#45 · Primary category： LLM Application Frameworks
adk-go
An open-source, code-first Go toolkit for building, evaluating, and deploying sophisticated AI agents with flexibility and control.
Project last updated：08/28/26
GitHub Stars
8.7K
Forks
983
Contributors
86
License
Apache-2.0
Why we included this project
Go teams that want to build production AI agents directly in Go will find ADK for Go a natural fit. The framework is code-first: agent logic, tool wiring, and orchestration are all written in Go, so the same testing, versioning, and review practices that apply to a normal service carry over. It is modular enough to compose several specialized agents into one larger system, and the pre-built tool ecosystem plus MCP and A2A support handle external integrations without custom plumbing. Although it is tuned for Gemini and Vertex AI, the model-agnostic core keeps you free to switch providers. For teams deploying to Cloud Run or other concurrent environments, the toolkit leans on Go's strengths, making it a reasonable choice for growing from simple agents to multi-agent workflows.
Articles for this project
No articles for this project yet.
To suggest a topic or contribute an article, contact us.
Related projects in this category
langchain
The agent engineering platform.
dify
Build Agentic workflows, RAG pipelines, with rich AI model and tool support on one collaborative workspace. Deploy on cloud, VPC, or self-hosted, so teams move from prototype to production without rebuilding the stack.
headroom
Compress tool outputs, logs, files, and RAG chunks before they reach the LLM. 20% fewer tokens for coding agents, 60-95% fewer tokens for JSON, same answers. Library, proxy, MCP server.
litellm
The fastest, litest AI Gateway. Rust core with Python SDK. Call 100+ LLM APIs in OpenAI (or native) format with cost tracking, guardrails, load balancing, and logging [Bedrock, Azure, OpenAI, Anthropic, OpenAI, VertexAI, vLLM, Nvidia NIM]
llama_index
LlamaIndex is the leading document agent and OCR platform