Benchmark LangGraph, Strands, OpenAI Agents, and Google ADK on the same agent graph

Published June 9, 2026

by Scarlett Attensil

Agent framework debates are mostly vibes. One engineer swears LangGraph is faster, another prefers the OpenAI Agents SDK, someone wants Google ADK because it feels future-proof. The team picks one, wires the workflow into its SDK, and the choice is welded in. Changing frameworks later means tearing out the wiring for one SDK and rebuilding the workflow on another, an expensive rewrite few teams take on.

This tutorial makes that decision reversible and then settles it with data. You put the agent graph in LaunchDarkly and run four frameworks (LangGraph, Strands, OpenAI Agents SDK, and Google ADK) over the same topology, with the model pinned so the framework is the only variable. A LaunchDarkly experiment ranks them on graph latency and token use, with an LLM judge guarding quality. The results table tells you which framework runs your graph fastest without degrading it.

This tutorial is the sequel to Compare AI orchestrators, which ran the same workflow across frameworks but kept the topology in each framework’s code. Here, the topology, routing, models, prompts, tools, and judge all live in LaunchDarkly, and each framework supplies only two functions.

The experiment results do more than set a benchmark. The flag that splits experiment traffic also routes production. When one framework wins, you don’t rewrite the app; you change the flag to serve the winner. In a single loop, LaunchDarkly does three jobs: the graph definition, the experiment split, and the runtime control that ships the winner.

The workload is a research-gap analysis over a set of arXiv papers. Two readers, approach-analyzer and contradiction-detector, read the same papers in parallel and fan in to gap-synthesizer, which writes the report.

Prerequisites

• A LaunchDarkly account with AgentControl access, and your environment’s SDK key
• Python 3.11+ and uv
• An ANTHROPIC_API_KEY for the pinned model. OPENAI_API_KEY and GOOGLE_API_KEY are only needed if you run the optional native-model bake-off in Step 9
• The companion repo: ai-orchestrators on branch tutorial/graph-experiments

The experiment design

The comparison is controlled: same graph, same model, same papers, same judge, with the framework as the only variable. Mechanically it runs in four stages:

1. Bootstrap. manifest.yaml creates the node configs, graph, orchestrator flag, and judge in LaunchDarkly.
2. Route. On each request, the app evaluates the orchestrator flag to pick a framework: langgraph, strands, openai-agents, or google-adk.
3. Run. The dispatcher runs the shared graph as a directed acyclic graph (DAG). The two readers run concurrently and fan in to the synthesizer.
4. Measure. Each run records how long the graph took, how many tokens it used, and whether the report passed the quality judge.

The shape looks like this:

                        ┌──▶  approach-analyzer  ───────┐
   intake (papers) ─────┤                               ├──▶  gap-synthesizer  ──▶  report
                        └──▶  contradiction-detector  ──┘

Step 1: Create the graph, flag, and judge

Everything starts from one file, config/graph_experiment_manifest.yaml. It declares the fetch_paper tool, four node configs (intake plus the three agents, pinned to claude-sonnet-4-5), the graph, the orchestrator flag, and the judge.

First, clone the companion repo and install its dependencies with uv:

$
git clone https://github.com/launchdarkly-labs/ai-orchestrators
$
cd ai-orchestrators
$
git checkout tutorial/graph-experiments
$
uv sync

Next, set up a LaunchDarkly project. The bootstrap doesn’t create one, so create it with the LaunchDarkly MCP server, the projects agent skill, or the UI. Name it graph-experiments to match the value in .env.example, so the defaults work without edits. When it exists, copy its key into LD_PROJECT_KEY and its production environment SDK key into LD_SDK_KEY in .env. The runners and experiment harness use that SDK key to evaluate the flag and graph. The bootstrap also reads LD_API_KEY from .env to create the resources.

