Explore the directory

A Sublime Text plugin that provides out-of-the-box C, C++, Objective-C, and Objective-C++ code completion using libclang, configured automatically from an existing CMake or Bazel build.

• Editors

OPFOR is an open-source red-teaming tool for AI agents, LLM applications and MCP servers, generating attacks across the OWASP LLM, Agentic AI, MCP and API Security top-ten lists and judging each response with an LLM, from a command line, an IDE, or a browser extension.

• AI evals
• Security

embeddedskills is a free, open-source collection of embedded development and debugging skills that let an AI assistant directly operate compilers, debuggers and communication buses, closing the loop from code generation to hardware verification.

• Agent skills
• Debugging

Compartment is encrypted, fully offline persistent memory for AI agents, stored as one vault on the user's own computer that Claude Code, Claude Desktop, Cursor, Codex and other MCP clients can read and write with no API key, account or network connection.

• Agent memory

Sleek Agent Skills is an agent skill that lets an AI coding assistant design mobile app screens and manage projects through Sleek, a commercial AI-powered mobile app design tool, using an API key tied to a Sleek account.

• Agent skills
• Design tools

YouTube Transcript Server is an MCP server that retrieves captions and subtitles from YouTube videos directly, with optional timestamps, automatic language fallback, and built-in filtering of ads and sponsorship segments.

• MCP servers

A 22-chapter open course teaching how to design, build and operate production AI agents, meant to be studied alongside your own AI assistant rather than as a stand-alone tutorial, with a companion skill that reviews agent designs against the course.

• Tutorials

Rome is a self-hosted agentic operating system where human and agent collaborate over time, agents build their own harnesses and workflows under guidance, and proven capabilities carry forward into later sessions, offered as an open-source alternative to Grok Bot and Meta's Muse.

• Agent frameworks

mcp-sequentialthinking-tools is a lightweight MCP server that records a model's step-by-step reasoning as a branching, revisable history, and validates tool-plan recommendations against a supplied tool list, without discovering or choosing tools itself.

• MCP servers

Wind Comic is a multi-agent AI pipeline that turns one line of text into a finished short-form drama, script, character-consistent storyboards, voice acting, music and a rendered video, using specialist agent roles for writing, directing, production and editing.

• Generative media

svg-diagram is an agent skill that teaches a coding agent a consistent house style for hand-placed SVG diagrams, architecture, flowchart, sequence, data-flow and lifecycle diagrams, checked by a zero-dependency linter.

• Agent skills

Elastic Agent Skills is Elastic's official library of Agent Skills that teach an AI coding assistant how to correctly use Elasticsearch, Kibana, Elastic Observability and Elastic Security, compatible with agentic IDEs such as Cursor, GitHub Copilot, Windsurf and Gemini CLI.

• Agent skills

ComfyUI VLM Nodes adds vision-language model nodes to ComfyUI, covering image and video captioning, structured prompting, open-vocabulary object detection, and segmentation, across a curated set of current small and large models.

• Generative media

An open-source iOS library that powers the Quran.com app, providing most of that app's code as a reusable Swift package foundation for building other Quran-related applications.

• Mobile
• Libraries

OpenAnalytics is an open-source, self-hostable web analytics platform that tracks page views, funnels and revenue without cookies or cross-site profiles, and includes its own MCP server and command-line tool.

• Monitoring

Athena is a local-first personal knowledge management agent that keeps a person's memory, reasoning structure and governance rules as plain files on their own machine, so that context can move between ChatGPT, Claude, Gemini or any other model instead of resetting with each one.

• Agent memory

A curated list of research papers and code for diffusion-model inference, covering sampling, caching, quantization, parallelism, and attention optimizations for image and video diffusion transformers.

• Curated lists
• Papers

ollama-helm is a community Helm chart that deploys Ollama on Kubernetes, with configuration for CPU-only or GPU-accelerated clusters and for pulling or creating models automatically at startup.

• Inference
• Containers

A macOS menu-bar app that keeps a chosen keyboard input source locked, re-applying it whenever it drifts, with separate rules per app, per website, or a global default.

• Desktop utilities

An LLM gateway and CLI proxy that compresses tool outputs, caches semantically similar requests, and routes each request across more than a dozen providers by complexity, including wrapping an existing Claude Code or Codex subscription.

• LLM gateways

Maestro is a workflow skill for AI coding agents that adds diagnostic, refinement and hardening commands, persistent memory and an audit trail, aimed at the common failure modes of unstructured prompts, context overflow and unnecessary multi-agent complexity.

• Agent skills

BigMoeOnEdge runs Mixture-of-Experts language models larger than a device's RAM, on a phone or PC, CPU-only, by streaming just the experts each token needs directly from flash storage, with output identical to running the full model in memory.

• Inference

MiniSearch is a self-hosted, private web search engine with an AI assistant that can run entirely inside the browser, requiring no API key, inference server or third party to see a user's queries.

• Inference

LLM Hub is an open-source mobile app for Android and iOS that runs chat, image, video and music generation entirely on the device, with CPU, GPU or NPU acceleration and a mode that builds a small app live from a spoken idea.

• Inference
• Generative media