georgeguimaraes/arcana

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

Build interactive AI agents in Elixir with OTP supervision, middleware composition, human-in-the-loop approvals, sub-agent delegation, and real-time Phoenix LiveView integration. Built on LangChain.

Structured outputs, vectorization and tool calling for your Ash application

Production-ready RAG Framework (Python/FastAPI). 1-line config swaps: 6 Vector DBs (Weaviate, Pinecone, Qdrant, ChromaDB, pgvector, MongoDB), 5 LLMs (Gemini, OpenAI, Claude, Ollama, OpenRouter). OpenAI-compatible API. 2100+ tests.

Elixir runtime for AI agents that live inside your app and get things done by writing code

pgvector support for Elixir

Claude Code plugin for Elixir/Phoenix/LiveView — 26 specialist agents, Iron Laws enforcement, and Tidewave MCP integration. Plan features with parallel research agents, execute with automatic verification, review with 4-agent parallel audits, and capture learnings as reusable knowledge.

Torus bridges Ecto and PostgreSQL, simplifying building search queries.

Korvus is a search SDK that unifies the entire RAG pipeline in a single database query. Built on top of Postgres with bindings for Python, JavaScript, Rust and C.