LinkedIn‑agent‑skill is a set of Claude prompt‑skills plus two tiny Python scripts that generate, clean, and score LinkedIn posts, comments, profile rewrites, weekly plans, carousel slides, DMs, inbox triage, and audits. It never posts automatically; you copy‑paste the final draft. The humanizer removes invisible characters, normalises punctuation, swaps buzzwords, and runs five local heuristics to give a “human‑score”. Install by copying the `li‑*` folders into `~/.claude/skills/` and optionally filling a `voice.md` file with your writing style.

Hindsight is a self‑hosted or cloud‑hosted *agent memory* platform that lets LLM‑driven agents retain facts, recall them via multi‑strategy search, and reflect to synthesize new knowledge. It provides Docker/Kubernetes/PyPI deployment, Python/Node/Go/CLI SDKs, and 60+ zero‑code integrations (LangChain, Claude Code, Zapier, etc.). The system claims state‑of‑the‑art benchmark performance and is aimed at production use in enterprises.

HiThink‑Tech / Financial‑API is a commercial A‑share market‑data platform (REST, MCP, CLI, Python SDK) that supplies real‑time quotes, historical K‑lines, financial statements, valuation ratios, fund/futures data and bulk market dumps. It is designed for AI agents, quantitative researchers and developers, with a unified Skill that lets LLM‑powered tools automatically choose the best access method. The service uses a single API key, stores large results locally (DuckDB), and is MIT‑licensed.

Whisper is OpenAI’s open‑source, transformer‑based speech‑to‑text system that handles transcription, language identification, and translation across many languages. It ships as a pip‑installable package with six model sizes (tiny → large, plus a fast “turbo” variant). The CLI (`whisper …`) and a simple Python API (`whisper.load_model(...).transcribe(...)`) let you turn audio files into text with just a few commands. The project runs on Python 3.8‑3.11, PyTorch, and requires ffmpeg (and optionally Rust for the tokenizer). All code and model weights are MIT‑licensed.

A native Rust CLI that lets AI agents (or scripts) control Chrome via simple commands, using accessibility‑based element refs (`@eN`). It supports opening pages, taking snapshots, clicking/filling, extracting text, screenshots, network mocking, tab management, batch execution, and an experimental WebMCP tool system.

Cockpit Tools is a cross‑platform desktop manager that lets you store, switch, monitor and run multiple accounts of many AI‑coding assistants (Antigravity IDE, Codex, GitHub Copilot, Windsurf, Kiro, Cursor, Grok CLI, CodeBuddy, Qoder, Trae, Zed, ZCode, etc.). It provides a unified dashboard with real‑time quota tracking, one‑click account switching, multi‑instance isolation, batch operations and optional local WebSocket integration. Install via native installers or Homebrew; data stays on your machine and the project is released under a non‑commercial CC‑BY‑NC‑SA 4.0 license.

QwenPaw is a self‑hosted AI‑assistant platform built on AgentScope. It provides three‑layer memory (live context, full history, ReMe‑based personal knowledge base), a sandboxed runtime, multi‑agent support, a unified file workspace, extensible skills/plugins, and omni‑channel connectivity (DingTalk, Discord, WeChat, etc.). Install via pip, a one‑click script, Docker, Alibaba Cloud, or a beta desktop app. Licensed under Apache 2.0.

Browser Harness is a Python library that lets LLM agents control a real Chrome/Edge browser via a single CDP WebSocket. The agent can write helper functions during a session, making the system improve over time. It includes an optional MCP server for any MCP‑compatible client and can scale to multiple cloud browsers via Browser Use Cloud.

Dashi PPT Skill is a Node‑based plugin that lets AI agents generate, edit, and export fully‑styled slide decks. It offers 12 themes, 1 020 templates, rich chart/model layouts, in‑browser controls, and one‑click PPTX/PDF export, all running locally under an AGPL‑3.0 license.

JobSync is a self‑hosted web app (Docker‑based) that tracks job applications, resumes, tasks and interview questions, and adds AI‑driven features—resume review, job‑match scoring, cover‑letter generation, and automated job discovery—via LLMs that support tool‑calling (local Ollama or cloud providers). It also exposes an MCP server so external AI agents can add jobs or interview items directly.

Agent‑Native is an open‑source TypeScript framework that lets you write actions once and use them both as tools for LLM‑driven agents and as regular UI calls. It provides shared actions, data, and state, a PostgreSQL backend, authentication, automations, and UI surfaces (chat, team workspaces, etc.) to build full‑stack agentic applications such as design assistants, email managers, and analytics bots.

