brainlid/langchain

Elixir implementation of a LangChain style framework that lets Elixir projects integrate with and leverage LLMs.

What it solves

Elixir LangChain provides a framework for Elixir applications to integrate Large Language Models (LLMs) and connect them to external data sources and application logic. It simplifies the process of "chaining" different services, libraries, and functions together to create data-aware and agentic applications.

How it works

The library uses a modular system of components and pre-built "chains" to manage interactions with LLMs. The central module, LLMChain, coordinates the flow of messages and tool execution. It supports a wide array of providers including OpenAI, Anthropic, Google Gemini, xAI Grok, and local models via Ollama or Bumblebee. A key feature is the LangChain.Function, which allows developers to expose specific Elixir functions as tools that the LLM can call to interact with the application's internal data or perform actions.

Who it’s for

Developers using the Elixir programming language who want to build AI-powered applications, agents, or tools that leverage both cloud-based and self-hosted language models.

Highlights

  • Extensive Provider Support: Integrates with numerous services including AWS Bedrock Mantle, Cloudflare Workers AI, DeepSeek, and Mistral.
  • Agentic Capabilities: Enables LLMs to interact with their environment through custom Elixir functions.
  • Multi-modal Support: Handles messages containing text, images, files, and "thinking" blocks.
  • Trajectory Tracking: Includes LangChain.Trajectory to capture and evaluate the sequence of tool calls for debugging and performance optimization.
  • Prompt Caching: Supports prefix-based prompt caching for providers like ChatGPT, Claude, and DeepSeek to reduce costs and latency.

Related

  • Project
    agentjido/req_llm

    A unified Elixir library that standardizes interactions with over 1,200 LLM models across 22 providers, offering a consistent interface for text, image, and audio generation tasks.

  • Project
    langchain-ai/langchain

    A framework for building agents and LLM-powered applications that simplifies development through interoperable components and a vast library of third-party integrations.

  • Project
    browser-use/browser-use

    Browser Use is an open‑source Python/TypeScript library that gives LLM agents full control over a real or cloud‑hosted web browser. It provides 31 browser actions as tools, supports custom functions, works with OpenAI, Anthropic, Google models or its own BU2 model, and offers three usage modes: a fully hosted cloud API, a CLI for existing agents, and a library you embed in your code. Ideal for automating web tasks, building AI assistants that browse, or researching LLM‑driven web navigation.

  • Project
    SciSharp/BotSharp

    An open-source .NET framework for building AI bot platforms that allows enterprise developers to integrate LLMs and multi-agent systems into business applications.

  • Project
    ahyatt/llm

    An Emacs Lisp library that provides a unified interface for interacting with various LLM providers, enabling developers to build AI-powered packages that work across different models.