Skip to main content

Python SDK for DuraGraph - Reliable AI Workflow Orchestration

Project description

DuraGraph Python SDK

CI PyPI version Python versions Downloads License GitHub Stars

Python SDK for DuraGraph - Reliable AI Workflow Orchestration.

Build AI agents with decorators, deploy to a control plane, and get full observability out of the box.

Installation

The package is published as duragraph-python on PyPI. We recommend uv for dependency management.

# With uv (recommended)
uv add duragraph-python
uv add 'duragraph-python[openai]'
uv add 'duragraph-python[anthropic]'
uv add 'duragraph-python[all]'

# With pip
pip install duragraph-python

Quick Start

from duragraph import Graph, llm_node, entrypoint

@Graph(id="customer_support")
class CustomerSupportAgent:
    """A customer support agent that classifies and responds to queries."""

    @entrypoint
    @llm_node(model="gpt-4o-mini")
    def classify(self, state):
        """Classify the customer intent."""
        return {"intent": "billing"}

    @llm_node(model="gpt-4o-mini")
    def respond(self, state):
        """Generate a response based on intent."""
        return {"response": f"I'll help you with {state['intent']}."}

    # Define flow
    classify >> respond


# Run locally
agent = CustomerSupportAgent()
result = agent.run({"message": "I have a billing question"})
print(result)

# Or deploy to control plane
agent.serve("http://localhost:8081")

Features

Decorator-Based Graph Definition

from duragraph import Graph, llm_node, tool_node, router_node, human_node

@Graph(id="my_agent")
class MyAgent:
    @llm_node(model="gpt-4o-mini", temperature=0.7)
    def process(self, state):
        return state

    @tool_node
    def search(self, state):
        results = my_search_function(state["query"])
        return {"results": results}

    @router_node
    def route(self, state):
        return "path_a" if state["condition"] else "path_b"

    @human_node(prompt="Please review")
    def review(self, state):
        return state

Streaming

async for event in agent.stream({"message": "Hello"}):
    if event.type == "token":
        print(event.data, end="")
    elif event.type == "node_completed":
        print(f"\nNode {event.node_id} completed")

Subgraphs

@Graph(id="research")
class ResearchAgent:
    @llm_node
    def research(self, state):
        return {"findings": "..."}

@Graph(id="main")
class MainAgent:
    research = ResearchAgent.as_subgraph()

    @entrypoint
    def plan(self, state):
        return state

    plan >> research

Requirements

  • Python 3.10+
  • DuraGraph Control Plane (for deployment)

Documentation

Related Repositories

Repository Description
duragraph Core API server
Go SDK (go-sdk/) Go SDK
duragraph-examples Example projects
duragraph-docs Documentation

Contributing

See CONTRIBUTING.md for guidelines.

License

Apache 2.0 - See LICENSE for details.

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

duragraph-0.3.0.tar.gz (324.7 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

duragraph-0.3.0-py3-none-any.whl (82.0 kB view details)

Uploaded Python 3

File details

Details for the file duragraph-0.3.0.tar.gz.

File metadata

  • Download URL: duragraph-0.3.0.tar.gz
  • Upload date:
  • Size: 324.7 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/6.1.0 CPython/3.13.12

File hashes

Hashes for duragraph-0.3.0.tar.gz
Algorithm Hash digest
SHA256 6a3ce488fb835c1d524bee49289315ca2899dbae9bc42b900dabbdb54cc06827
MD5 c553d49a40ee7332f67081abb112f11c
BLAKE2b-256 a40137752cd535209262761ffb6ff04f2bc6fc3ba73854d3b233006f24ece0fd

See more details on using hashes here.

Provenance

The following attestation bundles were made for duragraph-0.3.0.tar.gz:

Publisher: pypi.yml on Duragraph/duragraph

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

File details

Details for the file duragraph-0.3.0-py3-none-any.whl.

File metadata

  • Download URL: duragraph-0.3.0-py3-none-any.whl
  • Upload date:
  • Size: 82.0 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/6.1.0 CPython/3.13.12

File hashes

Hashes for duragraph-0.3.0-py3-none-any.whl
Algorithm Hash digest
SHA256 047ab8dd71228908f3fc0073eb3bf814733a76bcc15df1e7bca9d193c7521a71
MD5 ac16515ab673c8ab5307c6d4a1021275
BLAKE2b-256 bcdef055ecfc307d6437155196945936a94f47ca8c4a1f40d194f1f1853e96d2

See more details on using hashes here.

Provenance

The following attestation bundles were made for duragraph-0.3.0-py3-none-any.whl:

Publisher: pypi.yml on Duragraph/duragraph

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page