{"id":97474,"url":"https://github.com/agentjido/awesome-elixir-ai","name":"awesome-elixir-ai","description":"Awesome List for the Elixir AI Collective","projects_count":48,"last_synced_at":"2026-07-29T04:00:18.320Z","repository":{"id":320935481,"uuid":"1083825120","full_name":"agentjido/awesome-elixir-ai","owner":"agentjido","description":"Awesome List for the Elixir AI Collective","archived":false,"fork":false,"pushed_at":"2026-06-08T12:21:44.000Z","size":23,"stargazers_count":25,"open_issues_count":3,"forks_count":6,"subscribers_count":4,"default_branch":"main","last_synced_at":"2026-07-10T04:03:37.029Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":null,"language":null,"has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/agentjido.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":"CONTRIBUTING.md","funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null,"notice":null,"maintainers":null,"copyright":null,"agents":"AGENTS.md","dco":null,"cla":null}},"created_at":"2025-10-26T19:32:34.000Z","updated_at":"2026-06-22T06:27:14.000Z","dependencies_parsed_at":null,"dependency_job_id":"115f9a78-712b-43a7-98eb-87110ae20aa7","html_url":"https://github.com/agentjido/awesome-elixir-ai","commit_stats":null,"previous_names":["agentjido/awesome-elixir-ai"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/agentjido/awesome-elixir-ai","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/agentjido%2Fawesome-elixir-ai","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/agentjido%2Fawesome-elixir-ai/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/agentjido%2Fawesome-elixir-ai/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/agentjido%2Fawesome-elixir-ai/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/agentjido","download_url":"https://codeload.github.com/agentjido/awesome-elixir-ai/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/agentjido%2Fawesome-elixir-ai/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":36016154,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-07-20T02:08:10.276Z","status":"online","status_checked_at":"2026-07-29T02:00:04.910Z","response_time":95,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"created_at":"2025-10-31T03:06:48.244Z","updated_at":"2026-07-29T04:00:18.320Z","primary_language":"Elixir","list_of_lists":false,"displayable":true,"categories":["License","Resources","Vision \u0026 Image Processing","Data Ingestion \u0026 ETL","Speech \u0026 Audio","High-Level Agent Frameworks","Starters, Templates \u0026 Examples","LLM Clients \u0026 SDKs","LangChain-Style Components","Evolutionary \u0026 Genetic Algorithms","RAG \u0026 Embeddings","Observability, Evaluation \u0026 Guardrails","Vector Databases \u0026 Indexers","Featured Learning: Elixir Mentor"],"sub_categories":["Community \u0026 Ecosystem","Tutorials \u0026 Learning","How to Join","Model Context Protocol (MCP)"],"readme":"# Awesome Elixir AI [![Awesome](https://awesome.re/badge.svg)](https://awesome.re)\n\n\u003e **Help us curate the higher-level AI stack for Elixir—PRs welcome!** See [Contributing](CONTRIBUTING.md) to add packages, examples, and learning resources.\n\nA curated list of Elixir AI libraries, tools, frameworks, and resources for building production - ready agentic and LLM-driven applications on the BEAM.\n\n## About the Swarm\n\nThe **Elixir AI Swarm Collective** advances the higher-level AI ecosystem for Elixir/BEAM—empowering developers who ship production-ready agentic and LLM-driven applications.\n\n### What We Do\n\n- **Curate** an awesome-list of packages that work seamlessly together\n- **Educate** through tutorials, examples, and partnerships\n- **Maintain** packages to ensure compatibility and ease of use\n- **Share** production patterns and real-world examples\n- **Support** developers via Discord discussions and office hours\n- **Build** starter templates and integration guides\n- **Showcase** monthly highlights of production AI applications\n- **Fund** integration bounties for connecting to AI services\n\n### How to Join\n\nWant your package or content included? Simple PR to this awesome-list. If it helps developers build AI applications on Elixir, it belongs.