Skip to main content

Modern graph orchestration library for building stateful, multi-actor applications with LLMs

Project description

synth-graph

Modern graph orchestration library for building stateful, multi-actor applications with LLMs.

Part of the Synth AI ecosystem.

Features

  • 🔄 Stateful graph orchestration
  • 🎭 Multi-actor coordination
  • 🧠 LLM-native workflows
  • 📊 Built-in observability
  • ⚡ Async-first design
  • 🔗 Seamless integration with Synth AI tools

Installation

pip install synth-graph

Quick Start

from synth_graph import Graph, Node

# Create a graph
g = Graph()

# Add nodes
g.add_node("start", Node(fn=lambda x: x))
g.add_node("process", Node(fn=lambda x: x * 2))
g.add_node("end", Node(fn=lambda x: x))

# Connect nodes
g.add_edge("start", "process")
g.add_edge("process", "end")

# Execute
result = g.run(input_data=5)
print(result)  # 10

Related Packages

  • finetuning - Fine-tuning library for LLMs
  • synth-ai - Main Synth AI SDK

License

MIT

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

synth_graph-0.1.0.tar.gz (2.4 kB view details)

Uploaded Source

Built Distribution

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

synth_graph-0.1.0-py3-none-any.whl (2.1 kB view details)

Uploaded Python 3

File details

Details for the file synth_graph-0.1.0.tar.gz.

File metadata

  • Download URL: synth_graph-0.1.0.tar.gz
  • Upload date:
  • Size: 2.4 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.1.0 CPython/3.11.8

File hashes

Hashes for synth_graph-0.1.0.tar.gz
Algorithm Hash digest
SHA256 6d05481fff72a1cd5f52eab2c841927f417a5b1acda8e7cb0de15212d4f442da
MD5 4b648ee6b354f00c0f39a148cfb1e4c3
BLAKE2b-256 e194fc3ecc565a78225714efca491e6c08dc588b448abe791d18088d8e1b4cd0

See more details on using hashes here.

File details

Details for the file synth_graph-0.1.0-py3-none-any.whl.

File metadata

  • Download URL: synth_graph-0.1.0-py3-none-any.whl
  • Upload date:
  • Size: 2.1 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.1.0 CPython/3.11.8

File hashes

Hashes for synth_graph-0.1.0-py3-none-any.whl
Algorithm Hash digest
SHA256 3251893bf4a02e20740bad095cd937f65f26d413e4624e596c75e68b7cdd60a9
MD5 6ea433e8c416c43d1062c76db96b7062
BLAKE2b-256 d7429c1668bccc553f46552019a8425ee0d8d341feade7a5e8d12fb398df6f4d

See more details on using hashes here.

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