SmartSub (妙幕) is an open‑source, cross‑platform desktop app that lets you download a video, run local or cloud speech‑to‑text, translate subtitles with many services, edit/proofread them, synthesize voice (including zero‑shot voice cloning), and finally hard‑burn or mux the subtitles back into the video. It runs offline with optional GPU acceleration and can be used completely for free.

An open-source skill pack that turns coding agents into a professional workflow for writing Chinese web fiction, featuring tools for market analysis, story deconstruction, and consistency management.

A commercialization desktop client based on DeepSeek Harness and Jingyun Studio that enables AI developers to turn agents and workflows into monetizable products.

A realtime voice runtime that allows AI agents to maintain a continuous conversation with the user while simultaneously executing complex background tasks.

A Model Context Protocol server that enables AI assistants to control FreeCAD for 3D modeling, Python scripting, and FEM analysis.

QuantDinger is an open‑source, self‑hosted AI‑augmented trading operating system. It lets you write Python strategies, back‑test them, run paper‑trading simulations, and optionally execute live orders on crypto exchanges and traditional brokers. The platform integrates multiple LLM providers for market research, offers a Flask‑Gunicorn API, Docker‑compose deployment, optional Prometheus/Grafana observability, and a secure token‑based Agent Gateway for AI‑driven automation.

A one-button installer that automates the setup of a leaked DLSS 5 neural-rendering build into DirectX 11 and 12 games.

An MCP server that gives AI assistants real-time access to 85+ financial and crypto data sources with AI-analyzed impact scores and trading signals.

A context-engineering and spec-driven development framework that prevents AI coding agents from degrading due to context bloat by using a disciplined phase loop and fresh-context subagents.

A reverse proxy that converts the National Anti-Fraud AI assistant into a standard OpenAI-compatible API for use in third-party AI clients.

An open skill for agent-to-agent contracts that unifies payment, negotiation, and dispute resolution protocols to enable trustworthy autonomous commerce.

A multiplayer agent harness for organizations that provides isolated personal workspaces and shared collaborative environments across Slack and the web.

A Git-native, persistent memory layer for AI agents based on the Open Knowledge Format (OKF), providing fast local search and version-controlled knowledge storage.

DwarfStar (antirez/ds4) is a native inference engine for a few open‑weight LLMs (DeepSeek V4, GLM 5.x) that runs on consumer hardware (Apple Metal, NVIDIA CUDA, AMD ROCm). It supports SSD streaming, multi‑GPU and distributed tensor‑parallel execution, provides a CLI, an interactive coding‑agent, and an HTTP server, and includes tools for model download, evaluation, and benchmarking. The project is beta‑quality and builds on the llama.cpp/GGML ecosystem.

Phone Harness is an open‑source bridge that lets LLM agents control a real iPhone (via macOS mirroring) or Android device (via ADB). It captures the screen, OCRs visible text, and injects HID events so agents can open apps, tap text, type, and read results—all without installing anything on the phone.

A 3D visual manager for AI coding agent threads that maps repositories to spatial zones and sessions to astronauts, allowing users to track and launch agent activity across different tools.

Kwipu turns document folders and Obsidian vaults into a property-graph RAG index that can be queried via a terminal, 3D web interface, or MCP client.

Stop That Shit is a plug‑in that adds a guard layer to AI coding agents (Codex, Claude Code, OpenCode, Hermes CLI, Pi). It defines a “Stop Ladder” of four questions to decide if an agent‑proposed action (file write, dependency install, hash generation, etc.) is really required. The Guard intercepts those actions, blocking them unless the user explicitly authorizes them, and returns a clear STOP message. A separate skill, STSS, trims unnecessary defensive language from the agent’s textual output. The project ships adapters for the five agents, a test suite, and installation scripts for each host.

A genuine AI‑agent toolkit that runs as an OpenCode plugin, a Codex‑CLI component set, or a standalone beta command. It ships 11 pre‑configured agents, a one‑word `ultrawork` launch command, Team Mode for parallel agents, LSP/AST‑grep integration, and optional hash‑line editing. Install via `bunx oh-my-openagent install`, `npx lazycodex-ai install`, or `npm i -g omo-ai@beta`.

A research-driven agent skill that removes AI-like patterns from text by repairing narrative architecture and applying venue-specific rules for professional prose.

An agent-first computational platform that allows AI agents to offload hard optimization and decision problems to an accelerated, verified execution engine.

An autonomous research system that turns runnable, measurable projects into continuous, evidence-driven research runs to find optimal solutions through parallel agent exploration.

