Explore the directory

A Model Context Protocol server that gives AI coding agents a pre-built dependency graph, git history and code-health analysis of a repository in a single call, instead of piecing it together with repeated file reads and searches.

• MCP servers
• Agent memory

A SwiftUI workbench for discovering, converting, running and benchmarking machine-learning models with Apple's CoreAI framework, covering language, vision, audio and diffusion model recipes.

• Models
• Inference

A terminal-based collaborative agentic workspace that combines web search, browser control, coding, and voice interaction with long-running sessions for end-to-end development work.

• Coding agents

Sample code and a CloudFormation template for building a question-answering application with Amazon Bedrock, using a knowledge base backed by Amazon OpenSearch Serverless for retrieval-augmented generation.

• RAG
• Tutorials

A curated, tool-agnostic collection of copy-paste prompts for student developers using AI coding agents, built around disciplined workflows that require the agent to read code, take small confirmed steps, and verify its work with tests.

• Curated lists

A tool that compiles a SKILL.md file into a standalone, runnable Python AI agent instead of loading it as a prompt, addressing context isolation, validation and scaling problems with treating skills as loose instructions.

• Agent skills

A Spring Boot starter that generates a REST API directly from annotated JPA entities, adding multi-tenancy, an audit trail, filtering, pagination, exports and real-time WebSocket update events without hand-written repository, service or controller code.

• APIs
• Backend

A 559,000-parameter Japanese text-to-speech engine that runs in real time on a three-dollar ESP32-S3 microcontroller, doing morpheme analysis and pitch-accent estimation on the device with dependency-free C code, with a browser demo of the same engine compiled to WebAssembly.

• Speech

A Python implementation of the DroneCAN protocol stack, a lightweight CAN-bus communication protocol for aerospace and robotics, providing code generation, an interface and supporting utilities.

• Libraries

A Python package that extracts the accessibility tree of macOS application windows as JSON, with an option to capture matching screenshots that highlight each UI element by type, for accessibility testing, UI automation and visual debugging.

• Testing
• Debugging

A dependency-free, pure CUDA and C++ reimplementation of NVIDIA's DVLT transformer that reconstructs a 3D point cloud and camera poses from a handful of images in a single forward pass, packaged as one small binary.

• Inference
• Generative media

A free HTML theme built on Bootstrap for building a knowledge-base or documentation site, intended to be customized to work with WordPress or other content-management systems.

• UI kits
• Documentation tools

A Rust crate implementing the BM25 relevance-scoring algorithm as an embedder, scorer and in-memory search engine, for use directly or alongside vector databases such as Qdrant, Pinecone or Milvus.

• RAG
• Libraries

A Visual Studio Code extension that connects to a local Ollama server for chat and an autonomous coding agent that can read and modify a workspace, without leaving the editor.

• Coding agents
• Editors

A macOS menu bar app that maps a game controller's buttons and sticks to keyboard shortcuts, mouse movement and clicks, tuned for controlling AI coding assistants such as Claude Code and Codex CLI without touching a keyboard.

• Desktop utilities

A self-hosted, microservices-based LLM API platform with an OpenAI-compatible chat endpoint, multi-step tool orchestration, MCP tool integration, and OAuth authentication, deployable through Docker Compose or Kubernetes.

• Inference
• Backend

An autonomous agent harness for Kubernetes and GKE that continuously audits a fleet for compliance and security drift, opens pull requests with fixes through GitOps, and answers operational questions over chat.

• Security
• Containers

A Core ML conversion of the AOT-GAN inpainting model for removing unwanted objects from photos on iPhone, distributed with a runnable sample Xcode project.

• Generative media
• Mobile

A fast, dependency-free inference engine for Google's Gemma 4 language models, written in a single pure-Java file with a GGUF parser and a command-line chat interface.

• Inference

A framework-independent way to specify portable multi-agent systems in a single YAML format and generate runnable code for many popular agent frameworks.

• Agent frameworks

An experimental AI agent framework, built on the eidetica data layer, that runs a ReAct tool-calling loop and multi-agent orchestration behind a Matrix chat bot connected to any OpenAI-compatible language-model provider.

• Agent frameworks

The development workspace for Bevy Remote Protocol tools, including a Model Context Protocol server that lets AI coding assistants inspect and control a running Bevy game-engine application.

• MCP servers
• Debugging

A model-training and code-synthesis toolchain for Analog Devices' MAX78000 and MAX78002 ultra-low-power machine-learning accelerator chips, converting a trained PyTorch model into C code for the device.

• Models
• Inference

An identity and access management layer for AI agents that issues each agent a cryptographic key pair, checks its actions against granted capabilities before they run, and records every decision in an audit log.

• Auth