id=session_123"
Teams and workflows follow the same pattern:
  • POST /teams/{team_id}/runs
  • POST /workflows/{workflow_id}/runs

​
Authentication

If authentication is enabled, include a JWT token: 
curl http://localhost:7777/agents/my-agent/runs \
  -H "Authorization: Bearer <your-jwt-token>" \
  -H "Content-Type: application/x-www-form-urlencoded" \
  -d "message=Your query here"
See Security & Authorization to configure authentication.

​
Passing Dependencies

Pass runtime parameters like dependencies, session_state, or metadata as form fields: 
curl http://localhost:7777/agents/story-writer/runs \
  -H "Content-Type: application/x-www-form-urlencoded" \
  -d "message=Write me a 5 line story" \
  -d 'dependencies={"robot_name": "Anna"}'

​
Output Schema

Pass a JSON schema to structure the response: 
curl http://localhost:7777/agents/story-writer/runs \
  -H "Content-Type: application/x-www-form-urlencoded" \
  -d "message=Write a story" \
  -d 'output_schema={"type":"object","properties":{"title":{"type":"string"},"content":{"type":"string"}},"required":["title","content"]}'

​
Cancelling Runs

curl -X POST http://localhost:7777/agents/story-writer/runs/123/cancel