Skip to main content

LangGraph integration for KAgent with A2A server support

Project description

KAgent LangGraph Integration

This package provides LangGraph integration for KAgent with A2A (Agent-to-Agent) server support. It implements a custom checkpointer that persists LangGraph state to the KAgent REST API, enabling distributed agent execution with session persistence.

Features

  • Custom Checkpointer: Persists LangGraph checkpoints to KAgent via REST API
  • A2A Server Integration: Compatible with KAgent's Agent-to-Agent protocol
  • Session Management: Automatic session creation and state persistence
  • Event Streaming: Real-time streaming of graph execution events
  • FastAPI Integration: Ready-to-deploy web server for agent execution

Quick Start

from kagent_langgraph import KAgentApp
from langgraph.graph import StateGraph
from langchain_core.messages import BaseMessage
from typing import TypedDict, Annotated, Sequence

class State(TypedDict):
    messages: Annotated[Sequence[BaseMessage], "The conversation history"]

# Define your graph
builder = StateGraph(State)
# Add nodes and edges...

# Create KAgent app
app = KAgentApp(
    graph_builder=builder,
    agent_card={
        "name": "my-langgraph-agent",
        "description": "A LangGraph agent with KAgent integration",
        "version": "0.1.0",
        "capabilities": {"streaming": True},
        "defaultInputModes": ["text"],
        "defaultOutputModes": ["text"]
    },
    kagent_url="http://localhost:8080",
    app_name="my-agent"
)

# Build FastAPI application
fastapi_app = app.build()

Architecture

The package mirrors the structure of kagent-adk but uses LangGraph instead of Google's ADK:

  • KAgentCheckpointer: Custom checkpointer that stores graph state in KAgent sessions
  • LangGraphAgentExecutor: Executes LangGraph workflows within A2A protocol
  • KAgentApp: FastAPI application builder with A2A integration
  • Session Management: Automatic session lifecycle management via KAgent REST API

Configuration

The system uses the same REST API endpoints as the ADK integration:

  • POST /api/sessions - Create new sessions
  • GET /api/sessions/{id} - Retrieve session and events
  • POST /api/sessions/{id}/events - Append checkpoint events
  • POST /api/tasks - Task management

Deployment

Use the same deployment pattern as kagent-adk samples with Docker and Kubernetes.

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

kagent_langgraph-0.6.20.tar.gz (10.6 kB view details)

Uploaded Source

Built Distribution

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

kagent_langgraph-0.6.20-py3-none-any.whl (11.3 kB view details)

Uploaded Python 3

File details

Details for the file kagent_langgraph-0.6.20.tar.gz.

File metadata

  • Download URL: kagent_langgraph-0.6.20.tar.gz
  • Upload date:
  • Size: 10.6 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: uv/0.9.5

File hashes

Hashes for kagent_langgraph-0.6.20.tar.gz
Algorithm Hash digest
SHA256 6c330ee707a732dc09a592a0e495ef9b8a92f729e730dac5aee5f28225660669
MD5 1ae022d6c0a7fbe41cd75bf0c05e3aa7
BLAKE2b-256 7d20c30644a900489e03a00409eb0c5a143bb73f1f76a9665c3cf7d1440817cc

See more details on using hashes here.

File details

Details for the file kagent_langgraph-0.6.20-py3-none-any.whl.

File metadata

File hashes

Hashes for kagent_langgraph-0.6.20-py3-none-any.whl
Algorithm Hash digest
SHA256 3e45708c94b3ca092203433b7e7d3fd5759f5811579c5964c09e966b4ac59150
MD5 92558b53b4ea6228fb5327934d200769
BLAKE2b-256 c6e3c82511c4f0750b8bd711099d15476332a97deae5d5ff4d8ae732157e5c46

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