Agently Docs

Agently documentation for building AI applications with stable outputs, observable actions, and durable workflows.

View the Project on GitHub AgentEra/Agently

Agently 4.1.3.1 Release Notes

Languages: English · 中文

Agently 4.1.3.1 is a foundation release for explicit multi-turn task information management. It adds a durable Workspace substrate, a Recall context skeleton, and Action Runtime defaults that let application code store and recover task information across repeated execution steps.

This release does not introduce autonomous WorkLoop planning. Application code, TriggerFlow definitions, or ordinary Python loops still decide when to observe, ingest, search, checkpoint, and build context.

Highlights

agent = Agently.create_agent("issue-run").use_workspace("./.agently/runs/issue-123")

record = await agent.workspace.ingest(
    content={"route": None, "status": "failed"},
    collection="observations",
    kind="route_attempt",
    summary="Provider returned no route candidate",
    scope={"task_id": "issue-123", "area": "routing"},
    source={"type": "workflow", "step": "attempt-1"},
)

await agent.workspace.checkpoint(
    "issue-123",
    {"status": "failed", "evidence": record["id"]},
    step_id="attempt-1",
)

context = await agent.workspace.build_context(
    goal="Prepare the second routing attempt",
    scope={"task_id": "issue-123", "area": "routing"},
    budget={"max_items": 4},
)

Expose file actions separately when the model or action layer needs to read or write files in the Workspace file area:

agent.use_workspace("./.agently/runs/issue-123")
agent.enable_workspace_file_actions(write=True)
agent.enable_shell(commands=["cat", "python"])

Action outputs are not automatically memory. Store them explicitly:

result = agent.action.execute_action("inspect_workspace_files", {"cmd": "cat notes/runtime.txt"})
await agent.workspace.ingest(
    content={"stdout": result["data"]["stdout"]},
    collection="observations",
    kind="action_output",
    summary="Shell inspection output",
    scope={"task_id": "issue-123"},
    source={"type": "action", "name": "inspect_workspace_files"},
)

Examples

Compatibility