Skip to main content

Agents

Agents are workflow-powered assistants that run as persistent pods with function calling, memory, and tools. Use this resource to create and configure an agent, control its pod, manage conversation threads, chat (streamed), and upload knowledge.

Access it as client.agents on a Strongly client, or the same path on AsyncStrongly with await. All methods exist on both with identical signatures.

Quick start​

from strongly import Strongly

client = Strongly()

# List (auto-paginates as you iterate)  # filters: status, search
for agent in client.agents.list():
    print(agent.id)

Methods​

Core​

list​

list(*, status: Optional[str] = None, search: Optional[str] = None, limit: Optional[int] = None) -> SyncPaginator[Agent]

List agents with pagination and filtering.

Args: status: Filter by status ("running", "stopped", "starting"). search: Search by agent name. limit: Maximum number of items to return (default: all matching items).

create​

create(*, name: str, description: Optional[str] = None, nodes: Optional[Sequence[Mapping[str, Any]]] = None, connections: Optional[Sequence[Mapping[str, Any]]] = None) -> Dict[str, Any]

Create a new agent.

Creates a workflow in agent mode.

Args: name: Agent name (required). description: Human-readable description. nodes: Workflow node definitions. connections: Workflow connection definitions.

retrieve​

retrieve(agent_id: str) -> Agent

Get detailed agent information including live status.

Args: agent_id: Agent workflow ID.

update​

update(agent_id: str, *, name: Optional[str] = None, description: Optional[str] = None, nodes: Optional[Sequence[Mapping[str, Any]]] = None, connections: Optional[Sequence[Mapping[str, Any]]] = None, config: Optional[Mapping[str, Any]] = None) -> Dict[str, Any]

Update an agent's configuration.

Args: agent_id: Agent workflow ID. name, description, nodes, connections: Workflow-level fields to update. config: Runtime config applied to a running agent pod.

delete​

delete(agent_id: str) -> None

Delete an agent - stops pod, removes agent mode, cleans up records.

Args: agent_id: Agent workflow ID.

Lifecycle & actions​

start​

start(agent_id: str) -> Dict[str, Any]

Start an agent pod.

Creates a persistent Kubernetes pod running the agent server.

Args: agent_id: Agent workflow ID.

Returns: Dict with agent_id, pod_ip, success.

stop​

stop(agent_id: str) -> Dict[str, Any]

Stop a running agent pod.

Args: agent_id: Agent workflow ID.

redeploy​

redeploy(agent_id: str) -> Dict[str, Any]

Apply pending brain-config changes to a running agent by stopping and re-starting the pod. No-op when no pod is running - the next start picks up the latest config either way.

promote​

promote(workflow_id: str) -> Dict[str, Any]

Promote a workflow to agent mode.

The workflow must contain at least one agent node.

Args: workflow_id: Workflow ID to promote.

Other​

analytics​

analytics(agent_id: str, *, days: int = 30) -> AgentAnalytics

Get agent analytics - sessions, tokens, success rate, daily activity.

Args: agent_id: Agent workflow ID. days: Number of days to look back (default: 30).

attach_skill​

attach_skill(agent_id: str, *, skill_id: str, editable: Optional[bool] = None, auto_connected: Optional[bool] = None, connected_by: Optional[str] = None) -> Dict[str, Any]

Attach a skill to an agent.

Args: agent_id: Agent workflow ID. skill_id: Skill id to attach (required). editable: Whether the agent may edit the skill (default true server-side). auto_connected: Whether the skill was auto-connected (default true server-side). connected_by: Who attached the skill (default agent server-side).

chat​

chat(agent_id: str, thread_id: str, message: str) -> Iterator[Dict[str, Any]]

Send a message to an agent and stream the response.

Yields SSE events as dictionaries. Each event has an event field (e.g., "thread.message.delta") and a data field with the payload.

Args: agent_id: Agent workflow ID. thread_id: Thread ID for the conversation. message: Message to send.

Yields: SSE event dictionaries.

