{
    "products": [
        {
            "slug": "google-adk",
            "name": "Agent Development Kit (ADK)",
            "kind": "resource",
            "website": "https://adk.dev/",
            "page": "https://listme.name/software/google-adk",
            "tagline": "Open-source code-first toolkit for building and deploying agents",
            "summary": "Agent Development Kit is an Apache-2.0 framework from Google for building agents in code, with Python, TypeScript, Go, Java and Kotlin versions. It runs on your own infrastructure or deploys to Google Cloud through Agent Runtime, Cloud Run or GKE.",
            "developer": "Google",
            "platforms": [
                "cli",
                "windows",
                "macos",
                "linux"
            ],
            "pricing": "open-source",
            "price_note": "Apache-2.0 framework is free to use and self-host",
            "free_to_use": true,
            "open_source": true,
            "license": "Apache-2.0",
            "source": "https://github.com/google/adk-python",
            "strengths": [
                "Apache-2.0 license with an active repository",
                "Code-first agents with a built-in web interface",
                "Same framework in Python, TypeScript, Go and Java"
            ],
            "limits": [
                "Deployment shortcuts point mainly to Google Cloud",
                "Hosted model access is billed by the provider"
            ],
            "checked": "2026-10-10",
            "connected_to_publisher": false,
            "overview": "ADK lets developers define agent logic, tools and orchestration in code, then run the agent locally with the ADK Web interface. The project's documentation names Python as the main SDK and links ADK Java, ADK Kotlin, ADK Go and ADK TypeScript. The license is Apache-2.0, and the Python source is on GitHub.\n\nDeployment is either self-managed in a container or a single command to Google Cloud. The Google Cloud options named on the site are Agent Runtime, Cloud Run and GKE, with managed infrastructure and Cloud Trace observability. Models can come from hosted services, including Google Cloud. Teams already on Google Cloud get the shortest path, and teams that want a graph-based runtime may compare LangGraph in this ranking."
        },
        {
            "slug": "llamaindex",
            "name": "LlamaIndex",
            "kind": "resource",
            "website": "https://www.llamaindex.ai/",
            "page": "https://listme.name/software/llamaindex",
            "tagline": "MIT-licensed framework for document-based and agentic AI apps",
            "summary": "LlamaIndex is an MIT-licensed open-source framework for building document-based and agentic AI applications. Its company also sells LlamaParse, a document parsing service that can be used with the framework or alone.",
            "developer": "LlamaIndex",
            "platforms": [
                "self-hosted"
            ],
            "pricing": "open-source",
            "price_note": "MIT-licensed framework is free; LlamaParse is a separate service",
            "free_to_use": true,
            "open_source": true,
            "license": "MIT",
            "source": "https://github.com/run-llama/llama_index",
            "strengths": [
                "MIT licensed with source on GitHub",
                "Focus on document and data workflows",
                "Separate parsing service available"
            ],
            "limits": [
                "Parsing service is a separate product to evaluate",
                "Narrower agent focus than general orchestration frameworks"
            ],
            "checked": "2026-10-10",
            "connected_to_publisher": false,
            "overview": "LlamaIndex is an open-source framework for connecting language models to documents and data, and for building agentic applications around them. Its repository describes the project as a document processing platform for AI and releases it under the MIT license.\n\nThe framework is free to use. LlamaParse, the company's document parsing product, is offered separately and can be used on its own as well as with the framework. Compared with LangChain, LlamaIndex centers more on documents and retrieval, although both support agents. Teams with heavy document ingestion may find its parsing tools a natural fit."
        }
    ],
    "differences": [
        "Only Agent Development Kit (ADK) runs on Windows.",
        "Only Agent Development Kit (ADK) runs on macOS.",
        "Only Agent Development Kit (ADK) runs on Linux."
    ],
    "shared_rankings": [
        {
            "list": "ai-agent-tooling",
            "name": "AI agent frameworks and tooling",
            "page": "https://listme.name/best/ai-agent-tooling",
            "of": 12,
            "results": [
                {
                    "product": "google-adk",
                    "rank": 5,
                    "score": 85.5,
                    "verdict": "Apache-2.0 code-first toolkit from Google with Python, TypeScript, Go and Java versions and a built-in web interface. Its deployment shortcuts point mainly to Google Cloud, so it fits teams already there.",
                    "best_for": "Agents built in code and deployed to Google Cloud",
                    "spec": {
                        "language": "Python, TypeScript, Go and Java",
                        "agent_style": "Code-first agents with a web interface",
                        "hosted_service": "Agent Runtime on Google Cloud"
                    }
                },
                {
                    "product": "llamaindex",
                    "rank": 3,
                    "score": 88,
                    "verdict": "The strongest focus on documents and retrieval, with an MIT-licensed framework and a separate parsing service. It is narrower for general agent work than LangChain.",
                    "best_for": "Agents that work over documents and data",
                    "spec": {
                        "language": "Not listed",
                        "agent_style": "Document-centric agents",
                        "hosted_service": "LlamaParse, separate"
                    }
                }
            ]
        }
    ],
    "ranks_higher_in_closest_shared_list": "llamaindex",
    "page": "https://listme.name/compare/google-adk-vs-llamaindex",
    "json": "https://listme.name/api/v1/compare/google-adk-vs-llamaindex.json",
    "notes": [
        "Scores are editorial and only comparable inside one list. Products with connected_to_publisher true receive a disclosed ranking lift: https://listme.name/methodology"
    ],
    "source": "https://listme.name",
    "license": "Free to read and cite with attribution to listme.name.",
    "docs": "https://listme.name/developers"
}