KAgent LangGraph Integration

This package provides LangGraph integration for KAgent with A2A (Agent-to-Agent) server support.

Features

A2A Server Integration: Compatible with KAgent's Agent-to-Agent protocol
Event Streaming: Real-time streaming of graph execution events
FastAPI Integration: Ready-to-deploy web server for agent execution

Quick Start

from kagent.core import AsyncControllerClient, AsyncFileTokenProvider, KAgentConfig
from kagent.langgraph import KAgentApp
import os
import sqlite3
from langgraph.checkpoint.sqlite import SqliteSaver
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"]


config = KAgentConfig()
controller_client = AsyncControllerClient(
    config.grpc_url,
    agent_name=config.app_name,
    token_provider=AsyncFileTokenProvider(),
)

# Define and compile your graph
builder = StateGraph(State)
# Add nodes and edges...
checkpointer = SqliteSaver(
    sqlite3.connect(
        os.getenv("KAGENT_CHECKPOINT_DB", "/tmp/langgraph-checkpoints.sqlite"),
        check_same_thread=False,
    )
)
graph = builder.compile(checkpointer=checkpointer)

# Create KAgent app
app = KAgentApp(
    graph=graph,
    agent_card={
        "name": "my-langgraph-agent",
        "description": "A LangGraph agent with KAgent integration",
        "version": "0.1.0",
        "capabilities": {"streaming": True},
        "defaultInputModes": ["text"],
        "defaultOutputModes": ["text"],
    },
    config=config,
    controller_client=controller_client,
)

# Build FastAPI application
fastapi_app = app.build()

Architecture

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

LangGraphAgentExecutor: Executes LangGraph workflows within A2A protocol
KAgentApp: FastAPI application builder with A2A integration
Task Management: Automatic A2A task persistence through one shared authenticated gRPC channel

Configuration

Set both endpoints when running locally. A2A and MCP use KAGENT_GATEWAY_URL, while control-plane calls use KAGENT_API_URL.

export KAGENT_API_URL=http://localhost:8083
export KAGENT_GATEWAY_URL=http://localhost:8083
export KAGENT_NAME=my-agent
export KAGENT_NAMESPACE=default

Deployment

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

Metadata

Release files for kagent-langgraph 1.0.0a7

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

Source distribution (sdist)

Source distribution for kagent-langgraph 1.0.0a7
File	Size	Uploaded
kagent_langgraph-1.0.0a7.tar.gz	12.7 kB	Oct 1, 2026	Details

Built distribution (wheel)

Table of built distributions (wheels) for kagent-langgraph 1.0.0a7
File	Interpreter	ABI	Platform	Reset
kagent_langgraph-1.0.0a7-py3-none-any.whl 11.9 kB Oct 1, 2026	Python 3	none	any	Details

Total release size: 24.7 kB

Release files / kagent_langgraph-1.0.0a7.tar.gz

Download URL	kagent_langgraph-1.0.0a7.tar.gz
Size	12.7 kB
Tags	Source
SHA-256 checksum How to use checksums	`d1243f9156e797ee676a9d7c51f32d8fa5d76a4bcd34df1c011d66acc8a94a7b`
BLAKE2b-256 checksum How to use checksums	`68c3e6738f231014da615d2c3cb097b9769874b0dd14c62e848c33fb80c085a5`
Upload date	Oct 1, 2026
Uploaded using Trusted Publishing? What is trusted publishing?	No
Uploaded via	`uv/0.12.21 {"installer":{"name":"uv","version":"0.12.21","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":{"name":"Ubuntu","version":"24.04","id":"noble","libc":null},"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":true}`

Release files / kagent_langgraph-1.0.0a7-py3-none-any.whl

Download URL	kagent_langgraph-1.0.0a7-py3-none-any.whl
Size	11.9 kB
Tags	Python 3
SHA-256 checksum How to use checksums	`af9f73561b3880fb7b5c981c875ab19ed0df51d84da8d9c6ad09f695a184c08f`
BLAKE2b-256 checksum How to use checksums	`f4e115ea0abb5f32f7d116ec6b07850b7eb1992d1eccae19d4283656e7fd0c3f`
Upload date	Oct 1, 2026
Uploaded using Trusted Publishing? What is trusted publishing?	No
Uploaded via	`uv/0.12.21 {"installer":{"name":"uv","version":"0.12.21","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":{"name":"Ubuntu","version":"24.04","id":"noble","libc":null},"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":true}`