ADK: Python framework for building AI agents
Modular Python framework for building production AI agents.
Learn more about ADK
ADK is a Python framework designed for building AI agents using code-first principles. It provides modular components for defining agent logic, integrating tools, and orchestrating multi-agent workflows, with support for both Gemini and other language models. The framework includes pre-built tools, custom function integration, OpenAPI specification support, and tool confirmation flows for human-in-the-loop execution. Agents can be deployed to Cloud Run, Vertex AI Agent Engine, or containerized environments, and the framework supports agent-to-agent communication through the A2A protocol.
Code-first architecture
Agent logic, tools, and orchestration are defined directly in Python, enabling version control, testing, and direct code manipulation rather than configuration-based approaches.
Tool ecosystem integration
Supports multiple tool sources including pre-built tools, custom Python functions, OpenAPI specifications, and MCP tools, with tight integration for Google services.
Multi-agent composition
Enables building scalable systems by composing multiple specialized agents into hierarchies, with support for agent-to-agent communication via the A2A protocol.
from google import adk
agent = adk.LlmAgent(
model="gemini-2.0-flash-exp",
system_instruction="You are a helpful coding assistant."
)
response = agent.run("How do I reverse a list in Python?")
print(response.text)Restores deprecated eval endpoint for web compatibility and updates UI components.
- –Add back deprecated eval endpoint for web until we migrate
- –Update eval dialog colors, and fix a2ui component types
Major UI overhaul with consolidated event view, enhanced accessibility, and A2UI integration.
- –Breaking: Make credential manager accept `toolcontext` instead of `callbackcontext`
- –Consolidated Event View: Replaced Event tab with click-to-expand interaction on message rows
- –Enhanced Accessibility: Added full support for arrow-key navigation
- –Rich Developer Tooling: Introduced detailed tooltips for function calls
- –A2UI Integration: Integrated A2UI v0.8 standard catalog for native UI components in chat
Adds automatic session creation, OpenTelemetry tracing, and removes experimental decorators.
- –Breaking: Use OpenTelemetry for BigQuery plugin tracing, replacing custom `ContextVar` implementation
- –Add support to automatically create a session if one does not exist
- –Remove `@experimental` decorator from `AgentEngineSandboxCodeExecutor`
- –Add `--disable_features` CLI option to override default feature enable state
- –Add `oteltocloud` flag to `adk deploy agent_engine` command
See how people are using ADK
Related Repositories
Discover similar tools and frameworks used by developers
Heretic
Tool that removes safety alignment from transformer language models using directional ablation without post-training.
Ultralytics YOLO
PyTorch library for YOLO-based real-time computer vision.
vLLM
Fast, memory-efficient LLM inference engine with PagedAttention for production deployments at scale.
DeepSpeed
PyTorch library for training billion-parameter models efficiently.
Chart-GPT
AI tool that generates charts from natural language text descriptions.