tmc/langchaingo

LangChain for Go, the easiest way to write LLM-based programs in Go

What it solves

It provides a way for developers to build applications powered by Large Language Models (LLMs) using the Go programming language, bringing the composability patterns of the LangChain ecosystem to the Go environment.

How it works

It acts as a Go implementation of the LangChain framework, allowing developers to integrate LLMs (such as OpenAI, Gemini, or local models via Ollama) into their software by providing a structured way to generate completions from prompts.

Who it’s for

Go developers who want to build AI-powered applications without switching to Python or JavaScript.

Highlights

  • Support for multiple LLM providers including OpenAI, Gemini, and Ollama.
  • Focus on composability for building complex LLM workflows.
  • Comprehensive API reference and community-driven development.

Related

  • Project
    jaredpalmer/kev

    Kev is a family of small, specialized decision models that provide calibrated, structured outputs for classification and scoring tasks, designed as an open-source, self-hostable alternative to proprietary decision-model APIs.

  • Project
    spring-projects/spring-ai

    A Spring-friendly API and abstraction layer for Java developers to integrate various AI models and vector stores into enterprise applications with portability and modularity.

  • Project
    funstory-ai/BabelDOC

    BabelDOC is an open‑source Python tool that translates PDF scientific papers using LLMs (OpenAI‑compatible models) and outputs bilingual PDFs. It offers a CLI, a Python API, extensive PDF‑handling options, glossary support, offline asset packaging, and can be run locally or via a hosted beta service.

  • Project
    yihong0618/bilingual_book_maker

    A versatile AI-powered tool that translates books and documents into bilingual versions by leveraging various LLMs and translation services while preserving original file formatting.