\n\n## Join the Community\n\n- **Discord** — Home base for real-time discussion and support: https://discord.gg/9JAbhRRZ\n- **GitHub** — [`agentjido`](https://github.com/agentjido) org for awesome-list, templates, and examples\n- **X/Twitter** — [@agentjido](https://x.com/agentjido) for announcements and highlights\n- **ElixirForum** — Monthly showcases and major announcements\n- **Elixir Weekly** — Submit highlights for newsletter inclusion\n\n## Featured Learning: Elixir Mentor\n\n- **[Elixir Mentor YouTube](https://www.youtube.com/@ElixirMentor)** — Tutorials, deep dives, and monthly showcases focused on agentic AI with Elixir. Subscribe for expert content on building AI applications with Phoenix, LiveView, and the BEAM.\n\n## Contents\n\n- [Awesome Elixir AI ](#awesome-elixir-ai-)\n  - [About the Swarm](#about-the-swarm)\n    - [What We Do](#what-we-do)\n    - [How to Join](#how-to-join)\n  - [Join the Community](#join-the-community)\n  - [Featured Learning: Elixir Mentor](#featured-learning-elixir-mentor)\n  - [Contents](#contents)\n  - [Ecosystem Map](#ecosystem-map)\n  - [High-Level Agent Frameworks](#high-level-agent-frameworks)\n  - [LangChain-Style Components](#langchain-style-components)\n  - [LLM Clients \\\u0026 SDKs](#llm-clients--sdks)\n  - [RAG \\\u0026 Embeddings](#rag--embeddings)\n  - [Vector Databases \\\u0026 Indexers](#vector-databases--indexers)\n  - [Observability, Evaluation \\\u0026 Guardrails](#observability-evaluation--guardrails)\n  - [Data Ingestion \\\u0026 ETL](#data-ingestion--etl)\n  - [Speech \\\u0026 Audio](#speech--audio)\n  - [Vision \\\u0026 Image Processing](#vision--image-processing)\n  - [Evolutionary \\\u0026 Genetic Algorithms](#evolutionary--genetic-algorithms)\n  - [Starters, Templates \\\u0026 Examples](#starters-templates--examples)\n  - [Resources](#resources)\n    - [Tutorials \\\u0026 Learning](#tutorials--learning)\n    - [Model Context Protocol (MCP)](#model-context-protocol-mcp)\n    - [Community \\\u0026 Ecosystem](#community--ecosystem)\n  - [Contributing](#contributing)\n  - [License](#license)\n\n## Ecosystem Map\n\nQuick overview of how the pieces fit together:\n\n- **Build agents and orchestrations** → [High-Level Agent Frameworks](#high-level-agent-frameworks)\n- **Call LLMs** → [LLM Clients \u0026 SDKs](#llm-clients--sdks)\n- **Compose prompts, chains, tools, memory** → [LangChain-Style Components](#langchain-style-components)\n- **Do RAG: chunk, embed, index, retrieve** → [RAG \u0026 Embeddings](#rag--embeddings), [Vector Databases](#vector-databases--indexers)\n- **Observe, evaluate, and add guardrails** → [Observability \u0026 Evaluation](#observability-evaluation--guardrails)\n- **Integrate with your data** → [Data Ingestion \u0026 ETL](#data-ingestion--etl)\n- **Add speech and vision** → [Speech \u0026 Audio](#speech--audio), [Vision \u0026 Image Processing](#vision--image-processing)\n- **Use starters and examples to ship faster** → [Starters \u0026 Templates](#starters-templates--examples)\n\n## High-Level Agent Frameworks\n\n*Build autonomous agents, workflows, and multi-agent systems.*\n\n- [AshAi](https://github.com/ash-project/ash_ai) - Structured outputs, vectorization and tool calling for your Ash application with LangChain integration and MCP server capabilities.\n- [Jido](https://github.com/agentjido/jido) - Framework for building autonomous, distributed agent systems with modular actions, stateful agents, and sensors. AI-framework agnostic.\n- [LangChain](https://github.com/brainlid/langchain) - Framework for developing applications powered by language models, with support for OpenAI, Anthropic, Google, and Bumblebee models.\n- [SwarmEx](https://github.com/nrrso/swarm_ex) - Lightweight library for AI agent orchestration with built-in telemetry and tool integration.\n\n## LangChain-Style Components\n\n*Prompts, chains, tools, memory, and structured outputs.*\n\n- [Instructor.ex](https://github.com/thmsmlr/instructor_ex) - Structured outputs from LLMs using Ecto schemas. Works with OpenAI, llama.cpp and Bumblebee.