Copy the example file to create your .env:

$
cp .env.example .env   # then set LD_PROJECT_KEY, LD_SDK_KEY, and LD_API_KEY in .env

With the keys in place, run the bootstrap:

$
uv run python scripts/launchdarkly/bootstrap.py config/graph_experiment_manifest.yaml

This creates all four node configs, the research-gap-graph, the orchestrator flag (created off), and the gap-quality-judge attached to the gap-synthesizer node (its synthesizer-claude variation, set to 100% sampling). The judge scores the final report against the source papers, so it can verify grounding and citations. A judge can only check based on the information it has, so we give it the papers, not only an upstream agent’s analysis.

When the graph ships, it is incomplete by design. The bootstrap creates the contradiction-detector config but wires only intake to approach-analyzer to gap-synthesizer, leaving the detector out. You’ll add it in Step 5 to complete the parallel fan-in.

When it finishes, the bootstrap prints a link to your new agent graph. Open it and review the topology before moving on. The graph shows a straight line from intake to approach-analyzer to gap-synthesizer, with contradiction-detector created but not yet wired in.

Step 2: The dispatcher runs the graph

The dispatcher is the heart of the project, and it’s the same code for every framework. It reads the graph as a DAG, runs the entry nodes concurrently, hands every node the papers as ground truth, and connects the readers at the fan-in node. The only framework-specific pieces are build_agent and invoke, which are passed in as arguments.

The whole process is about 100 lines, built on the agent graph traversal methods in the SDK. The complete dispatcher.py is in the companion repo.

The dispatcher carries the design in four parts: it builds the execution plan from the graph’s edges, composes each node’s input, runs every ready node concurrently each round, and records the graph’s metrics once per run.

First, the dispatcher builds the execution plan from the graph’s edges, so the topology you draw in LaunchDarkly runs:

1
for key, node in nodes.items():
2
    for edge in node.get_edges():
3
        target = edge.target_config
4
        if target in nodes:
5
            succ[key].append(target)
6
            preds[target].append(key)

Next, every node receives the source papers and any upstream analyses, so each agent and the judge work directly from the source material rather than a summary handed down a chain:

1
def compose_input(user_input, predecessor_outputs):
2
    parts = [f"=== SOURCE PAPERS ===\n{user_input}"]
3
    for key, out in predecessor_outputs:
4
        if out and out.strip():
5
            parts.append(f"=== {key} ===\n{out}")
6
    return "\n\n".join(parts)

Then each round runs every node whose predecessors have finished, concurrently, so the two readers fan out and fan in with no special casing:

1
ready = [k for k in pending if all(p in done for p in preds[k])]
2
results = await asyncio.gather(*(run_node(k) for k in ready))

Finally, the dispatcher records the graph’s metrics on each run, including the end-to-end latency the experiment ranks on:

1
graph_tracker.track_duration(int((time.monotonic() - start) * 1000))
2
graph_tracker.track_total_tokens(TokenUsage(input=totals["in"], output=totals["out"], total=totals["in"] + totals["out"]))
3
graph_tracker.track_path(path)
4
graph_tracker.track_invocation_success()

The dispatcher reads the topology at runtime, so reshaping the workflow in the UI, adding a node, or redrawing an edge takes effect on the next request with no code change. You’ll do exactly that in Step 5.

Step 3: Each framework is a thin adapter

Each framework implements build_agent(node_key, config, instructions) and async invoke(agent, input_text, tracker). Everything dynamic still comes from the LaunchDarkly node config: the model, the attached tools, and the instructions.

LangGraph has a LaunchDarkly companion package, so its runner is only a few lines. The companion handles model creation, tool binding, and token tracking, so the adapter holds no framework plumbing of its own:

1
def build_agent(node_key, config, instructions):
2
    llm = create_langchain_model(config)
3
    tools = build_tools(config, TOOL_REGISTRY)  # binds only this node's attached tools
4
    return create_react_agent(llm, tools, prompt=instructions)
5
6
async def invoke(agent, input_text, tracker):
7
    result = await tracker.track_metrics_of_async(
8
        lambda res: LDAIMetrics(success=True, tokens=sum_token_usage_from_messages(res.get("messages", []))),
9
        lambda: agent.ainvoke({"messages": [{"role": "user", "content": input_text}]}),
10
    )
11
    messages = result.get("messages", [])
12
    for message in messages:
13
        for name in get_tool_calls_from_response(message):
14
            tracker.track_tool_call(name)
15
    text = _content_to_text(messages[-1].content) if messages else ""
16
    return text, sum_token_usage_from_messages(messages)

