- tracing: turn off FastAPI's native tracing on Agent Engine (87e5399)
Agent Development Kit (ADK) by Google
Google's open-source, code-first toolkit for building, evaluating and deploying AI agents, with SDKs for Python, TypeScript, Go, Java and Kotlin.
Use it in: API / SDK Works with: MCP Local models Multi-agent
On this page
Usage data: latest readings Nov 17 to Nov 19, 2026, last checked Nov 19, 06:26 UTC. Date of each number
What Agent Development Kit (ADK) does
Agent Development Kit (ADK) is a vendor agent SDK from Google, first released in April 2025. You use it through a Python library, a TypeScript library, a Go library, a Java library and a Kotlin library. Its documentation covers MCP servers, subagents or parallel agents and local models. It can run models from Google, Anthropic and any OpenAI-compatible endpoint. It is used from Python, TypeScript, Java and Go. It is free and open source (Apache-2.0); you pay only for the models it calls.
Key facts
| Maker | |
|---|---|
| Type | Vendor agent SDK |
| First released | April 2025 |
| License | Apache-2.0 |
| Interfaces | Python library, TypeScript library, Go library, Java library, Kotlin library |
| Main language | Python |
| Open issues and PRs | 546 |
Pricing
Agent Development Kit (ADK) is open source and free to use; you pay only for the models and infrastructure it runs on.
Checked Oct 14, 2026. Prices change often; confirm before you buy.
Quick answers
- Free to start?Yes
- Open source?Yes (Apache-2.0)
- Where you use itPython library, TypeScript library, Go library, Java library, Kotlin library
- Supports MCP?Yes
- Model providersgoogle, anthropic, any OpenAI-compatible, local
- Subagents / multi-agent?Yes
- Feature comparisonAll agents
- Closest alternativeLangChain · all alternatives
What's new in Agent Development Kit (ADK): November 2026 so far
November brought stability to execution environments and sandboxes, along with new evaluation capabilities for running multiple test iterations. File handling was improved to work more efficiently with large files.
- Execution environments (LocalEnvironment, E2BEnvironment, DaytonaEnvironment) are now stable and ready for production use.
- Files are now streamed in chunks, allowing tools to read specific line ranges without loading entire files into memory.
- Evaluation runs can now execute multiple times concurrently and combine results across runs.
- Container code execution supports input and output files, with skill scripts running from validated paths instead of shell command strings.
2 releases this month · summarised from the official release notes · all months
AgentGid articles about Agent Development Kit (ADK)
Best AI Agent Frameworks in 2026: LangGraph, CrewAI, OpenAI Agents SDK and More
The AI agent frameworks developers actually use, ranked on live downloads and GitHub data, with a plain guide to which one fits Python, TypeScript, multi-agent or Microsoft-stack work.
How to Build an AI Agent: No-Code Builders, Frameworks and SDKs
A practical guide to building your first AI agent: choosing between no-code builders, open-source frameworks and model vendors' SDKs, the core agent loop, tools, guardrails and testing, with live usage data for each option.
Get started with Agent Development Kit (ADK)
| npm | npm install @google/adk |
|---|---|
| PyPI | pip install google-adk |
These commands use the packages tracked on this page. The vendor may recommend a different installer; see the official documentation.
What Agent Development Kit (ADK) users report right now
Fixed Users report that ADK's two ways of migrating old v0 session databases read event timestamps differently, so the same database migrated through each path ends up with times shifted by the host's UTC offset. A maintainer says a merged pull request fixed it; the thread does not name a release.
Reported on GitHub · 1 👍
The most discussed problems in its GitHub repository, checked Nov 12, 2026. Written by AgentGid in its own words; statuses and fix versions come from the project's own pages. Reports are users' accounts, not AgentGid tests.
Add-ons for Agent Development Kit (ADK): save tokens, add memory and tools
LiteLLM
One gateway for 100+ models with spend tracking, budgets, rate limits and fallbacks.
Langfuse
Traces every model and tool call with its cost and latency, and runs evaluations.
Firecrawl
Turns websites into clean Markdown or structured data the agent can read.
E2B
Runs agent-written code in isolated cloud sandboxes instead of on your machine.
Composio
Connects the agent to 1,000+ apps and APIs with managed sign-in.
Mem0
Adds long-term memory, so the agent remembers users and past work across sessions.
Listed because each tool documents support for Agent Development Kit (ADK) or for agent frameworks in general. Savings and results depend on your workload.
