Skip to main content

GreenNode Agent Bridge

A bridge package for connecting multiple agent frameworks (LangGraph, CrewAI, Microsoft Agent Framework, etc.) with GreenNode AgentBase. Use your preferred agent framework while persisting state and memory in AgentBase Memory and Runtime services.

Features

  • Framework adaptors – Integrate agent frameworks with GreenNode AgentBase Memory and Runtime.
  • Optional extras – Install only the frameworks you use; extras are isolated so installing one does not pull in others.
  • LangGraph support – First-class support for LangGraph with:
    • AgentBaseMemoryEvents – A BaseCheckpointSaver that persists LangGraph checkpoints as events in AgentBase Memory.
    • AgentBaseMemoryRecords – A BaseStore that saves chat messages as conversational events and retrieves memories via semantic search (embedding and processing run in AgentBase Memory).

Requirements

Installation

Base package (AgentBase only; no framework adaptors):

pip install greennode-agent-bridge

With LangGraph support:

pip install "greennode-agent-bridge[langgraph]"

Other extras (e.g. CrewAI) may be added in future releases. Installing one extra does not install packages from other extras.

Usage

LangGraph checkpoint and store

When the [langgraph] extra is installed, you can use AgentBase Memory as a checkpoint saver and as a store for conversation and memory:

from greennode_agent_bridge import AgentBaseMemoryEvents, AgentBaseMemoryRecords

# Checkpoint saver for LangGraph (persists graph state to AgentBase Memory)
checkpointer = AgentBaseMemoryEvents(
    memory_id="your-memory-id",
    # optional: memory_client=client,
)

# Store for chat messages and semantic memory (saves events, retrieves via AgentBase)
store = AgentBaseMemoryRecords(
    memory_id="your-memory-id",
)

# Use with your LangGraph graph
# graph = ... .compile(checkpointer=checkpointer)
# app with store for memory operations

Configure memory_id (and optionally credentials/client) according to your AgentBase Memory setup.

Without optional dependencies

If you import LangGraph types without installing the [langgraph] extra, the package raises an error that tells you to install greennode-agent-bridge[langgraph].

Development

With uv:

uv sync --group dev --group build
uv run ruff check src
uv run pytest

License

Apache-2.0. See LICENSE for details.

Links

Metadata

Release files for greennode-agent-bridge 1.0.5

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for greennode-agent-bridge 1.0.5
File Size Uploaded
greennode_agent_bridge-1.0.5.tar.gz 154.2 kB Details

Built distribution (wheel)

Table of built distributions (wheels) for greennode-agent-bridge 1.0.5
File Interpreter ABI Platform
greennode_agent_bridge-1.0.5-py3-none-any.whl Python 3 none any Details

Total release size: 176.8 kB

Release files / greennode_agent_bridge-1.0.5.tar.gz

Download URL greennode_agent_bridge-1.0.5.tar.gz
Size 154.2 kB
Tags Source
SHA-256 checksum
How to use checksums
2f63ee53ae239c6d2850545076a383854ec949e1cc31f69bf6ab94c0877aa4d7
BLAKE2b-256 checksum
How to use checksums
a37e288c1bf6d886164ea1d9e7a077ab1faa87cbbcab9f544425aabb90147657
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via twine/6.1.0 CPython/3.13.7

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

PyPI Publish Attestation

PyPI verified that this artifact, at this checksum, originated from the publisher listed below.

Signed by GitHub Actions, verified by PyPI on Mar 24, 2026.

Transparency log

Release files / greennode_agent_bridge-1.0.5-py3-none-any.whl

Download URL greennode_agent_bridge-1.0.5-py3-none-any.whl
Size 22.7 kB
Tags Python 3
SHA-256 checksum
How to use checksums
074bbeade89cdd9a09e5c36a169c2ba18fd2de0dd5e448e5491534c114d71094
BLAKE2b-256 checksum
How to use checksums
58bcce98dd59f49128881baef6719382f9cf952869a05f3507022accdafb81db
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via twine/6.1.0 CPython/3.13.7

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

PyPI Publish Attestation

PyPI verified that this artifact, at this checksum, originated from the publisher listed below.

Signed by GitHub Actions, verified by PyPI on Mar 24, 2026.

Transparency log
Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page