Google Agent Development Kit (ADK) vs mini-SWE-agent

A side-by-side look at pricing, capabilities, pros, cons, and our editorial scores.

	Google Agent Development Kit (ADK) Agents	mini-SWE-agent Agents
Tagline	Google's open-source framework for building, evaluating, and deploying production AI agents	A 100-line open-source coding agent that scores 74%+ on SWE-bench Verified.
Category	Agents	Agents
Pricing	Free· Framework itself is free and open-source (Apache 2.0). Costs come from the underlying model provider (e.g. Gemini API / Vertex AI usage) and any hosting infrastructure (Cloud Run, GKE, Agent Engine).	Free· Free and open source (Apache 2.0); you pay only for the underlying LLM tokens.
Model	Gemini (default) plus Claude, GPT-4/5, Llama, and other providers via LiteLLM	Multi-model (via litellm, OpenRouter, Portkey)
Editorial score	—	7.2 / 10
Use cases	Multi-agent research assistantCustomer support triage agentRAG chatbot backed by Vertex AI SearchCode review and refactoring agentBigQuery natural-language analytics agentDocument processing pipelineVoice/streaming conversational agentInternal tool-use agent orchestrating APIsEvaluation and regression testing of LLM workflowsEnterprise workflow automation on Agent Engine	swe-bench-evaluationautonomous-codingagent-researchbatch-inferenceagent-baseline
Pros	Genuinely open-source (Apache 2.0) with active Google engineering behind it, not a hosted-only product Multi-language: first-class Python, Java, and Go SDKs — rare among agent frameworks that are usually Python-only Built-in dev UI (`adk web`) with trace inspection, event stream, and session replay speeds up debugging enormously Model-agnostic via LiteLLM — Gemini is default but Claude, GPT, and local models plug in cleanly Rich multi-agent primitives out of the box: SequentialAgent, ParallelAgent, LoopAgent, and hierarchical sub-agents Tight Google Cloud integration for deployment (Cloud Run, GKE, Agent Engine) plus native BigQuery/Vertex Search tools Evaluation harness with trajectory-level scoring is included, not a separate paid add-on First-class MCP (Model Context Protocol) client and server support	Roughly 100 lines of Python — trivially readable and hackable Scores 74%+ on SWE-bench Verified despite the minimal design Model-agnostic via litellm, OpenRouter, and Portkey Sandbox-friendly: Docker, Podman, Singularity, Bubblewrap, local Apache 2.0; backed by the SWE-bench and SWE-agent authors
Cons	Documentation and examples lean heavily on Gemini + Google Cloud; non-Google paths work but feel like second-class citizens API surface is still evolving — breaking changes between minor versions have been common through 2025-2026 Multi-agent orchestration primitives are powerful but the graph/callback model has a real learning curve compared to a plain prompt loop Agent Engine deployment is convenient but locks you into GCP billing and quotas TypeScript/Kotlin support lags the Python SDK in features and community examples	No GUI, IDE integration, or hosted product Bash-only tool surface — no built-in browser, search, or planning tools You build your own ops layer (logging, cost caps, retries) Aimed at researchers more than day-to-day end users
Website	google.github.io	mini-swe-agent.com

Pick Google Agent Development Kit (ADK) if

✅ Genuinely open-source (Apache 2.0) with active Google engineering behind it, not a hosted-only product
✅ Multi-language: first-class Python, Java, and Go SDKs — rare among agent frameworks that are usually Python-only
✅ Built-in dev UI (`adk web`) with trace inspection, event stream, and session replay speeds up debugging enormously
✅ Model-agnostic via LiteLLM — Gemini is default but Claude, GPT, and local models plug in cleanly

Pick mini-SWE-agent if

✅ Roughly 100 lines of Python — trivially readable and hackable
✅ Scores 74%+ on SWE-bench Verified despite the minimal design
✅ Model-agnostic via litellm, OpenRouter, and Portkey
✅ Sandbox-friendly: Docker, Podman, Singularity, Bubblewrap, local

Compare a different pair →