Comparisons / Google ADK vs LangGraph
Google ADK vs LangGraph: Which Agent Framework to Use?
Google's Agent Development Kit (ADK) is an open-source framework for building multi-agent systems. LangGraph is LangChain's stateful workflow framework — a graph of nodes (functions) connected by edges with shared state. Here is how they compare — paradigm, ecosystem, and the use cases each one is actually built for.
By the numbers
Google ADK
18.7k
3.2k
Python
Apache-2.0
2025-04-01
Google/Alphabet
Vertex AI
Yes
LangGraph
18.9k
3.4k
Python
MIT
2024-01-17
LangChain Inc (Harrison Chase)
Sequoia Capital, Benchmark
Part of LangChain Inc — $50M raised across A and B
8.2M
LangGraph Platform (hosted), LangSmith (observability)
Yes
Used by: Replit, Klarna, Elastic
github.com/langchain-ai/langgraph→GitHub stats as of April 2026. Stars indicate community interest, not necessarily quality or fit for your use case.
| Concept | Google ADK | LangGraph |
|---|---|---|
| Agent | `LlmAgent` class with model, instructions, and `sub_agents` list | A `StateGraph` with nodes, edges, and a typed `State` channel |
| Tools | `FunctionTool`, built-in tools (Search, Code Exec), third-party integrations | `ToolNode(tools)` paired with a conditional edge for routing |
| Agent Loop | `Runner.run()` with automatic tool dispatch and sub-agent delegation | — |
| Multi-Agent | Hierarchical agent tree with root agent delegating to specialized sub-agents | — |
| Workflows | `SequentialAgent`, `ParallelAgent`, `LoopAgent` workflow primitives | — |
| Session | Session and State service with typed channels and persistence | — |
| Loop | — | `add_conditional_edges` from a node back to itself until a `END` condition |
| State | — | Typed `State` channels with reducers (`Annotated[list, add_messages]`) |
| Checkpointing | — | `MemorySaver` / `PostgresSaver` persists state per `thread_id` |
| Human-in-loop | — | `interrupt_before` / `interrupt_after` pauses execution for review |
| Parallel fanout | — | Multiple edges from one node + reducers merge results |
Google ADK vs LangGraph, head to head
Google ADK Google's Agent Development Kit (ADK) is an open-source framework for building multi-agent systems.
LangGraph LangGraph is LangChain's stateful workflow framework — a graph of nodes (functions) connected by edges with shared state.
Both wrap the same underlying agent pattern — an LLM call, a tool dispatch, a loop — in different abstractions. The choice between them is mostly about which mental model and ecosystem fits the team you have, not which one is technically more capable.
Pick Google ADK if
Pick Google ADK if aDK earns its complexity when you need multi-agent orchestration on Google Cloud with Vertex AI deployment. If you're using Gemini and need production-grade agent infrastructure, it's well-designed. For single-agent use cases or non-Google stacks, plain Python keeps things simpler. Google ADK is the right fit when the tradeoffs in its intro line up with how your team actually wants to work day-to-day; LangGraph would force you to translate.
Pick LangGraph if
Pick LangGraph if langGraph earns its weight when your agent is a workflow — explicit branches, checkpoints, parallel branches, or a human approval gate. For a single-agent loop, the graph machinery is overkill and a plain while loop is faster to write, debug, and ship. LangGraph is the right fit when the tradeoffs in its intro line up with how your team actually wants to work day-to-day; Google ADK would force you to translate.
What both add
Both Google ADK and LangGraph pull in a class hierarchy and a dependency tree to wrap what is, at the core, an HTTP POST in a while loop. If your use case is straightforward — one provider, a handful of tools, a single agent — the framework cost may exceed the framework benefit. The lesson below shows the same pattern in ~60 lines without either dependency.
Or build your own in 60 lines
Both Google ADK and LangGraph implement the same 8 patterns. An agent is a function. Tools are a dict. The loop is a while loop. The whole thing composes in ~60 lines of Python.
No framework. No dependencies. No opinions. Just the code.
Build it from scratch →