Agent Development Kit (ADK) alternatives
Best Agent Development Kit (ADK) alternatives compared · All agent frameworks and SDKs
| # | Agent | Gid Score | Downloads 7d | 7d | 30d | Stars | Latest release | Price | |||
|---|---|---|---|---|---|---|---|---|---|---|---|
| 1 |
LangChainLangChain |
79 | 41.1M | up 5.7% | down 2.7% | 150K+76/day | 1.5.22d ago | Free (OSS) | |||
| 2 |
LangGraphLangChain |
75 | 20.1M | up 5.5% | up 29.2% | 45.1K+48/day | 1.2.23yesterday | Free (OSS) | |||
| 3 |
AI SDKVercel |
68 | 47.2M | up 3.9% | up 38.4% | 28.1K+30/day | 7.0.1772d ago | Free (OSS) | |||
| 4 |
Claude Agent SDKAnthropic |
64 | 29.3M | up 5.9% | up 37.6% | 8,588+9/day | 0.2.185yesterday | Free (OSS) | |||
| 5 |
MastraMastra |
63 | 3.7M | up 14.9% | up 49.9% | 29.6K+23/day | 1.84.02d ago | Free (OSS) | |||
| 6 |
OpenAI Agents SDKOpenAI |
62 | 7.2M | up 4.8% | up 38.9% | 30.8K+21/day | 0.25.02d ago | Free (OSS) | |||
Head to head: Agent Development Kit (ADK) vs LangGraph
Tools used with Agent Development Kit (ADK)
What 350 public GitHub projects that depend on Agent Development Kit (ADK) use with it, from their dependency files.
- python-dotenv49.4%
- Google GenAI Python SDK39.7%
- FastAPI38.6%
- Uvicorn36.9%
- Pydantic34.3%
- Requests24.9%
- TypeScript22.3%
- Model Context Protocol SDK (Python)22.0%
- Google Cloud AI Platform21.4%
- Zod18.3%
Used far more often here than in AI-built projects overall: what sets Agent Development Kit (ADK) projects apart.
- Google Cloud Secret Manager10.9% · 169.8×
- Google Cloud AI Platform21.4% · 121.8×
- Google Cloud BigQuery10.9% · 113.2×
- Google Cloud Storage (Python)15.4% · 80.4×
- graphviz9.7% · 60.8×
- LiteLLM18.0% · 31.3×
- gRPC8.9% · 25.2×
- Authlib10.3% · 24.7×
Ratings from people who use Agent Development Kit (ADK)
No ratings yet. Used Agent Development Kit (ADK)? Rate it and say what it is good and bad at.
Agent Development Kit (ADK) news
-
Agent Development Kit (ADK) 2.14.1 released
tracing: turn off FastAPI's native tracing on Agent Engine (87e5399)
-
Agent Development Kit (ADK) 2.14.0 released
Execution environments and sandboxes; BaseEnvironment, LocalEnvironment, EnvironmentToolset, DaytonaEnvironment, and E2BEnvironment are now stable. (c54b253, 799fc94); BaseEnvironment.read_file_stream streams files in chunks across LocalEnvironment…
What changed: recent Agent Development Kit (ADK) releases
11 stable releases in the last 90 days · Monthly summary · Full changelog
- Execution environments and sandboxes
- BaseEnvironment, LocalEnvironment, EnvironmentToolset, DaytonaEnvironment, and E2BEnvironment are now stable. (c54b253, 799fc94)
- BaseEnvironment.read_file_stream streams files in chunks across LocalEnvironment, E2BEnvironment, and DaytonaEnvironment so ReadFileTool reads line ranges without loading the whole file into memory.
- AgentEngineEnvironment reads and writes large files in chunks and reports commands over 570 seconds as timed out before the service deadline. See the unit guide and sample for more details.
- ContainerCodeExecutor supports input and output files, and RunSkillScriptTool runs skill scripts from validated paths and arguments instead of a shell command string. (effd641, ff61524)
- Evaluation
Earlier releases
- Stability: Access 12 mature experimental features now promoted to stable status. See the unit guide for more details. (ea298d4)
- Classifiers: Route workflows with TypeSafe's Jev models via the new TypesafeClassifier and ClassifierNode. Jev returns calibrated probabilities in a single forward pass, much faster than an LLM.
- Live Audio: Enable natural real-time voice interactions with barge-in support alongside Gemini speech-to-text and text-to-speech integration. See the unit guide for more details. (2e7ef92)
- MongoDB Sessions & Memory: Persist sessions in MongoDB and share them across runner replicas with the new MongoDbSessionService.
- MongoDB: Deploy MongoDbToolset to Agent Engine without packaging your connection string, and let Atlas Automated Embedding embed search queries server-side, with no Google embedding call or…
- Performance: Enjoy up to 8x faster execution turns for string-model agents and reduced event-loading overhead. (772f139)
- Performance: Cut time to first model request by 40% in long sessions. (1754b3e)
- Tools: Intercept and filter tool outputs before returning them to the model using after_tool_callback. (fdda17c)
- Workflows: Require human confirmation before executing workflow nodes via require_confirmation. (988fd1a)
- Deployment: Deploy agents to Agent Engine using dedicated custom service accounts. (629e119)
- Python 3.15: Install and run ADK on Python 3.15. (75aef1e)
- add --state_file option to adk run (c390266), closes #7083
- Execution cancellation: Pass an abort_signal to Runner, Workflow, and nodes to stop a run gracefully; /run_sse now cancels the run when the client disconnects. See the unit guide for more details.
