Agently Agent工作流

Quickstart

Install:

pip install -U agently

Use DeepSeek or another OpenAI-compatible hosted endpoint:

from agently import Agently

Agently.set_settings(
    "OpenAICompatible",
    {
        "base_url": "https://api.deepseek.com/v1",
        "model": "deepseek-chat",
        "auth": "DEEPSEEK_API_KEY",
        "model_type": "chat",
        "request_options": {"temperature": 0.2},
    },
)

agent = Agently.create_agent()

result = (
    agent
    .input("Introduce Python in one sentence and list three strengths.")
    .output({
        "intro": (str, "one sentence", True),
        "strengths": [(str, "one strength")],
    })
    .start(ensure_all_keys=True)
)

print(result)

Use local Ollama by changing provider settings:

ollama pull qwen2.5:7b

Agently.set_settings(
    "OpenAICompatible",
    {
        "base_url": "http://127.0.0.1:11434/v1",
        "model": "qwen2.5:7b",
        "api_key": "ollama",
        "model_type": "chat",
    },
)

For file-backed settings, prefer:

from agently import Agently

Agently.load_settings("yaml_file", "settings.yaml", auto_load_env=True)

Examples

Recommended model-app examples call a real model through DeepSeek or local Ollama and include an Expected key output source comment with stable key values from one real run.

Useful entry points:

Archived examples live under examples/archived/ and are compatibility references, not the recommended starting point for new apps.

Integrations

FAQ

What makes Agently different from direct SDK calls?

Direct SDK calls are excellent when the app only needs a small number of prompts. Agently adds contracts around those calls: prompt slots, output parsing, validation, retries, response reuse, action logs, session memory, configuration, service helpers, and TriggerFlow.

How is Agently different from LangChain?

LangChain provides broad integrations, prebuilt agents, and flexible building blocks. Agently is narrower and more opinionated about the model request boundary: provider setup, prompt slots, structured output, parser feedback, retries, validation, response reuse, action execution, settings, and observability are designed to line up as one contract. The goal is to let teams change the underlying model or provider without forcing downstream business logic to relearn output or tool-call shape.

How is Agently different from LangGraph?

LangGraph is strong when the central problem is graph-based agent state and durable execution. TriggerFlow is designed as Agently's signal-driven workflow layer: model-side instant structured events, action results, external events, pause/resume, runtime stream items, execution state, and close snapshots can all participate in the same orchestration story.

How is Agently different from CrewAI or AutoGen?

CrewAI and AutoGen are strong choices when the primary design is collaboration among agents. Agently is a lower-level application framework: multi-agent collaboration can be built as one pattern on top of structured model requests, Actions, TriggerFlow signals, sub-flows, Session, runtime resources, and service-facing execution handles.

Do I need TriggerFlow for every multi-step task?

No. Use plain Python or async functions for simple linear work. Use TriggerFlow when you need branches, fan-out, external events, pause/resume, runtime stream, persistence, or restart-safe execution.

Can I keep using older tool APIs?

Yes. The old tool family remains a compatibility surface and maps into the current action runtime. New code should prefer @agent.action_func, agent.use_actions(...), and the enable_* helpers.

How do I deploy an Agently service?

Use the async request APIs directly or wrap agents, requests, generators, TriggerFlow definitions, or TriggerFlow executions with FastAPIHelper. See the FastAPI docs and examples/fastapi/.