Strands has no companion package, so its runner builds the model with a small provider-aware factory and binds tools with Strands’ native @tool. The contract is identical:

1
def build_agent(node_key, config, instructions):
2
    return Agent(
3
        name=node_key,
4
        model=_create_strands_model(config),
5
        system_prompt=instructions or "Process the input and respond.",
6
        tools=_bind_tools(config),
7
        callback_handler=None,
8
    )

OpenAI Agents and Google ADK round out the four. For the comparison to stay fair, all four have to run the same model, but these two SDKs default to their own vendors’ models. LiteLLM, a thin adapter, lets them call any provider, so we point both at the pinned claude-sonnet-4-5 and keep the model identical across all four orchestrators. No OpenAI or Google servers are involved. Instead, LiteLLM translates the request format in process and the call goes straight to Anthropic with your key.

Google ADK is fully companion-free, and OpenAI Agents uses the ldai_openai companion for token and tool-call telemetry even though it builds the model through LiteLLM. This experiment pins one model across all four frameworks, so every framework here runs Claude. Pointing each framework at its own vendor’s default model instead is a separate, optional exercise, the native-model bake-off in Step 9. The tool callables live in TOOL_REGISTRY, a plain {name: callable} map that each framework binds its own way.

Step 4: Smoke test the graph

Before you run any experiment, confirm the bootstrapped graph runs end to end. First, run one framework:

$
uv run python orchestrators/verify_run.py langgraph

It prints the path it took and the first part of the report. On the graph as it shipped, the path is intake to approach-analyzer to gap-synthesizer: intake runs its short pass, approach-analyzer reads the papers, and gap-synthesizer writes the report. There’s no contradiction-detector yet, and no error. The metrics land in the AgentControl UI under the graph you created.

Step 5: Add the parallel fan-in in the UI

Here’s the payoff of keeping the topology in LaunchDarkly: you finish building the workflow in the UI, with no redeploy, and the running app picks up the new shape on its next request. The contradiction-detector config already exists, with its fetch_paper tool attached. You wire it into the graph to add the second reader and form the parallel fan-in.

To complete the graph:

1. Click Agents in the LaunchDarkly sidebar.
2. Click Agent graphs.
3. Select research-gap-graph.
4. Add the contradiction-detector node.
5. Draw an edge from intake to contradiction-detector, then another from contradiction-detector to gap-synthesizer.
6. Click Save.

You add no routing logic: the edge itself is the route, because routing is structural.

Re-run the smoke test:

$
uv run python orchestrators/verify_run.py langgraph

The path now includes contradiction-detector, and because approach-analyzer and contradiction-detector run concurrently, their order can vary. You completed a multi-agent workflow from the UI, and the config you wired in already had its tool attached.

You finished a multi-agent workflow from the UI, mid-development, and the dispatcher ran the new shape on the next request. No redeploy, no code change: the graph you draw is the graph that runs.

Step 6: Smoke test all four frameworks

Before you collect experiment data, make sure all four frameworks can run the completed graph. One command runs all four in sequence:

$
uv run python orchestrators/verify_run.py all

It runs each framework against the completed graph and ends with a pass/fail summary, one line per framework, exiting non-zero if any framework failed, so it works as a gate. Each framework prints the path it took and a preview of its report, then a final summary collects the results. A successful run looks like this:

▶ Running 'langgraph' over 2 papers on graph 'research-gap-graph'...
  ✓ PATH : intake -> contradiction-detector -> approach-analyzer -> gap-synthesizer
▶ Running 'strands' over 2 papers on graph 'research-gap-graph'...
  ✓ PATH : intake -> contradiction-detector -> approach-analyzer -> gap-synthesizer
▶ Running 'openai-agents' over 2 papers on graph 'research-gap-graph'...
  ✓ PATH : intake -> contradiction-detector -> approach-analyzer -> gap-synthesizer
▶ Running 'google-adk' over 2 papers on graph 'research-gap-graph'...
  ✓ PATH : intake -> contradiction-detector -> approach-analyzer -> gap-synthesizer
=== smoke summary ===
  ✓ langgraph
  ✓ strands
  ✓ openai-agents
  ✓ google-adk

If a framework fails, its line shows an X instead of a checkmark and the command exits non-zero. All four frameworks smoke test against the pinned Claude model. ANTHROPIC_API_KEY is the only model key you need, because OpenAI Agents and Google ADK reach Claude through LiteLLM. The OpenAI Agents SDK turns on tracing by default and looks for OPENAI_API_KEY to export traces, so the openai-agents run may print a harmless tracing warning when that key is absent. It doesn’t affect the run.

Step 7: Run it through the experiment

Now you can use a LaunchDarkly experiment to rank the four frameworks on real traffic, on the same graph, with the model held constant. Because the model is fixed, the comparison is operational: which orchestrator delivers the model’s quality fastest, with the least token overhead. The bootstrap already created the flag, the judge, and the graph.

These metrics are measured on each request, so do a one-time setup first:

• Make the request context kind available for experiments.
• Set the analysis unit of graph latency, tokens, and the judge metric to request.

Then create the experiment in the UI:

1. Create an experiment with the orchestrator flag as the treatment.
2. Set the primary metric to Graph latency ($ld:ai:graph:duration:total, the time for a complete graph execution).
3. Add tokens and $ld:ai:judge:gap-quality as secondary metrics.
4. Set the audience to 100% and the randomization unit to request. Each run is a single request, there are no users in this workflow, and request is the unit LaunchDarkly measures AI and graph metrics by.
5. Turn on the orchestrator flag, which the bootstrap created set to off, so it serves the experiment’s variations.
6. Start an experiment iteration.

We rank on latency and tokens because, with the model and the graph held constant, those are the things that genuinely differ: a framework can move quality only by degrading the plumbing, like a truncated report or a broken tool call. So $ld:ai:judge:gap-quality stays a guardrail that catches a framework “winning” by cutting corners, not part of the ranking. Swap the model, prompt, or tools later instead of the framework, and that same judge becomes your primary metric.

Then drive traffic. The flag assigns each run one framework at random:

$
uv run python scripts/run_experiment.py --runs-per-category 6

That’s six runs over each of the six shipped topics, 36 in total. Assignment is random, so it usually fills all four variations, though it isn’t guaranteed. Each run analyzes the topic’s entire paper set, because gap analysis needs every paper to find real gaps.

Open the experiment in LaunchDarkly: latency per variation, with tokens and $ld:ai:judge:gap-quality alongside. The winner is the framework with the best latency and lowest token use that doesn’t let quality slip. Because the model is pinned, cost is a fixed multiple of tokens, so the token column is also the cost ranking; for actual dollar figures, read them from Insights.

Because the experiment holds everything but the framework constant, most of these bars land close, often within a few percent, which is by design.

In our run, Strands won on speed: it ran the graph fastest, with quality holding at the guardrail. If you optimize for speed and quality holds, that makes Strands the orchestrator to ship for this workload. Six topics and one randomized split isn’t a large sample, so confirm the lead with more topics before you standardize on it. You can do that in Step 9.

Step 8: Ship the winner with runtime control

The experiment gave you data. The reason to run it in LaunchDarkly, rather than a one-off script, is that acting on that data takes no deploy: the orchestrator flag that was the experiment treatment is also your production router.

When a variation wins, stop the iteration and set the flag’s default to that framework. Every request routes to it on the next evaluation, with no redeploy.

