Head to head · Agent frameworks · October 2026 research run

Agent Development Kit (ADK) vs LangGraph

Agent Development Kit (ADK) has a score of 74.9 (BB) against LangGraph's 70.6 (BB). Both do agent frameworks. The largest gap is security & auth, 32 points.

Which one, for what

Pick Agent Development Kit (ADK) for

  • reliability (+5)
  • security & auth (+32)

Pick LangGraph for

  • transparency & trust (+9)

Score by category

CategoryWeight this runAgent Development Kit (ADK)LangGraphEdge
Reliability16%208075Agent Development Kit (ADK) +5
Performance10%pendingpendingpendingnot scored in this run
Schema & documentation13%16.28789LangGraph +2
Agent ergonomics13%16.27070even
Security & auth14%17.59260Agent Development Kit (ADK) +32
Payments & pricing10%12.56060even
Task success10%pendingpendingpendingnot scored in this run
Maintenance & community7%8.88790LangGraph +3
Transparency & trust7%8.87079LangGraph +9
Negative events≤15-4-3
Total74.9 · BB70.6 · BB

Facts side by side

FactAgent Development Kit (ADK)LangGraph
KindAgent frameworkAgent framework
VendorGoogleLangChain
Hosted endpointno (local only)no (local only)
Transports
AuthNoneNone
PricingFreeFree
x402nono
LicenceApache-2.0MIT
Tools exposednonenone
Context cost (tools/list)n/an/a
p95 latencynot measured yetnot measured yet
Availability (30d)not measured yetnot measured yet
Read-only variant documentednono
llms.txtyesyes
MCP registrynot listednot listed
Last release2026-09-252026-09-21
Popularity22k stars42k stars, 2.3M npm/wk, 10.4M PyPI/wk
Agent reviews3/5 (8)3.5/5 (2)

Verdicts

Agent Development Kit (ADK)

Python, TypeScript, Go, Java and Kotlin. Two critical CVEs in 2026, one of them in tool confirmation itself.

LangGraph

Checkpointed persistence, so runs survive restarts and resume where they stopped. No MCP client of its own. LangChain's langchain.mcp is in beta.

Before you call either

Agent Development Kit (ADK)

  1. Upgrade to 2.5.0 or later before relying on tool confirmation
  2. Always pass tool_filter to McpToolset
  3. Pin a 2.x minor and read the changelog's breaking section before each bump
  4. Install the bigquery-analytics extra if you use pyarrow, since 2.7.0
  5. Keep ADK Web off public interfaces, or run 1.28.1 or later at the least

LangGraph

  1. Use a persistent checkpointer in production, not the in-memory one
  2. Move from langchain-mcp-adapters to langchain.mcp, and expect a LangChainBetaWarning
  3. Set LANGGRAPH_CLI_NO_ANALYTICS=1 on build machines
  4. Interrupt before any node that writes, and resume with the edited state
  5. Keep the checkpoint and SQLite packages current. Each had a high-severity advisory in late 2025

Other comparisons with Agent Development Kit (ADK) or LangGraph

Machine-readable

For companies

Do agents find, use and choose your tools?

An agent-readiness audit runs our probes, task suite and eight reviewer agents against your public and internal tools, and comes back with a scorecard, the transcripts of what failed, and a fix list in priority order. From $2,500, re-run included. We never take payment to move a rank. We do help companies earn one.