- Tool confirmation in workflows: Tool nodes now pause for user approval via RequestInput, the same way an LlmAgent does, instead of passing an error downstream. (ce132b9)
- ModelConsultTool: Let an agent consult another model mid-task, capped by per-turn and per-session budgets. See the unit guide for more details. (84cc99a)
- SQLite memory service: Keep agent memory in a local SQLite database, selected with a sqlite:// memory service URI. (9625b06)
- MCP SDK 2.x: Connect to MCP servers over the modern protocol through a new opt-in path. (e738c26)
- add a sample preloading memory profiles into the instruction (fdf1b7f)
- Skills: Control resource usage and tool persistence dynamically using new ephemeral lifecycles and active skill limits (experimental; enable with ADK_ENABLE_SKILL_LIFECYCLE=1). (43b73e4)
- Database Integrations: Perform high-performance vector and hybrid searches seamlessly within your agent flows with the new MongoDB toolset. (0961ced)
- Evaluation: Optimize agent execution costs and latency with new evaluation metrics for tracking duration, token consumption, and model call counts. (2d428ea)
- Model Support: Integrate OpenAI reasoning models more effectively with automated request parameter adaptation and precise reasoning token reporting. (52a2f0f)
- BigQuery protected write mode now runs a non-SELECT statement only when the dry run places it in the session's anonymous dataset, so multi-statement scripts, CALL, EXPORT DATA and other statements…
- BigQuery protected mode keeps its BigQuery session in process memory instead of session state, so its temporary tables do not survive a restart or carry over to another replica. (094012b)
Agent Development Kit (ADK) prices over time
Agent Development Kit (ADK) popularity and usage data
Agent Development Kit (ADK) was downloaded 3.1M times from npm and PyPI in the week ending Nov 17, 2026, up 5.2% on the week before and up 12.9% over the last 30 days compared with the 30 before. The GitHub repository has 22.3K stars, 393 of them added in the last 30 days. The latest stable release is 2.14.1, published Nov 12, 2026; there were 3 stable releases in the past 30 days. It was mentioned in 7 Hacker News posts and comments over the last 30 days.
Download the raw daily series: google-adk.csv
Gid Score breakdown
Gid Score shows public popularity and activity (usage, GitHub stars, mentions, growth), not the quality of the product. Each component is scored 0 to 100 from public signals; a dash means no data for it. How the Gid Score works.
How fresh these numbers are
| Number | Latest reading | Last checked |
|---|---|---|
| Package downloads | Nov 17, 2026 | Nov 19, 06:24 UTC |
| GitHub stars | Nov 19, 2026 | Nov 19, 06:26 UTC |
| Hacker News mentions | Nov 18, 2026 | Nov 19, 06:26 UTC |
We fetch every source once a day. Registries publish downloads and page views a day or two late, so their latest reading trails the check. A reading more than 4 days old is marked out of date; the Gid Score still uses it until a newer one arrives.
Agent Development Kit (ADK) FAQ
How much does Agent Development Kit (ADK) cost?
Agent Development Kit (ADK) is open source and free to use; you pay only for the models and infrastructure it runs on.
Is Agent Development Kit (ADK) open source?
Yes. Agent Development Kit (ADK) is open source, released under the Apache-2.0 license.
How popular is Agent Development Kit (ADK)?
Agent Development Kit (ADK) was downloaded 3.1M times from npm and PyPI in the week ending Nov 17, 2026, up 5.2% on the week before and up 12.9% over the last 30 days compared with the 30 before. The GitHub repository has 22.3K stars, 393 of them added in the last 30 days. The latest stable release is 2.14.1, published Nov 12, 2026; there were 3 stable releases in the past 30 days.
What is the latest version of Agent Development Kit (ADK)?
The latest stable release we track is 2.14.1, published on Nov 12, 2026.
What are the alternatives to Agent Development Kit (ADK)?
The closest alternatives in the same category by Gid Score are LangChain, LangGraph, AI SDK, Claude Agent SDK.
For the makers of Agent Development Kit (ADK) badges, corrections
Add a live badge to your README or site:
[](https://agentgid.com/agents/google-adk/)
[](https://agentgid.com/agents/google-adk/)
[](https://agentgid.com/agents/google-adk/)
Something wrong or outdated on this page? Send a correction with a link to the official source. More for makers.
Where these numbers come from
npm: @google/adk. PyPI: google-adk. GitHub: google/adk-python. See data sources for how each one is collected.