A GitHub template that lets AI coding agents (Claude Code, Codex, Gemini, etc.) recreate any public website as a clean Next.js 16 project via a single `/clone-website` command. It runs a five‑step pipeline (recon, asset download, component spec generation, parallel build, QA) and outputs a fully typed TypeScript/React codebase. The repo includes scripts for multi‑agent support, Docker, linting, and clear ethical usage guidelines. MIT licensed.

Repowise is an open‑source Python tool that builds a local, continuously‑updated index of a codebase (graph, git history, tests, docs, decisions). It exposes ten deterministic MCP endpoints that let AI coding agents and developers retrieve cited answers, change‑risk scores, test‑impact lists, and concrete refactoring plans with far fewer token calls. The system also provides a health‑score engine (49 detectors) and a GitHub PR bot that posts risk and health analysis directly on pull requests. Installation is a simple `pip install repowise`, `repowise init`, and `repowise serve`. The project is AGPL‑3.0 licensed, self‑hosted, and backed by published benchmarks showing ~30 % reduction in agent output and 97 % smaller payloads.

dsh‑web is a plug‑in aggregation package that extends DeepSeek Harness’s web UI with a full AI‑development workbench: task board with cron, mobile remote control, SSH terminal, image‑understanding tool, per‑model capability UI, Git graph, skins, pets, rescue mode, and more. Install via `dsh plugin --profile web add @linxin666/dsh-web-all@latest` and restart DSH.

Agent Orchestrator is a cross‑platform desktop app that lets you run multiple LLM‑based coding agents as isolated Git‑backed workers, coordinate them via a project‑level orchestrator, and monitor everything on a live Kanban board.

jcode is a terminal‑based AI‑agent harness that emphasizes ultra‑low RAM usage and sub‑50 ms startup. It embeds each conversation turn into a vector graph for automatic memory recall, offers side‑panel file/diagram views, and supports a “swarm” mode where multiple agents collaborate on the same codebase. The tool works with many cloud providers (Claude, OpenAI, Gemini, Copilot, etc.) and any OpenAI‑compatible endpoint, and can be installed via a one‑line script on macOS, Linux, or Windows.

OpenChamber is an open‑source, cross‑platform workspace that lets developers start AI coding agents (via OpenCode), monitor their progress, compare multiple model runs, review changes with guided walkthroughs, preview the app being edited, and integrate directly with GitHub—all while syncing sessions across desktop, web/PWA, VS Code, and mobile devices.

Gentle‑AI is a Go‑based configurator that enhances existing AI coding agents (Claude Code, Cursor, etc.) with persistent memory, skill libraries, planning (Spec‑Driven Development), security guardrails and optional evidence‑based review (Receipt‑Driven Development). It installs via a simple script, runs an interactive TUI to select agents and components, writes native config files, and provides a health‑check command. The tool does not ship its own model; it merely augments agents you already use.

A self-hosted AI transcription and note-taking platform that transforms audio recordings into searchable, intelligent notes with privacy-first infrastructure.

Pascal Editor is a local‑first 3‑D building editor built with React Three Fiber and WebGPU. It runs via a CLI (`npx @pascal-app/cli editor`), stores scenes locally, and exposes a Model Context Protocol (MCP) server that lets AI agents (Claude, Codex, etc.) interact with the scene through published “skills”. The monorepo contains core state (Zustand), a viewer runtime, editing tools, a CLI installer, and the MCP server. Plugins can add new node types or tools. Ideal for architects, researchers, or anyone needing an offline, AI‑ready 3‑D design environment.

Ouroboros is an open‑source *Agent OS* that adds a specification‑first, replayable workflow to any code‑generating LLM (Claude, Codex, Gemini, Copilot, etc.). A one‑line installer provides the `ooo` CLI; you run `ooo setup` then `ooo interview "…"` to have the tool ask Socratic questions, lock the resulting spec (Seed), generate code, automatically evaluate it, and repeat until the contract is satisfied. All actions are recorded in an immutable ledger, making the process auditable and model‑agnostic. The core kernel lives in this repository, while a terminal UI (`ourocode`) and domain‑specific plugins live in companion repos.

