BeamWeaver – LangChain/DeepAgents-style agents and workflows for Elixir
LangChain for Elixir with OTP supervision — useful if you're already on BEAM.
From-scratch OTP-native Elixir implementation of LangChain, LangGraph, and Deep Agents concepts
LangChain for Elixir teams who refuse to spin up Python services for agents.
Elixir developers building AI applications
LangChain · LangGraph · DeepAgents
We build agents in Elixir. We kept running into the same issue and found there is no observability for agentic systems.
We decided to take the best aspects of LangChain, LangGraph, and DeepAgents and put them into Elixir.
BeamWeaver comes with an OTP-native design and: - agents and tool calling - graph workflows - checkpoints and resumable execution - memory stores - retries, fallbacks, interrupts, and human review - typed streaming events - provider adapters for OpenAI, Anthropic, Google Gemini, xAI, and Moonshot/Kimi - fake/replay models for deterministic tests
We're also building observability on top of it through WeaveScope, which we'll release very soon.
BeamWeaver gives Elixir teams the tools needed to build advanced agentic systems without pushing the hard parts into Python services.
LangChain for Elixir with OTP supervision — useful if you're already on BEAM.
OTP supervisor trees mapping to agent workflows is genuinely clever, but early-stage and GitHub Copilot-only.
First Elixir↔WASM bridge tooling, but no maintained packages existed for a reason.
LangChain alternative with 2 dependencies and async-native architecture from the start.
Quoracle forces you to stop trusting one model and instead runs every decision through an explicit consensus pipeline, with per-model conversation history persisted to Postgres and a LiveView dashboard for realtime inspection. Agents can spawn children recursively and communicate via messages, which makes it a neat sandbox for studying emergent behaviors or building robust multi-model workflows — heavy, opinionated, and clearly aimed at folks who want to experiment rather than ship a lightweight chatbot.
Quoracle actually does something interesting: it queries a pool of models and only executes actions they agree on, while letting agents spawn children and persist full state to Postgres — all visible in a LiveView dashboard. The per-model conversation history, recursive hierarchy, and explicit consensus pipeline are clever touches; it’s clearly aimed at experimentation rather than drop-in production use (the README even flags security and deployment caveats).