A high-performance AI gateway that provides a unified API for multiple LLM providers with built-in cost tracking, caching, and failover mechanisms.

A Generative UI framework that enables AI to create safe, predictable, and cross-platform interfaces by constraining AI-generated JSON to a predefined component catalog.

A comprehensive educational ecosystem for Claude Code, featuring deep architectural guides, a security threat database, and an MCP server for in-session learning.

A skill for AI coding agents that scaffolds a Next.js editor to create and export production-ready marketing screenshots for the Apple App Store and Google Play Store.

A backend framework for building ontology-driven business knowledge networks that provide AI agents with high-quality context and safe, controllable execution over proprietary data.

A high-performance Rust-based MCP server that provides structured repository tools for AI agents to efficiently read, search, and edit codebases.

A minimal, self-evolving autonomous agent framework that allows LLMs to control a local computer and autonomously build a personal library of reusable skills.

An open-source, engine-independent simulation platform for autonomous systems that supports both lightweight headless execution and high-fidelity 3D environments via Unreal Engine 5.

An open-source AI IDE that allows developers to run multiple coding agents in parallel, providing each task with an isolated git worktree and environment.

Terminal-Bench is a continuous benchmark for measuring the capabilities of frontier AI agents using a diverse and evolving set of difficult tasks.

Hermex is a native iOS 18+ SwiftUI app that acts as a remote control panel for a self‑hosted **hermes‑webui** AI agent. It streams chat, lets you switch models, manage sessions, view the agent’s file workspace, scheduled tasks, installed skills, memory and usage insights—all while keeping the model inference and data on your own hardware. The app is free, open‑source (MIT) and requires you to run the hermes‑webui server yourself and expose it via HTTPS (e.g., Cloudflare Tunnel or Tailscale).

An open-source platform for shipping reliable AI agents by unifying evaluations, tracing, simulations, guardrails, and prompt optimization into a single feedback loop.

An open-source platform for building durable, long-running AI workflows and agents in TypeScript with built-in retries, observability, and elastic scaling.

FastGPT is an open‑source platform for building AI agents and LLM‑driven applications. It provides a visual Flow editor, knowledge‑base (RAG) support, plugin hot‑reloading, debugging tools, and can be run locally via Docker or deployed on Sealos/Kubernetes. A hosted SaaS version and a commercial edition are also offered.

An MCP server that integrates Telegram accounts with AI agents, allowing them to read and send messages, manage contacts, and transcribe voice notes.

A lightweight Python framework for face recognition and facial attribute analysis that wraps multiple state-of-the-art models for identity verification and demographic prediction.

An open-source framework that enables coding agents to generate production-ready Lottie animations from text prompts and SVG assets.

An ML-powered manga translator written in Rust that automates text detection, OCR, translation, and generative inpainting for a local-first workflow.

pua is a multi‑platform skill that injects corporate‑style “performance‑improvement‑plan” rhetoric and a 7‑point debugging checklist into AI coding assistants (Claude Code, OpenAI Codex, Cursor, Kiro, etc.). It auto‑triggers when the model shows lazy patterns (retries, blaming the user, passive waiting) or can be invoked manually with `/pua`. The skill forces the model to exhaust solutions, verify results, and act proactively, offering language‑specific packs (Chinese, English, Japanese). Benchmarks on a handful of bugs show higher fix and verification counts, though speed gains are modest. Installation is via the respective tool’s plugin/skill system (e.g., `npx skills add tanweai/pua --skill pua-en` for Claude Code).

The open-source runtime for E2B, providing hardware-isolated Firecracker microVMs that allow AI agents to execute untrusted code with instant pause, resume, and fork capabilities.

A Claude Code skill that automates iOS App Store Optimization (ASO), including keyword research, localized metadata, screenshot rendering, and worldwide pricing.

A portable agent plugin that provides AI coding tools with expert SwiftUI best practices, modern API references, and a toolchain for analyzing performance traces.

An open-source, privacy-focused personal finance app that uses AI for automated bookkeeping and offers five different self-controlled data synchronization options.

Clawd on Desk is a cross‑platform desktop pet that visualises the activity of AI coding agents (Claude, Copilot, Gemini, Cursor, etc.) in real time, showing animations for thinking, typing, tool use, permission requests, and task completion. It supports dozens of agents via hook files, offers clickable permission bubbles (with optional Telegram/Feishu/Slack forwarding), a session dashboard, a read‑only mobile PWA, and customizable themes.

A specialized Claude Code workspace that automates research, writing, and optimization of long-form SEO content and landing pages using data-driven analysis and AI agents.