\n- [InstructorLite](https://github.com/martosaur/instructor_lite) - Lightweight structured outputs for LLMs using JSON schemas with multi-provider support including OpenAI, Anthropic, and Gemini.\n- [Mentor](https://github.com/zoedsoupe/mentor) - Library for generating validated structured outputs from LLMs with automatic retries and schema validation.\n\n## LLM Clients \u0026 SDKs\n\n*Connect to LLM providers with unified or specialized clients.*\n\n- [ExLLM](https://github.com/azmaveth/ex_llm) - Multi-provider LLM library with unified API for Anthropic, OpenAI, Gemini, Groq, Ollama, and more. Features streaming, cost tracking, and structured outputs.\n- [Honeycomb](https://github.com/seanmor5/honeycomb) - Fast LLM inference service and library built on Elixir, Bumblebee, and EXLA with OpenAI API compatibility.\n- [LLM Composer](https://github.com/doofinder/llm_composer) - An Elixir library for integrating and managing multiple LLM backends including OpenAI, Ollama, and Google Gemini.\n- [Ollama-ex](https://github.com/lebrunel/ollama-ex) - Elixir client for Ollama API with support for completions, chat, tools, and function calling.\n- [ReqLLM](https://github.com/agentjido/req_llm) - Composable LLM client built on Req. Plugin-based providers for Anthropic, OpenAI, Google, and more with typed data structures.\n\n## RAG \u0026 Embeddings\n\n*Retrieval Augmented Generation, chunking, and embedding pipelines.*\n\n- [Rag](https://github.com/bitcrowd/rag) - Library for building Retrieval Augmented Generation (RAG) systems with support for vector stores like pgvector and chroma.\n- [TextChunker](https://github.com/revelrylabs/text_chunker_ex) - Semantic text chunking library optimized for vector embedding and RAG applications.\n\n## Vector Databases \u0026 Indexers\n\n*Similarity search and vector storage for AI applications.*\n\n- [ExFaiss](https://github.com/elixir-nx/ex_faiss) - Elixir front-end to Facebook AI Similarity Search (Faiss) for efficient similarity search and clustering of dense vectors.\n- [pgvector-elixir](https://hex.pm/packages/pgvector) - Ecto type and helpers for pgvector. Use Postgres as your vector store.\n\n## Observability, Evaluation \u0026 Guardrails\n\n*Track, evaluate, and protect your AI applications.*\n\n- [DeepEvalEx](https://github.com/holsee/deep_eval_ex) - LLM evaluation framework benefiting from Elixir concurrency model with metrics for faithfulness, hallucination detection, answer relevancy, and RAG-specific evaluation. Output compliance with DeepEval standard for ecosystem integration.\n- [Evals](https://github.com/ash-project/evals) - Tool for evaluating AI language models on Elixir code generation with side-by-side model comparisons and automated testing.\n- [Usage Rules](https://github.com/ash-project/usage_rules) - Tool for synchronizing LLM rules files with dependencies to prevent AI hallucinations and ensure consistent usage patterns.\n\n## Data Ingestion \u0026 ETL\n\n*Web crawling, data extraction, and preprocessing for AI pipelines.*\n\n- [Crawly](https://github.com/elixir-crawly/crawly) - Powerful Elixir web crawler for building corpora and data extraction pipelines.\n- [Explorer](https://github.com/elixir-explorer/explorer) - Series and dataframes for data exploration in Elixir. Essential for preprocessing and feature pipelines.\n- [Floki](https://github.com/philss/floki) - HTML parser for extraction pipelines.\n\n## Speech \u0026 Audio\n\n*Text-to-speech, speech recognition, and audio processing.*\n\n- [Chatterbex](https://github.com/holsee/chatterbex) - Elixir wrapper for Chatterbox TTS with zero-shot voice cloning and support for multiple Chatterbox models including multilingual synthesis.\n- [Membrane Framework](https://github.com/membraneframework/membrane_core) - Real-time multimedia processing framework. Great for TTS/STT pipelines and streaming audio applications.\n\n## Vision \u0026 Image Processing\n\n*Image processing, computer vision, and OCR for AI applications.