# brainlid/langchain

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

Repository: https://github.com/brainlid/langchain
Canonical: https://ross.abutalabs.com/products/brainlid-langchain
Homepage: https://hexdocs.pm/langchain/
Language: Elixir
License: NOASSERTION
License Family: other
Topics: chatgpt, elixir, langchain, llm, ai, anthropic, bumblebee, claude-ai
Last push: 2026-08-23T05:33:06+00:00

## Health v2 (maintenance only)
Score: 96/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 99, release rhythm 99, longevity 82
- inputs: {"age_days": 1148, "days_push": 10, "days_rel": 7, "gap_med": 6.0, "n_releases_24m": 47}
- flags: no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1196, forks 214 (observed 2026-08-28T04:03:57.238961+00:00)

## What it is
An Elixir framework for building LLM-powered applications, providing abstractions and integrations for chat models like OpenAI, Anthropic Claude, Google Gemini, Ollama, and self-hosted Bumblebee models. It supports chaining LLM interactions with data sources and agentic workflows within Elixir projects.

## Use cases
- integrate chatgpt into an elixir app
- build ai agents in elixir
- call anthropic claude from elixir
- run locally hosted llms with ollama in elixir
- chain llm calls with custom elixir functions
- build a chatbot backend in phoenix with llms

## When to choose
- you are building an Elixir or Phoenix application that needs LLM integration
- you want multi-provider chat model support behind a unified API
- you want agentic or chained LLM workflows in Elixir

## When to avoid
- your project is in Python, JavaScript, or another language with the official LangChain
- you need features like vector store integrations or document loaders not provided here
- you only need a simple raw HTTP client to one LLM provider

## Facets
- artifact type: framework
- maturity: active
- function: agent-framework, llm-inference, chatbot, rag, prompt-engineering, sdk
- domain: large-language-models, artificial-intelligence, chatbots, developer-tools
- platform: elixir, cross-platform
- tags: langchain, llm, openai, anthropic, claude, gemini, ollama, bumblebee, chat-models, elixir, ai-agents, retrieval-augmented-generation

## Member repositories
- brainlid/langchain (main) score 96

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:03:57.238961+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T06:22:01.525063+00:00, confidence not recorded.
  - readme: https://github.com/brainlid/langchain (fetched 2026-08-28T04:03:57.238961+00:00, sha eee81e67fdf4)
  - homepage: https://hexdocs.pm/langchain/ (fetched 2026-08-29T12:28:49.377304+00:00, sha 531b38a8cef7)
- Data as of 2026-08-30T08:39:29.467469+00:00.