AgentMemory vs Google Agent Development Kit (ADK)

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

	AgentMemory Agents	Google Agent Development Kit (ADK) Agents
Tagline	Open-source persistent memory runtime for AI coding agents, with hybrid retrieval and zero external dependencies.	Google's open-source framework for building, evaluating, and deploying production AI agents
Category	Agents	Agents
Pricing	Free· Free, open-source (Apache 2.0); bring your own LLM API key	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).
Model	Multi-model (Claude, Gemini, MiniMax, OpenRouter)	Gemini (default) plus Claude, GPT-4/5, Llama, and other providers via LiteLLM
Editorial score	7.3 / 10	—
Use cases	agent-memorycoding-agentscontext-managementknowledge-graphmcp-server	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
Pros	Zero external infrastructure: single Node process, JSON on disk Triple-stream retrieval (BM25 + vectors + graph) with sub-20ms recall Native plugins for Claude Code, Cursor, Cline, Windsurf, and 15+ agents Apache 2.0, runs on your existing LLM subscription Strong benchmark numbers (95.2% R@5 on LongMemEval-S)	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
Cons	Pre-1.0 (v0.9.27), expect breaking changes Single-process JSON storage may not scale to team-wide deployments Self-hosted only; you operate the runtime Effectiveness depends on the LLM provider you wire in	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
Website	agent-memory.dev	google.github.io

Pick AgentMemory if

✅ Zero external infrastructure: single Node process, JSON on disk
✅ Triple-stream retrieval (BM25 + vectors + graph) with sub-20ms recall
✅ Native plugins for Claude Code, Cursor, Cline, Windsurf, and 15+ agents
✅ Apache 2.0, runs on your existing LLM subscription

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

Compare a different pair →