Elixir agents

Symphony turns project work into isolated, autonomous implementation runs, allowing teams to manage work instead of supervising coding agents.

🤖 Autonomous agent framework for Elixir. Built for distributed, autonomous behavior and dynamic workflows.

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

Bringing the power of the command line to chat

community-maintained OpenAI API Wrapper written in Elixir.

Open Agentic Schema Framework

Embeddable RAG library for Elixir/Phoenix with agentic pipelines and dashboard

An Elixir API for calling Node.js functions

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.

Community maintained Elixir library for OpenAI API

AI integration layer for Jido agents with LLM orchestration and reasoning strategies.

Structured outputs, vectorization and tool calling for your Ash application

What if AI agents could form teams as fluidly as humans? Spawn specialists in milliseconds, share discoveries in real-time, review each other's work, and remember everything across sessions. Watch it all unfold in a live mission control UI. Open source.

Demo web project using the Elixir LangChain library

Lux is an open-source framework for building multi-agent, swarmed intelligence built by Spectral Labs. With Beams, Prisms, Lenses, and Signals, it orchestrates AI-driven workflows to create truly autonomous organizations.

the extensible, customizable, self-documenting, real-time multi-agent computing environment

BEAM-native personal AI agent built on Elixir/OTP. Runs on your hardware. Your data stays yours.

Language Chain Library for Elixir

ChatGPT UI with auth, OpenAI, Claude, Gemini support, written in Elixir + LiveView

Auto-generated Elixir SDK for OpenAI APIs with full typespecs, docs and streaming support

Agent swarming organization system

Claude Agent SDK for Elixir – Build AI agents with Claude Code

Elixir-native framework for building runtime AI agents

BEAM-native coding agent for Elixir/OTP projects with TUI, web UI, eval, tools, memory, and subagents

Elixir library for lightweight AI agent orchestration inspired by openai/swarm

The full featured self-hosted Codex gateway, for teams, agents and you

The MVC framework for chat apps built on a platform designed for communication systems.

Elixir-native framework for building AI agents

Model-agnostic agent harness for Elixir

TRINITY in Elixir (An Evolved LLM Coordinator): route LLM calls via a small-model hidden-state router + Axon coordination head, with Thinker/Worker/Verifier orchestration and policy loop for acceptance-driven completion.

Write one app, render it to a terminal, a browser, or as agent tools. The terminal for your Gundam.

A persistent, local-first AI development daemon built in Elixir/OTP. AST-level code intelligence, Property Graph, runtime BEAM introspection, and semantic search — all via a 80+ endpoint REST API.

Your own self-evolving AI agent powered by Elixir/OTP

🔮 A smol coding agent in Elixir

UcxUcc is a simple but powerful team collaboration suite of applications designed to improve communications, information sharing and productivity for the businesses small and large.

Unofficial Anthropic API client for Elixir. Integrate Claude, Anthropic's powerful language model, into your applications.

Headless, declarative multi-agent orchestration framework with a domain-agnostic signal bus, workflow engine with Postgres persistence, and configurable agent runtime (ships code review domain).

Twitch Messaging Interface for Elixir.

Chatbot framework

Fnord is an AI code archaeologist.

Accessibility snapshot testing for Phoenix LiveView - capture HTML during tests, run Pa11y for WCAG compliance, debug with AI-friendly timeline analysis

OSA: the Optimal System Agent. One AI that maximizes signal, eliminates noise, and finds the optimal path — across code, work, and life. Elixir/OTP. Runs locally. Open-source OpenClaw alternative.

A WIP framework for developing cross-platform chatbots

Convert HTML to Markdown with Elixir

Elixir-native LangChain, LangGraph, and DeepAgents for traceable LLM apps: OTP workflows, tools, memory, human-in-the-loop, streaming, custom clients/adapters, minimal deps, and WeaveScope tracing.

A platform evolution of OpenAI Symphony (openai/symphony) for running Codex, Claude Code, CodeBuddy Code, and OpenCode from real project tasks.

Elixir framework for composing autonomous AI agent workflows.

ScoutAPM Elixir Agent. Supports Phoenix and other frameworks.

Porting Microsoft's Autogen library into Elixir

Multi-agent orchestration system built on Elixir/OTP. DAG workflows + mesh mode + real-time LiveView dashboards on local, docker , and kubernetes.

A bot for iMessage ([email protected]), Telegram (@ImSueBot), and Discord. Now in Elixir!

An Elixir SDK for Claude Code - provides programmatic access to Claude Code CLI with streaming message processing

Recursive agent orchestration with multi-LLM consensus

Composable multi-agent workflows and LLM orchestrators with human-in-the-loop, checkpointing, and OpenTelemetry observability

A demo Phoenix LiveView application showcasing the Sagents's multi-conversation agent architecture.

