Back to browse
GitHub Repository

From-scratch OTP-native Elixir implementation of LangChain, LangGraph, and Deep Agents concepts

31 starsElixir

BeamWeaver – LangChain/DeepAgents-style agents and workflows for Elixir

by caudena·Jun 19, 2026·1 point·0 comments

AI Analysis

●●SolidNiche GemShip It

LangChain for Elixir teams who refuse to spin up Python services for agents.

Strengths
  • OTP-native supervision trees ensure durable agent execution without external orchestrators.
  • Typed streaming events integrate cleanly with existing Elixir telemetry pipelines.
  • Fake replay models enable deterministic testing without burning API tokens.
Weaknesses
  • Promised WeaveScope observability tool is not yet released for production use.
  • Agent framework category is crowded with established Python and TypeScript alternatives.
Target Audience

Elixir developers building AI applications

Similar To

LangChain · LangGraph · DeepAgents

Post Description

Hi HN,

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.

Similar Projects

AI/ML●●Solid

Stop Using LangChain

LangChain alternative with 2 dependencies and async-native architecture from the start.

Big BrainSolve My Problem
aminau
302mo ago
AI/ML●●Solid

Quoracle, a recursive consensus-based multi-agent orchestrator (Elixir)

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.

WizardryNiche Gem
shelvick
114mo ago
AI/ML●●Solid

Quoracle: Self-replicating multi-LLM-consensus agents (Elixir)

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).

WizardryNiche Gem
shelvick
214mo ago