*\n\n- [Evision](https://github.com/cocoa-xu/evision) - OpenCV bindings for Elixir/Erlang with comprehensive computer vision capabilities.\n- [NxImage](https://github.com/elixir-nx/nx_image) - Image processing in Nx for preprocessing and augmentation.\n- [Vix](https://github.com/akash-akya/vix) - Fast image processing via libvips for preprocessing and augmentation.\n- [YOLO](https://github.com/poeticoding/yolo_elixir) - Real-time object detection using YOLOv8 models with 38ms processing time and optional Rust NIF for performance.\n\n## Evolutionary \u0026 Genetic Algorithms\n\n*Evolution-based optimization and problem solving.*\n\n- [Genex](https://github.com/seanmor5/genex) - Genetic Algorithms in Elixir. Simple library for evolutionary computing and optimization problems.\n\n## Starters, Templates \u0026 Examples\n\n*Get started quickly with pre-built templates and example applications.*\n\n- [Livebook](https://livebook.dev/) - Write interactive and collaborative notebooks with integrations to databases, messaging, visualization and AI workflows.\n- [Kino](https://github.com/livebook-dev/kino) - Render rich and interactive output in Livebook for building AI demos and explorations.\n\n## Resources\n\n### Tutorials \u0026 Learning\n\n- **[Elixir Mentor YouTube](https://www.youtube.com/@ElixirMentor)** — Tutorials, deep dives, and showcases for AI with Elixir.\n- **[Elixir Mentor Podcast](https://podcasts.apple.com/gr/podcast/elixir-mentor/id1710056466)** — Community interviews and project showcases.\n- **[Livebook Notebooks](https://livebook.dev/)** — Interactive notebooks and SmartCells for AI use-cases.\n- **[Genetic Algorithms in Elixir](https://pragprog.com/titles/smgaelixir/genetic-algorithms-in-elixir/)** — Book by Sean Moriarity on evolutionary computing in Elixir.\n\n### Model Context Protocol (MCP)\n\n*Connect AI assistants to Elixir services and documentation.*\n\n- [Anubis MCP](https://github.com/zoedsoupe/anubis-mcp) - SDK for the Model Context Protocol (MCP) with support for multiple transport options (STDIO, HTTP/SSE, WebSocket).\n- [HexDocs MCP](https://github.com/bradleygolden/hexdocs-mcp) - Enables semantic search of Elixir package documentation for AI assistants via Model Context Protocol (MCP).\n- [MCP Proxy](https://github.com/tidewave-ai/mcp_proxy_elixir) - Proxy that connects STDIO-based MCP clients to HTTP-based Server-Sent Events (SSE) MCP servers.\n- [Tidewave Phoenix](https://github.com/tidewave-ai/tidewave_phoenix) - AI-powered development assistant for Phoenix web applications that connects editor AI assistants to web framework runtime via MCP.\n\n- [TWZRD Agent Intel](https://intel.twzrd.xyz) - Trust scoring MCP server for AI agents on Solana. Provides wallet identity verification and trust receipts for Elixir-based agent pipelines via streamable-HTTP MCP. Free to use: `{\"mcpServers\":{\"twzrd-agent-intel\":{\"url\":\"https://intel.twzrd.xyz/mcp\"}}}`\n\n### Community \u0026 Ecosystem\n\n- **[Discord](https://discord.gg/9JAbhRRZ)** — Home base for the Elixir AI Swarm Collective.\n- **[agentjido GitHub Org](https://github.com/agentjido)** — Packages, templates, and examples.\n- **[@agentjido on X/Twitter](https://x.com/agentjido)** — Announcements and highlights.\n- **[ElixirForum AI Topics](https://elixirforum.com/)** — Monthly showcases and discussions.\n\n## Contributing\n\nWe welcome contributions! Please read our [Contributing Guidelines](CONTRIBUTING.md) before submitting a PR.\n\n**Quick Guidelines:**\n\n- Format: `[Name](link) - Description.`\n- Keep entries alphabetized within each section\n- Descriptions should be short, clear, and descriptive\n- Start with a capital letter and end with a period\n- Ensure packages are generally useful, actively maintained, and documented\n\n## License\n\n[![CC0](https://licensebuttons.net/p/zero/1.0/88x31.png)](https://creativecommons.org/publicdomain/zero/1.0/)\n\nTo the extent possible under law, the Elixir AI Swarm Collective has waived all copyright and related or neighboring rights to this work.\n","projects_url":"https://awesome.ecosyste.ms/api/v1/lists/agentjido%2Fawesome-elixir-ai/projects"}