An open-source autopilot stack for drones and unmanned vehicles that provides a modular flight control system supporting various airframes and hardware.

A governance framework for autonomous AI agents that provides deterministic policy enforcement, identity management, and audit logging to prevent unauthorized actions.

A high-performance CUDA kernel library for LLMs that provides optimized GEMM and fused MoE primitives for NVIDIA SM90 and SM100 GPUs.

A CLI and MCP server that bundles project files with prompts to provide grounded AI reviews and audits via APIs or browser automation.

Invoke AI is an open‑source, locally‑run visual‑media generation platform. It provides a web‑based UI with a unified canvas, node‑based workflow editor, gallery management, and support for dozens of modern text‑to‑image models (Stable Diffusion, Flux, Qwen‑Image, etc.). Users install via the provided launcher, run a local server, and create or refine images through an intuitive browser interface. The project targets artists, designers, and developers who need a flexible, extensible AI image creation tool.

A macOS application for real-time audio transcription using Whisper and Parakeet engines, featuring flexible keyboard and mouse triggers for quick voice-to-text conversion.

A privacy-first, local-first AI meeting notepad that records audio directly from your device to provide transcriptions and summaries without needing a bot to join the call.

An AI-powered stock analysis tool that integrates global market data with LLMs to provide intelligent stock selection, sentiment analysis, and automated market reporting.

Skales is a closed‑source, locally‑run AI desktop and mobile agent that can chat, automate multi‑step goals, edit code, generate design/media assets, manage calendars, and retain memory—all without sending data to the cloud. It installs with a single click on Windows/macOS/Linux/Android/iOS and supports >15 LLM providers or fully offline models.

A framework created by the UK AI Security Institute for evaluating large language models, featuring over 200 pre-built evaluations and support for model-graded scoring.

A privacy-preserving human pose estimation system that uses WiFi Channel State Information (CSI) and machine learning to detect poses without cameras.

A set of skills and hooks for AI coding agents that forces them to communicate progress, decisions, and project state in plain, non-technical language for non-engineer builders.

A pre-trained, lightweight Voice Activity Detector (VAD) that identifies speech in audio streams across 6,000+ languages with high accuracy and low latency.

A multimodal AI lakehouse and vector database built on the Lance columnar format for fast, scalable search over petabytes of vectors and multimodal data.

ModLens is a plug‑in for DeepSeek Harness (and other local AI assistants) that adds vision capability to text‑only LLMs. Users paste an image directly into the chat; the plugin forwards it to a configurable vision engine (Gemini, OpenAI‑compatible, Anthropic, Antigravity CLI, Claude/Kimi CLIs, or local agents) and returns a structured transcription for the model to cite. Installation is a single `npx` command or via `skills.sh`, with zero‑config defaults and automatic key rotation/fail‑over. The project is MIT‑licensed and focuses on lightweight integration rather than heavy wrappers.

An open-source incremental indexing framework that keeps AI agent context fresh by only reprocessing data changes (deltas) from enterprise sources into vector or graph stores.

An AI-powered e-commerce customer service SaaS platform that unifies multiple shopping platforms into one interface and automates responses using LLMs and custom knowledge bases.

A curated collection of 300+ specialized agent skills for Google Antigravity, providing repeatable workflows and domain expertise across development, security, and operations.

A unified Linux game library manager that aggregates games from Steam, Lutris, Heroic, and emulators into a single, cover-focused interface.

A curated index of 53 Claude‑compatible *Agent Skills* (design, data, video, writing, persona‑based reasoning, etc.) with install instructions, an update checker, and a machine‑readable catalog. Enables AI agents to perform concrete productivity tasks without custom coding.

slotstream is a Swift‑based inference engine that runs the 125‑billion‑parameter Qwen‑3.8‑Flash‑Next model on Apple‑silicon Macs. It streams 4‑bit‑quantised weights from SSD into a RAM cache, enabling ~12 tokens / s on a 48 GB Mac. The tool offers a CLI, Ollama‑compatible and OpenAI‑compatible HTTP APIs, optional vision support, speculative decoding, and a Swift package for embedding in apps.

A production-grade AI filmmaking tool that automates the entire pipeline from script parsing and character consistency to batch video generation.

Banana Slides is an open‑source AI‑powered app that turns ideas, outlines, or uploaded documents into fully editable PowerPoint decks. It uses LLMs (Gemini, OpenAI, Claude, etc.) for text and image‑generation models for graphics, supports natural‑language “Vibe” editing, custom templates, multi‑format import, PPTX/PDF export, and optional narrated video output. Deployable via Docker, a one‑click cloud template, or a desktop binary, it targets anyone who wants fast, high‑quality slide creation.