Team

Configures a team of Agno agents that collaborate to handle complex tasks, with an optional lead model for coordination.

Config

Field	Type	Required	Default	Description
`name`	`string`	No	Resource name	Display name for the team
`description`	`string`	No	—	Team description
`role`	`string`	No	—	Team role description
`members`	`list[Dependency]`	Yes	—	References to `agno/agent` resources (at least one)
`model`	`Dependency`	No	—	Optional lead model (`agno/models/anthropic` or `agno/models/openai`)
`instructions`	`list[string]`	No	—	System instructions for the team coordinator
`prompt`	`Dependency`	No	—	Reference to `agno/prompt` for reusable instructions
`tools`	`list[Dependency]`	No	`[]`	Team-level tools (`agno/tools/mcp` or `agno/tools/websearch`)
`knowledge`	`Dependency`	No	—	Team-level knowledge base (`agno/knowledge`)
`db`	`Dependency`	No	—	Team-level database (`agno/db/postgres`)
`memory`	`Dependency`	No	—	Team-level memory (`agno/memory/manager`)
`respond_directly`	`boolean`	No	`false`	Allow team to respond without delegating to members
`delegate_to_all_members`	`boolean`	No	`false`	Delegate tasks to all members simultaneously
`markdown`	`boolean`	No	`false`	Format responses as Markdown
`add_datetime_to_context`	`boolean`	No	`false`	Include current datetime in context
`read_chat_history`	`boolean`	No	Auto	Read chat history (auto-enabled when `db` is set)
`add_history_to_context`	`boolean`	No	Auto	Add history to context (auto-enabled when `db` is set)
`num_history_runs`	`integer`	No	—	Number of previous runs to include
`enable_agentic_memory`	`boolean`	No	`false`	Enable agentic memory
`update_memory_on_run`	`boolean`	No	`false`	Update memory after each run
`add_memories_to_context`	`boolean`	No	—	Add stored memories to context
`enable_session_summaries`	`boolean`	No	`false`	Enable session summaries

Outputs

Field	Type	Description
`spec`	`object`	Serialized team specification for runtime reconstruction
`member_count`	`integer`	Number of member agents
`pip_dependencies`	`list[string]`	Python packages required by the team and all members

Dependencies

Depends on:

agno/agent (required, one or more) — member agents
agno/models/anthropic or agno/models/openai (optional) — team lead model
agno/tools/mcp or agno/tools/websearch (optional) — team-level tools
agno/knowledge (optional) — team-level knowledge base
agno/memory/manager (optional) — team-level memory
agno/db/postgres (optional) — team-level database
agno/prompt (optional) — reusable prompt template

Depended on by:

agno/runner — for deployment to Kubernetes

Example

provider: agno
resource: team
name: research-team
config:
  description: "A research team with a writer and reviewer"
  members:
    - provider: agno
      resource: agent
      name: researcher
    - provider: agno
      resource: agent
      name: writer
  model:
    provider: agno
    resource: models/anthropic
    name: claude
  delegate_to_all_members: true
  markdown: true

Notes

The members list must contain at least one agent.
Team-level dependencies (model, tools, knowledge, etc.) are shared across all members but do not override member-specific configurations.
Pip dependencies are aggregated from all members and team-level tools/knowledge.

Getting Started

Concepts

Resource Catalog

Agno (AI Agents)

GCP

Kubernetes

Building Providers

Config

Outputs

Dependencies

Example

Notes

​Config

​Outputs

​Dependencies

​Example

​Notes

Config

Outputs

Dependencies

Example

Notes