eino
The ultimate LLM/AI application development framework in Go.
What is eino?
The ultimate LLM/AI application development framework in Go.
Overview of eino
What it is
Eino is an LLM application development framework written in Go. It draws inspiration from LangChain, Google ADK, and other open-source frameworks, and is designed to follow Go conventions. The framework provides reusable components such as ChatModel, Tool, Retriever, and ChatTemplate, with official implementations for providers like OpenAI and Ollama. It also includes an Agent Development Kit (ADK) for building AI agents with tool use, multi-agent coordination, context management, and interrupt/resume capabilities. Additionally, Eino supports composition, allowing components to be connected into graphs and workflows that can run standalone or be exposed as tools for agents.
Key features
- Component Ecosystem: Defines component abstractions (ChatModel, Tool, Retriever, Embedding, etc.) with official implementations for OpenAI, Claude, Gemini, Ark, Ollama, Elasticsearch, and more.
- Stream Processing: Automatically handles streaming throughout orchestration, including concatenating, boxing, merging, and copying streams as data flows between nodes.
- Callback Aspects: Allows injection of logging, tracing, and metrics at fixed points (OnStart, OnEnd, OnError, etc.) across components, graphs, and agents.
- Interrupt/Resume: Any agent or tool can pause execution for human input and resume from checkpoint, with state persistence and routing handled by the framework.
Use cases
Eino can be used to build conversational AI agents that use tools to perform actions. It supports multi-agent coordination for complex tasks, where a DeepAgent can delegate to sub-agents and track progress. The composition feature enables creation of deterministic workflows, such as data processing pipelines, which can then be exposed as tools for agents. The interrupt/resume capability allows for human-in-the-loop interactions.
Getting started
See the repository README for installation and quick start instructions. A minimal example of creating a ChatModelAgent is shown below: Go chatModel, _ := openai.NewChatModel(ctx, &openai.ChatModelConfig{ Model: 'gpt-4o', APIKey: os.Getenv('OPENAI_API_KEY'), }) agent, _ := adk.NewChatModelAgent(ctx, &adk.ChatModelAgentConfig{ Model: chatModel, }) runner := adk.NewRunner(ctx, adk.RunnerConfig{Agent: agent}) iter := runner.Query(ctx, 'Hello, who are you?') for { event, ok := iter.Next() if !ok { break } fmt.Println(event.Message.Content) }
License and pricing
This project is licensed under the Apache-2.0 License. It is open source and free to use.
Based on the project's public README and repository metadata.