Oil Motion is an AI‑agent skill that turns design prompts and source images into interactive web animations (scroll‑driven, mouse‑follow, touch, etc.). It automates key‑frame creation, AI video generation, frame‑level cleaning, and packaging into MP4 or WebP assets, then provides ready‑to‑embed front‑end code.

A collection of packaged instructions and scripts that extend AI coding agents with specialized capabilities for Vercel deployment, performance auditing, and frontend engineering best practices.

An MCP server that enables LLMs to interact with web pages using structured accessibility snapshots via Playwright, bypassing the need for vision models.

Official AI skills for GSAP that teach AI coding agents how to correctly use the GreenSock Animation Platform for web animations.

An agent skill for Codex, Claude Code, and OpenClaw that translates entire books in parallel using sub-agents, featuring a glossary system for terminology consistency and multi-format export.

SillyTavern is a locally installed user interface that provides a unified frontend for interacting with various LLM APIs, image generation engines, and TTS models.

A cross-device open-source workbench that allows you to manage and monitor AI agents like Claude Code and DeepSeek Harness running on your work devices from any mobile or web client.

delegate‑skills is a Node‑based toolkit that discovers installed AI code‑generation CLIs, lets you map them to named "lanes" (a fleet), and provides thin wrappers (skills) to run those agents head‑lessly, capture their diffs, and return a structured result for human review before committing.

A self-evolving AI research system that uses a multi-agent team to autonomously explore, analyze data, and iteratively improve its own skills and scientific judgment.

An open-source Postgres development platform that provides a Firebase-like experience with built-in authentication, auto-generated APIs, and real-time database subscriptions.

A model-aware long-context execution framework that reduces LLM serving latency and compute costs through head-aware KV reuse and sparse execution.

A Claude‑skill that watches your work sessions, logs observations, and suggests new or improved Claude skills—including improvements to itself. Install by adding the `.skill` bundle to Claude, let it run, then review its structured logs to keep your skill library evolving automatically.

A Claude-first framework for paid-media operations that automates audits, planning, and creative workflows across 12 advertising platforms with strict safety gates.

A high-performance, single-binary infrastructure that allows you to run Cloudflare Workers unchanged on your own hardware using SQLite and S3.

An open-source, AI-powered workspace and Notion alternative that prioritizes data privacy and native cross-platform performance.

A Model Context Protocol (MCP) server that provides AI agents with unified access to multi-market financial data from providers like Tushare, Qveris, and Binance.

Memgraph is an in‑memory graph database (C/C++) that combines sub‑millisecond graph traversals with built‑in vector, text, and geospatial indexes. It ships a 40+ algorithm library (MAGE), an “Atomic GraphRAG” query model, and an AI Toolkit for LLM‑aware workflows, while offering enterprise features like Raft HA, multi‑tenancy, and fine‑grained security.

A secure tool runtime for AI agents that enables them to operate files, commands, and deployments across multiple local and remote machines via the Model Context Protocol.

A local-first, plain-text workspace that uses MCP integration to allow humans and AI assistants to collaborate directly on the same files.

Engram is a single‑binary Go program that gives AI coding agents a persistent, searchable memory store (SQLite + FTS5). It works with any MCP‑compatible agent (Claude Code, Gemini CLI, VS Code Copilot, Cursor, etc.) via CLI, HTTP API, MCP, or a terminal UI. The tool is zero‑dependency, supports local‑first storage with optional cloud replication, and provides a rich set of memory commands (`mem_save`, `mem_search`, `mem_context`, `mem_session_summary`, …) to let agents remember decisions, bug fixes, and design rationales across sessions and teams.

An agile framework for AI Driven Development that turns ideas into software by making planning and architectural decisions explicit and durable.

An AI Agent system for long-form story creation and translation that manages world-building, character continuity, and narrative state to prevent plot holes and AI-style prose.

Codex Router is a community‑maintained bridge that lets the Codex editor/CLI send prompts to many external LLM providers (Anthropic, Kimi, DeepSeek, Grok, Gemini, Claude, etc.). It stores credentials locally, offers a guided installer, a macOS menu‑bar/desktop‑widget UI, and a Homebrew‑installable CLI. Experimental bridges let it reuse existing Claude, Cursor, and Gemini agents without exposing their OAuth tokens.

A tool that unlocks DLSS 3 Frame Generation and Neural Rendering for NVIDIA RTX 20 and 30 series GPUs in DirectX 12 games.

An extremely fast Python package and project manager written in Rust that replaces pip, poetry, and pyenv to streamline dependency and version management.

A collection of AI agent skills for Codex and Claude Code that automates the end-to-end production of polished Three.js browser games, from asset generation to QA.