Clodds is an open‑source, self‑hosted AI trading terminal. It lets you chat (via Claude or other LLMs) to trade on 10 prediction‑market platforms, 7 futures exchanges, and dozens of Solana/EVM DEXs, launch Solana tokens, mine Bittensor, and run 118+ pre‑built strategies. Install with a single npm command, onboard via a wizard, then use the built‑in WebChat UI or any of 21 messaging apps to place trades, run arbitrage scans, or manage risk. The system includes a unified risk engine, full trade ledger, semantic memory, and a marketplace for AI agents.

CLI‑Anything is a Python framework that automatically generates agent‑friendly Click CLIs for any software, outputting JSON for easy parsing. It includes a 7‑phase generation pipeline (analyze → design → implement → test → document → publish) and a package manager called CLI‑Hub to browse, install, and run a growing catalog of pre‑built CLIs (e.g., GIMP, Blender, Zoom). The project targets AI agents (Claude Code, Cursor, OpenClaw, etc.) that need deterministic, composable command interfaces, and it ships with a comprehensive test suite and security hardenings.

Harbor is a Python framework for running and scaling benchmarks of AI agents and language models. Installable via `pip`/`uv`, it provides a CLI (`harbor run`) that lets you specify a dataset (e.g., Terminal‑Bench‑2.0), an agent (Claude‑Code, OpenHands, etc.), and a model, then executes the benchmark locally or on cloud providers (Daytona, Modal, etc.) with configurable parallelism. It also supports creating custom benchmarks and generating RL roll‑outs.

OpenWhispr is a cross‑platform desktop app for privacy‑first voice dictation, meeting transcription, and AI‑assistant interaction. It supports offline speech‑to‑text with Whisper‑based models or cloud services, offers speaker diarisation, note‑taking with semantic search, team collaboration, and a public API for developers.

AAS Core (Agentic Awesome Skills) is a preview‑stage, open‑source toolkit that lets LLM agents (Codex, Claude, etc.) search a local catalog of 2 115+ reusable instruction “skills”, pick exact IDs for a project, and produce a validated, immutable manifest (`aas‑stack.json`). The core is read‑only: it validates IDs, does not rank or execute them. A CLI can preview a plan, audit risk, and dry‑run a direct installer that copies selected skill directories into `~/.agents/skills`. Specialized plugins bundle related skills for domains like web‑app building or security. The system is designed for auditability and offline control, with safety warnings that it does not certify semantic suitability and that apply/recovery features are experimental.

TourMind Booking Skills are AI‑agent plug‑ins that let chat models search live hotel inventories and flight schedules, compare prices, re‑check availability, and complete bookings/payments via natural language conversation. Installable with a single `npx` command or through the agent, they work with many LLM clients (ChatGPT, Claude, etc.) and require a TourMind token for authenticated actions. The repo provides end‑to‑end hotel and flight booking workflows, multilingual support, and MIT licensing.

A self-hosted, real-time soundscape analyzer for birds, wildlife, and bats that provides local AI inference and a web dashboard for detections.

A free set of Claude‑compatible “skills” that let the Claude LLM audit, optimize and create marketing assets (Google/Meta ads, SEO, email, etc.) by connecting to live ad data through Ryze’s MCP connector.

A high-performance C++ audio inference framework built on ggml that provides a portable, native runtime for running a wide variety of local audio AI models.

A powerful few-shot voice conversion and text-to-speech system that can clone a voice using as little as 5 seconds of audio.

UX/UI Agent Skills is a Claude‑agent knowledge kit that provides design tokens, component specs, accessibility audits, and 17 slash‑command‑style “skills” to let the AI act as a senior UI/UX architect. It can generate token‑driven code for any framework (React, Vue, SwiftUI, Flutter, etc.), enforce WCAG 2.2 compliance via 37 CI gates, and includes a library of 138 design systems for aesthetic direction. Install via `npx ux-ui-agent-skills init`; the agent reads a `CLAUDE.md` brief and runs the skills or natural‑language prompts to produce design assets, code, and audits.

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`.

cmux is a native macOS terminal (built on Ghostty) that adds vertical tabs, a notification system, an in‑app scriptable browser, and SSH workspaces to help developers run and monitor multiple AI coding agents (Claude Code, Codex, OpenCode, etc.) in parallel.

