cloudwego/eino-ext

Various extensions for the Eino framework: https://github.com/cloudwego/eino

Eino Extension (cloudwego/eino‑ext)

What it is

  • A collection of plug‑ins and helper libraries that extend the Eino framework, which is a CloudWeGo project for building LLM‑based applications.

What it provides

  • Component implementations – ready‑made code for the component types defined by Eino, such as:
    • ChatModel: adapters for OpenAI, Claude, Gemini, Ark, Ollama, etc.
    • Tool: integrations like Google Search, DuckDuckGo.
    • Retriever / Indexer: connectors for Elastic Search, Volc VikingDB.
    • Document Loader: readers for web URLs, Amazon S3, local files.
    • Document Transformer: utilities like HTMLSplitter, ScoreReranker.
    • Embedding: OpenAI, Ark, and others.
    • Lambda: e.g., a JSONMessageParser.
  • Callback handlers – implementations of Eino’s CallbackHandler interface, for example a Langfuse tracing handler.
  • DevOps tools – an IDE plugin that adds visual debugging, graph‑based workflow editing, and other UI aids for Eino projects.

Why it matters

  • Saves developers from writing boiler‑plate glue code for popular LLM services and data stores.
  • Keeps the ecosystem consistent: all extensions follow the same component contracts defined by Eino.
  • The IDE plugin makes it easier to design and debug complex LLM pipelines.

Typical use‑cases

  1. Rapid prototyping of a chatbot that uses OpenAI’s GPT model, searches the web via Google, and retrieves documents from Elastic Search.
  2. Production‑grade pipelines where you need reliable, tested connectors to storage (S3), vector stores (VikingDB), and tracing (Langfuse).
  3. Team collaboration where visual workflow editing in the IDE helps non‑engineers understand the LLM application flow.

Getting started

  1. Clone the repository and add it as a dependency to your Eino project (the README points to the official Eino docs for exact import instructions).
  2. Choose the component you need (e.g., ChatModel.OpenAI) and instantiate it according to the Eino component documentation.
  3. Optionally install the IDE plugin (details in the DevOps docs) to edit and debug your pipeline visually.

Documentation links

License

  • Apache‑2.0 (see LICENSE).

Security

  • Report any vulnerabilities privately to Bytedance Security via their security center or sec@bytedance.com.

Related

  • Project
    cloudwego/eino-examples

    A collection of practical examples and demonstrations for the Eino framework, covering AI agents, multi-agent orchestration, and RAG applications.

  • Project
    cloudwego/eino

    An LLM application development framework for Golang that provides tools for building AI agents, multi-agent coordination, and graph-based workflows.

  • Project
    brainlid/langchain

    A framework for Elixir applications to integrate LLMs and chain them with external data and custom functions to build agentic, data-aware AI applications.

  • Project
    Ingenimax/agent-sdk-go

    A Go SDK (and CLI) for building production‑ready AI agents with multi‑LLM support, persistent memory, tool integration, multi‑agent orchestration, guardrails, and enterprise features, configurable via environment variables or rich YAML files.

  • Project
    tryAGI/LangChain

    A C# implementation of the LangChain framework that enables .NET developers to build composable AI applications using LLMs, vector databases, and document loaders.