An abstraction library for building domain-specific intelligent agents based on Large Language Models (LLMs). LLMAgent provides a core architecture and behavior definitions that simplify the development of specialized agents by leveraging the AgentForge framework for dynamic workflow orchestration.

Bespoke agent-to-agent discovery and communication protocol

Single-binary LLM agent runtime built on Elixir/OTP: chat UI, 4-tier memory, Anthropic-compatible Skills, scheduled tasks, multi-provider LLM routing, and platform bots.

OpenAI Codex SDK written in Elixir

A modal text editor built for the age of AI agents — Neovim-style editing, Emacs-style runtime flexibility, powered by Elixir/BEAM and Zig

Developer-friendly LLM agent harness built on Jido and Jido AI

Create multi-agent workflows with AI and Language Models using OTP components in Elixir for reliable and scalable automation.

Elixir in memory VectorDB build with Rust using rustler! It's small, fast, efficient, simple!

Ankole is an open-source, self-hosted AgentOS for shared AI colleagues. Claude Tag open source alternative.

GPT powered slack bot for summarizing/acting on messages and threads, written in Elixir

Unofficial Facebook Messenger Platform *chatbot client* and *webhook handler*

Universal Elixir client for LLM APIs. Streaming text generation, tool use, and structured output.

BullX is an AgentOS for working side by side with self-directed AI Colleagues.

Elixir RAG library with multi-LLM routing (Gemini, Claude, OpenAI, Ollama), GraphRAG, knowledge graphs, modular retrievers/rerankers, composable pipelines, pgvector integration, advanced chunking, and tool-using agents. Fork of bitcrowd/rag.

Elixir framework for multi-model LLM councils. Debate, vote, tournament, synthesize. Provider-agnostic.

Elixir OpenAi Library with streaming support

Normalized Elixir protocol for CLI AI coding agent adapters.

RSS-powered album reviews aggregator + playlist.

OpenAI Codex CLI adapter for Jido.Harness.

Your personal AI, everywhere you are.

Multi-agent systems framework for the BEAM platform - build distributed autonomous agents with OTP supervision and fault tolerance

Agent Session Manager - A comprehensive Elixir library for managing AI agent sessions, state persistence, conversation context, and multi-agent orchestration workflows

a portable implementation + augmentation of the workflow described in The Ralph Wiggum Playbook, combined with a Skills-Driven Development closed-loop workflow.

Event stream query and flow control

A multi-human, multi-agent LiveView component for autogen

Pure-Elixir git: clone, fetch, push over smart HTTP v2 with lazy partial-clone and a path-oriented FS API for agents

Engram: Personal knowledge RAG system — Obsidian vault indexer, vector search, MCP server

A set of skills and workflows. Intended to allow autonomous writing of long-form fiction.

Ipsa cognitio fructus

Governed Model Gateway & Agentic Recording/Debugging Platform

Elixir implementation of GEPA: LLM-driven evolutionary optimization using Pareto-efficient search for text-based systems. Features OpenAI/Gemini integration, BEAM concurrency, OTP supervision, 218 tests with 75% coverage.

Batteries-included Elixir library for orchestrating OpenAI-compatible APIs with streaming, tool calling, and deterministic testing

Code Intelligence: Token-budgeted codebase context for Elixir agents. Solves context window limitations by providing a deterministic Elixir semantic graph and agent-ready Repo Map for LLMs.

Simulating society as it actually behaves: LLM-driven agents with memory, beliefs, and interactions grounded in real microdata.

An agent-based integrated development environment

Agent-Native Version Control for AI Swarms (CASM Architecture)

A *Claw clone that utilizes BeamAgent to allow for TOS compliant subscription based account usage. A cautionary tale proving that technical adherence to the letter of a request is the most effective way to subvert its intended restrictions. "Be careful what you wish for..."

Open-source DeepWiki alternative: AI-generated documentation and natural language Q&A for any Git repository.

Elixir-native semantic memory engine for agents: ETS working memory, durable recall, typed observations, mental models, scoped search, and reflection packets.

🏰 AI agents live autonomously in a blockchain-powered fantasy world. Fully open source — everyone can participate.

Desktop application for managing and orchestrating JIDO autonomous agents with a Conductor-style UI

Phoenix coordination server and embeddable Elixir client for augmented human-AI telepathy. Transforms multiplayer terminal chat into live, room-scoped structured context graphs and actionable consensus workflows.

Make your coding agent actually finish the job. Install one skill and Claude Code keeps working — planning, fixing, testing, deploying — until your goal is objectively true (tests pass, endpoint live, deployed), or it tells you why.