Example::

for event in client.agents.chat("wf_abc", "thread_123", "/help"): if event.get("event") == "thread.message.delta": content = event["data"]["delta"].get("content", "") print(content, end="") elif event.get("event") == "thread.run.completed": print("\n--- Done ---")

config​

config(agent_id: str) -> Dict[str, Any]

Read the agent's current config - personality, operating prompt reference, context policy, session policy, heartbeat, primary model, fallback models, plus whether the agent pod is running.

create_artifact​

create_artifact(agent_id: str, *, title: str, content: str, artifact_type: Optional[str] = None, thread_id: Optional[str] = None, summary: Optional[str] = None, skill_id: Optional[str] = None, tags: Optional[Sequence[str]] = None, metadata: Optional[Mapping[str, Any]] = None) -> Dict[str, Any]

Record a new agent artifact.

Args: agent_id: Agent workflow ID. title: Artifact title (required). content: Artifact content (required). artifact_type: Artifact type (default html_report server-side). thread_id: Originating thread id. summary: Short summary. skill_id: Skill that produced the artifact. tags: Categorization tags. metadata: Arbitrary metadata blob.

create_thread​

create_thread(agent_id: str, *, title: Optional[str] = None) -> AgentThread

Create a new conversation thread.

Args: agent_id: Agent workflow ID. title: Thread title (default: "New Conversation").

delete_artifact​

delete_artifact(agent_id: str, artifact_id: str) -> None

Delete an agent artifact.

delete_thread​

delete_thread(agent_id: str, thread_id: str) -> None

Delete a conversation thread.

Args: agent_id: Agent workflow ID. thread_id: Thread ID to delete.

detach_skill​

detach_skill(agent_id: str, skill_id: str) -> Dict[str, Any]

Remove a skill from an agent.

list_artifacts​

list_artifacts(agent_id: str) -> Dict[str, Any]

List artifacts the agent has produced.

list_skills​

list_skills(agent_id: str) -> Dict[str, Any]

List skills attached to an agent.

list_threads​

list_threads(agent_id: str) -> List[AgentThread]

List conversation threads for an agent.

Args: agent_id: Agent workflow ID.

retrieve_artifact​

retrieve_artifact(agent_id: str, artifact_id: str) -> Dict[str, Any]

Get a single agent artifact.

status​

status(agent_id: str) -> AgentStatus

Get the current status of an agent pod.

Args: agent_id: Agent workflow ID or pod ID.

update_context_policy​

update_context_policy(agent_id: str, *, kind: str, token_budget: int, keep_recent: int) -> Dict[str, Any]

Write the agent's context policy. kind is one of window / summarise / hierarchical. Requires a redeploy.

update_model​

update_model(agent_id: str, model_id: str, fallback_model_ids: Optional[List[str]] = None) -> Dict[str, Any]

Swap the agent's primary model and (optionally) its ordered fallback list. The platform rebuilds the runtime services bundle on save; call redeploy afterwards to bring up a pod on the new model.

update_operating_prompt​

update_operating_prompt(agent_id: str, operating_prompt_id: Optional[str]) -> Dict[str, Any]

Point the agent at a Library prompt. None resets to the platform default. Operating-prompt edits live-reload on the agent's next turn - no redeploy needed.

update_personality​

update_personality(agent_id: str, personality: str) -> Dict[str, Any]

Set the inline personality paragraph. Requires a redeploy via redeploy to take effect on a running agent.

update_skill​

update_skill(agent_id: str, skill_id: str, *, editable: bool) -> Dict[str, Any]

Update a skill attachment's editable flag on an agent.

upload_knowledge​

upload_knowledge(agent_id: str, file: Union[str, Path, BinaryIO], *, description: Optional[str] = None, tags: Optional[str] = None, document_id: Optional[str] = None) -> KnowledgeUploadResult

Upload a document to the agent's knowledge base.

The file is sent to the agent's knowledge-upload workflow which parses it (PDF, PPTX, TXT, MD, HTML, CSV - with OCR fallback for scanned PDFs), chunks the text, generates embeddings, and stores them in the agent's Milvus vector database.

Args: agent_id: Agent workflow ID. file: Path to a file, or a file-like object opened in binary mode. description: Human-readable description of the document. tags: Comma-separated tags for categorization. document_id: Custom document ID. Auto-generated if omitted.

Returns: KnowledgeUploadResult with document_id, filename, file_size, execution_id, and status.

Example::

result = client.agents.upload_knowledge( "wf_abc123", "brand-guide.pdf", description="Company brand guidelines", tags="brand,guide", ) print(f"Ingesting {result.filename} → {result.status}")