Explore the directory

A ready-to-run Docker Compose bundle of local AI services, including Ollama, a chat UI, an LLM gateway, embeddings, speech-to-text, text-to-speech and an MCP gateway.

• Inference
• Containers

A Ruby gem that gives AI coding assistants ground truth about a Rails application's schema, models, routes, controllers and conventions, so they stop guessing from training data.

• MCP servers

A local-first, self-hosted operating system for autonomous agents, running on Ollama or LM Studio with no required cloud calls, and reachable through 18 channels including a terminal, a web UI, Telegram and Discord.

• Agent frameworks

A production-oriented Go framework for distributed microservices, giving generated services one consistent way to handle transport, configuration, governance, background work, and observability.

• Backend

AI agents with a chat interface built into JupyterLab, connected through MCP tools so they can execute code, manage files and interact with notebooks in response to natural-language requests.

• Coding agents
• Data engineering

A collection of pinned build recipes, benchmark records and failure notes for running LLM inference on Intel Arc Pro B60/B70 GPUs with vLLM and llama.cpp.

• Inference

An agent framework that gives an AI agent long-term memory with active recall, a self-evolution cycle that rewrites its own prompts after failures, and multi-agent quality gates before code ships.

• Agent frameworks
• Agent memory

A command-line tool that turns local video folders into a searchable library, finding moments by meaning, spoken words or on-screen text using your own model API key.

• RAG
• CLI tools

A toolkit for running MLX models from Node.js, covering language and multimodal inference, an HTTP server, model conversion, and GRPO/SFT training, with a Rust and C++ native layer and no Python required.

• Inference
• Libraries

An Nx backend that runs GPU-accelerated tensor operations on Apple Silicon through Apple's MLX library, for numerical computing and machine learning in Elixir.

• Libraries

A Visual Studio Code extension that adds SAS language support, connecting to SAS Viya or SAS 9 servers to run code with syntax highlighting, completion, and SAS notebooks.

• Editors

A Swift implementation of the Model Context Protocol over JSON-RPC, supporting stdio, HTTP with Server-Sent Events, and local TCP+Bonjour discovery.

• MCP servers

A step-by-step, notebook-based tutorial that builds a retrieval-augmented-generation pipeline meant to stay accurate at a scale of ten million or more documents, ending in a self-correcting agent that cites and verifies its own claims.

• RAG
• Tutorials

A from-scratch inference engine that separates the prefill and decode phases of LLM generation onto dedicated GPUs, avoiding the interference between the two phases that limits throughput when they share hardware.

• Inference

A set of forty Credo checks that catch patterns common in AI-generated Elixir code but rare from experienced Elixir developers, such as blanket rescues, narrator-style comments and N+1 queries.

• Code quality

A collection of 44 agentic skills and 18 commands across six plugins that give an AI agent working vocabulary and practices for designing AI products, from model interaction patterns through alignment, evaluation and prompt architecture.

• Agent skills

An on-device speech SDK for Android offering streaming speech recognition, text-to-speech, voice activity detection, and noise cancellation, built on ONNX Runtime with Qualcomm NNAPI acceleration.

• Speech

A framework-free, pure-Java implementation of a retrieval-augmented-generation pipeline, with a visual playground for uploading documents, asking grounded questions, and inspecting the retrieved passages behind each answer.

• RAG

A coding agent that reads, writes, runs commands and searches code in a loop until a task is done, run through a hub with a web UI, a terminal dashboard, and a non-interactive command line for scripting.

• Coding agents

A curated list of resources for LLM security operations, covering architecture risks, vulnerabilities, jailbreaks, RAG security, defensive tools, threat modeling, datasets and research.

• Security
• Curated lists

An agent runtime built from narrow, single-purpose Rust worker binaries that each register functions and triggers on a shared engine, which handles routing, retries, state and traces for all of them.

• Agent frameworks

A plugin library that lets developers and researchers inspect, analyze, and steer the internal workings of large language models running on the vLLM inference engine, such as their attention and activations.

• AI evals
• Libraries

An embedded, in-process vector database library for .NET that runs inside an application with no separate server, used for semantic search and retrieval-augmented generation.

• RAG
• Databases

A macOS application for discovering, browsing, installing and tagging skills for AI coding assistants such as Claude Code and Codex, sourced from GitHub repositories or a local directory.

• Agent skills