Back to directory

Agent Development Kit (ADK)

A code-first Python framework for building, evaluating and deploying AI agents, optimized for Gemini but model- and deployment-agnostic, with sibling implementations in Java, Kotlin, Go and TypeScript.

Agent Development Kit (ADK)

Agent Development Kit (ADK) is a flexible, modular Python framework that applies software development principles to building AI agents, from simple tasks to complex multi-agent systems. It is optimized for Gemini but is model-agnostic, deployment-agnostic and compatible with other frameworks.

A graph-based workflow runtime composes deterministic execution flows with routing, fan-out and fan-in, loops, retries, state management, dynamic nodes, human-in-the-loop steps and nested workflows. A task API supports structured agent-to-agent delegation in multi-turn or single-turn modes, and multiple specialized agents can be composed into scalable hierarchies. Agent logic, tools and orchestration are defined directly in Python for testability and versioning, though an Agent Config feature can also build an agent without code, and a tool-confirmation flow lets a human approve tool execution.

It deploys to Cloud Run or scales with Vertex AI Agent Engine, installs with pip, requires Python 3.10 or newer, and is licensed under the Apache-2.0 license.

More in Agent frameworks

See all 902
  • Recurse

    recurse.run

    A serverless harness that lets a coding agent design, test, and deploy its own specialist sub-agents as tools, MCP servers, or bots, defined by a schema-validated manifest.

  • ProofForge

    shulgin.is-a.dev

    An AI-agent pipeline that decomposes a mathematics problem, proves each piece, and formalizes the result in Lean 4 and Mathlib until the Lean kernel accepts it, with six of its proofs already merged into Google DeepMind's formal-conjectures repository.

  • local-coder

    github.com

    Builds a local coding-agent team on top of Ollama and OpenCode by detecting the machine's hardware, recommending models for seven specialist roles, and testing whether each assigned model can actually use tools, edit a repository and pass verification.