
Write HTML. Render video. Built for agents.
ADK Go is a modular framework for building agent applications in Go. It covers agent orchestration, tool use, memory, artifacts, model adapters, and authentication so you can assemble and run agent workflows in one codebase.

Builders who want to create and ship agent workflows in Go.
You can build agent systems with reusable Go packages instead of wiring everything from scratch.
Defines agent logic and workflow control in `agent/`, including workflow and remote agent support.
Provides model packages under `model/` for Gemini, OpenAI, and other LLM integrations.
Includes `memory/` and `artifact/` packages for persisted context and generated files.
Adds `agentregistry/` for discovering and resolving agents, including MCP-related flows.
Supplies `auth/` and `platform/` utilities for credentials, execution, time, and UUID handling.
Ships `cmd/adkgo`, `cmd/launcher`, and `examples/` to show how the framework is used.
go get google.golang.org/adk/v2
Agent Development Kit (ADK) is a flexible and modular framework that applies software development principles to AI agent creation. It is designed to simplify building, deploying, and orchestrating agent workflows, from simple tasks to complex systems. While optimized for Gemini, ADK is model-agnostic, deployment-agnostic, and compatible with other frameworks.
This Go version of ADK is ideal for developers building cloud-native agent applications, leveraging Go's strengths in concurrency and performance.
To add ADK Go to your project, run:
go get google.golang.org/adk/v2
adk.dev/llms.txt is a machine-readable index of the ADK documentation, and adk.dev/llms-full.txt is the same documentation as a single file. Both are generated from adk-docs and include the Go API reference and samples, so you can point a coding agent at either one for context:
Plan and implement an agent that reviews customer issues and generates a report. Use the ADK Go framework, referring to https://adk.dev/llms-full.txt for sample code.
To work on this repository rather than build with it, see AGENTS.md.
This project is licensed under the Apache 2.0 License - see the LICENSE file for details.
The exception is internal/httprr - see its LICENSE file.
Sign in to join the discussion.
No comments yet. Be the first to say what this is good for.

Write HTML. Render video. Built for agents.
Ultra-lightweight, open-source, self-hosted personal AI agent framework in Python with WebUI, tools, memory, MCP, multi-agent workflows, automation, and chat apps
SkillOpt is a text-space optimizer that trains reusable natural-language skills for frozen LLM agents through trajectory-driven edits, validation-gated updates, and deployable best_skill.md artifacts.

Omnigent is an open-source AI agent framework and meta-harness: orchestrate Claude Code, Codex, Cursor, Pi, and custom agents โ swap harnesses without rewriting, enforce policies and sandboxing, and collaborate in real time from any device.
A theoretical reconstruction of the Claude Mythos architecture, built from first principles using the available research literature.
๐ท๏ธ An adaptive Web Scraping framework that handles everything from a single request to a full-scale crawl!