Explore the directory

An open source Chrome extension and runtime that lets any AI model act inside the browser, executing page actions and verifying results against the live DOM under a set of declared guardrails.

• Browser automation

A curated, hand-written index of more than 200 AI tools organized by the job to be done rather than by vendor, with quick-find tables, role-based tool stacks, and short write-ups comparing alternatives.

• Curated lists

A citation and ontology knowledge graph built from structured PubMed metadata rather than LLM extraction, used to answer biomedical questions with traceable evidence and no answer when a claim cannot be traced.

• RAG

A browser-based modeling and simulation tool for hierarchical UML state machines that generates dependency-free C++17 code from the diagram, and simulates the machine live while it is being drawn.

• Design tools

An unreleased, alpha-stage low-level systems programming language built around explicit memory and execution control, typed failures and deterministic cleanup, with a self-hosted stage-0 compiler that emits native code and WebAssembly through LLVM.

• Languages

A Ruby extension for the Prawn PDF-generation library that adds simple QR-code generation and rendering to a Prawn document.

• Libraries

A Julia implementation of the server side of the Model Context Protocol, letting a Julia application expose tools, resources and prompts to language models such as Claude in a standardized way.

• MCP servers

A Python library that runs text-to-speech, voice cloning and speech recognition entirely on Apple Silicon through Apple's MLX framework, sharing one Python API and command-line interface across several open speech models.

• Speech

A zero-dependency Java library and command-line tool that runs GPU-accelerated large-language-model inference on Apple Silicon from a single executable JAR, by binding a Metal-enabled llama.cpp build through Java's foreign-function interface.

• Inference

A Rust image-dithering and halftoning library that works directly on typed pixel buffers, offering ordered, diffusion, stochastic and palette-based methods to avoid banding when reducing color depth.

• Libraries

A set of skills, rules and API references for Cursor IDE that let an AI agent assemble, edit and validate 1C:Enterprise source objects directly in their platform export format, without needing the 1C Configurator running.

• Agent skills

The official Ollama extension for Visual Studio Code, which adds locally running or Ollama-hosted cloud models to the VS Code Chat model picker.

• Inference
• Editors

Open-source infrastructure for running self-hosted language models in production, deploying vLLM, SGLang or a custom backend across AWS, GCP, Kubernetes or RunPod behind one stable OpenAI-compatible endpoint with guarded, evidence-based releases.

• Inference
• Hosting

A free desktop app that runs open AI chat models locally, and lets multiple computers running SwarmLLM team up over the internet to run models too large for one machine.

• Inference

A community-maintained vLLM hardware plugin that integrates the IBM Spyre AI accelerator into vLLM, following vLLM's own plugin system so IBM's Artificial Intelligence Unit hardware can be used in existing vLLM inference workflows.

• Inference

An airgapped, closed-corpus question-answering demo where a self-hosted Qwen3.6 agent explores a zipped document collection with local tools, such as bash, grep, embeddings and rerankers, under a fixed token budget, to test how test-time compute affects search.

• RAG

A companion code repository for a beginner tutorial video and blog that builds a university FAQ chatbot on Amazon Bedrock step by step, from a first Converse API call through tool use, retrieval-augmented generation, guardrails, and a full agent built with the Strands Agents SDK.

• Tutorials

A single-binary, fully offline Rust CLI that combines semantic and lexical search over a codebase to hand an AI agent only the relevant code, with file paths, line ranges and confidence scores, instead of full files.

• RAG
• CLI tools

A local-first personal AI agent framework with a hybrid short-term and long-term memory, combining an episodic SQLite store and a semantic knowledge graph, plus a DAG-based workflow engine for running several agents concurrently under one persona.

• Agent frameworks
• Agent memory

A collection of security-focused skills for AI coding assistants such as Claude Code, Cursor and Copilot, from Red Hat's product security team, encoding security recommendations and practices as structured Markdown files an assistant reads while writing, testing or auditing code.

• Agent skills
• Security

An open, developer-friendly implementation of a research paper's approach to turning timestamped banking event histories, such as transactions and app sessions, into embeddings for fraud detection, anti-money-laundering graph analysis, and credit scoring.

• Papers

An experimental C++/CUDA and PyTorch inference stack for running large language models on consumer multi-GPU systems, with model-specific kernels, low-bit quantization, tensor and expert parallelism, and benchmarks tuned for older hardware such as the RTX 2080 Ti.

• Inference

A Neovim plugin for inline AI pair programming: writing a marker comment such as cc: with an instruction and saving the file has Claude edit that file directly in place, with a separate marker for Claude to ask a clarifying question before proceeding.

• Editors

A self-hosted, multi-provider AI gateway that exposes one OpenAI-compatible endpoint in front of every configured LLM provider, auto-discovering available models, forming automatic failover groups around shared model names, and storing no prompt data by design.

• LLM gateways