Then automate what you don’t want to babysit. An adaptive trigger watches a guardrail and changes a flag on its own when production drifts past it. The orchestrator you shipped is operational and won’t degrade by itself, so point the trigger at the model flag from Step 9: it fails over to a backup model when your primary provider has a bad day, the same guardrail driving a different flag. That closes the loop: experiment to find the winner, runtime control to ship it, and automation to keep it healthy.

Step 9: Extend the experiment

Tighten the bands by adding more topics. Confidence comes from more distinct topics, not more runs over the same few. Download one with a title-phrase (ti:) query, and the harness picks it up automatically on the next run:

$
uv run python scripts/download_papers.py --query 'ti:"LLM-as-a-judge"'

Make quality the headline by flipping a config, not a flag. The framework lives in the orchestrator flag because it is app-level routing, not a property of any agent. The model, the prompt, and the tool set are different: they live in the node configs, so you experiment on the config itself. Add a second variation to a node, such as gap-synthesizer with a stronger model or a tightened prompt, and run an experiment with that config as the treatment and its variations as the arms. Pin the framework by setting the orchestrator flag to one value and leave the graph alone, so the config is the only thing moving. The judge attached to the synthesizer already emits $ld:ai:judge:gap-quality, so quality is the primary metric with no new instrumentation. Now it genuinely moves, because a different model or prompt reasons differently about the same papers.

Experiment on the graph shape with a graph-key flag. The dispatcher takes the graph key as an argument, so the shape is another value you can put behind a flag:

1
graph_key = ld.variation("graph_shape", context, "research-gap-graph")
2
result = await execute_graph(ai_client, graph_key, context, user_input, build_agent, invoke)

Build two graphs with different keys: for example, a linear research-gap-graph-linear (intake to approach-analyzer to gap-synthesizer) against the parallel research-gap-graph, or one with an added critic node against one without. Make a multivariate graph_shape flag whose variations are those graph keys, evaluate it exactly as the app evaluates orchestrator, and set it as the experiment treatment with the framework and model held constant. You are measuring whether the extra structure earns its latency and quality, and because the dispatcher runs whatever shape the key resolves to, no runner or dispatcher code changes. You build the judge once, and it is the guardrail for the framework bake-off and the headline metric for every model, prompt, tool, and shape you test next.

Run a native-model bake-off. This experiment holds the model constant so the framework is the only variable. To compare each framework on its own default model instead, build separate node configs per framework. This is the optional bake-off the prerequisites mention. It’s a follow-up beyond this walkthrough, and the only part that needs OPENAI_API_KEY and GOOGLE_API_KEY.

Whatever you flip, follow three rules:

1. Change one variable at a time (the framework, the model, or the shape), never two. If you change more than one, you can’t attribute the win.
2. Keep the quality guardrail on every run, because the fastest variant is often the one that quietly truncated its report or dropped a tool call.
3. Earn confidence with distinct inputs, not repeats: a tight band around three repeated topics is still a tight band around the wrong number.

To learn more about judge design, read When to add online evals and Evaluating with LLM-as-judge evaluators. To add a pre-production regression layer, read Offline evaluation of RAG-grounded answers.

Recap and next steps

Framework choice doesn’t have to be a one-way door. Put the topology in a LaunchDarkly agent graph, have each framework supply only build_agent and invoke, and let one experiment settle a question that usually gets answered by whoever argues hardest: pin the model, let the judge guard quality, and pick the orchestrator that delivers it fastest, with evidence in hand.

Then keep going, because the framework is only the first swappable component. The same flag, experiment, and judge machinery compares models, prompts, tools, and whole graph shapes the same way, so “which is better” stops being a debate and becomes a measurement. And because the experiment and the runtime control are one flag, you never stop at a finding: you ship it, ramp it with a progressive rollout, and let an adaptive trigger hold the line in production while the AI iteration loop for reliable agents keeps the next change shipping behind eval gates.

The complete code is in the sample repo. Get started with AgentControl, point the four frameworks at a graph your team actually runs, and settle the next framework argument with a number instead of a hunch.