Qwen Code is an open‑source AI coding agent that runs in the terminal, desktop, web, IDEs, and chat apps. It supports multiple LLM providers (OpenAI, Anthropic, Gemini, Qwen, Ollama, vLLM), offers agentic features like auto‑memory, sub‑agents, dynamic workflows, and provides SDKs for TypeScript, Python, and Java. Installation is a one‑line script or npm/Homebrew, and the tool can be used interactively (`qwen`) or headlessly in scripts. Benchmarks on SWE‑bench show ~77 % average pass@3 across versions. The project is Apache‑2.0 licensed and actively maintained.

MemOS 2.0 is a Memory Operating System for LLM‑based AI agents. It offers a unified API to store, retrieve, edit, and delete multi‑modal memories (text, images, tool traces) organized as a graph. The system can run as a hosted cloud service (API‑key access) or be self‑hosted via Docker (Neo4j + Qdrant) or a local SQLite plugin. Ready‑made plugins integrate MemOS with OpenClaw, Hermes, and DeepSeek Harness. Benchmarks show it outperforms existing commercial memory products. Licensed under Apache 2.0.

VODER is a local, offline, professional-grade voice processing toolkit that combines 8 modes—speech-to-text, text-to-speech, voice conversion, music generation, speech enhancement, sound effects, vocal separation, and speaker diarization—plus a Project Eva DLC for image/video/3D generation and uncensored chat. It runs entirely on your machine, works with or without a GPU, and uses open-source models like Whisper, Qwen3-TTS, Seed-VC, and more.

fx is a tiny native CLI coding assistant written in Zig. It talks to any OpenAI‑compatible model (ChatGPT, Vercel AI Gateway, Grok, Ollama, etc.) and can be used interactively, via one‑shot commands, or embedded in apps through a WebAssembly‑based SDK (npm package libfx). Installation is a one‑liner, and the tool is highly configurable and themable.

Pipecat is an open‑source Python framework for building real‑time voice and multimodal AI agents. It offers plug‑and‑play support for dozens of speech‑to‑text, large‑language‑model, text‑to‑speech, and speech‑to‑speech services, composable pipelines, multi‑agent orchestration, and client SDKs for web, mobile, and embedded platforms. The Pipecat CLI can scaffold a working bot in minutes, and additional tools (Whisker debugger, Tail dashboard, Voice UI Kit) help with development and deployment.

An AI‑agent skill that lets coding assistants review and improve UI designs against Apple’s Human Interface Guidelines, supporting Flutter, React Native, SwiftUI, etc., and providing framework‑specific fixes.

AionUi is an open‑source, cross‑platform desktop app that turns LLM APIs into autonomous office assistants. It ships with a built‑in Rust agent (zero‑setup), supports 30+ AI providers, can read/write Word/PPT/Excel files via OfficeCLI, integrates dozens of existing CLI agents, offers team‑mode orchestration, scheduled cron jobs, and remote access through a WebUI or chat‑bot bridges (Telegram, WeChat, etc.). Ideal for developers, analysts, and power‑users who want AI to act on their files and automate tasks without writing glue code.

A JetBrains‑maintained plugin that supplies AI coding assistants with version‑aware guidelines for writing modern Go (up to Go 1.27). It integrates with Junie, Claude Code, Codex, Cursor, and generic `skills.sh` agents, letting them automatically prefer newer language features and idioms.

OpenHuman is an open‑source personal AI assistant platform that provides a persistent, locally stored memory (Memory Tree + Obsidian‑style wiki), a graph‑based orchestrator for multi‑agent workflows, and built‑in research tools (search, scraping, code, voice, image/video generation). It integrates 100+ OAuth services, offers 17 messaging channels, and emphasizes privacy (on‑device encryption, a one‑click privacy mode). The system is built with Rust core, Tauri desktop UI, and several supporting crates (tinyagents, tinyflows, etc.), and is released under a GNU license in early beta.

LlamaFactory is an open‑source toolkit that lets you fine‑tune, evaluate, and serve over 100 large language models with a simple YAML config, offering both a command‑line interface and a Gradio‑based web UI. It supports many modern training methods (LoRA, QLoRA, RLHF, PPO, DPO, etc.), a wide range of models (LLaMA‑3/4, Qwen 3, Mixtral‑MoE, Gemma 3, etc.), and runs on NVIDIA, AMD, Ascend NPU, or cloud services. Integrated monitoring (TensorBoard, WandB, SwanLab) and deployment options (OpenAI‑style API, vLLM/SGLang) make it suitable for researchers, product teams, and educators.

Tick‑Stock‑Panel (TSP) is a self‑hosted, Docker‑deployable web platform for Chinese A‑share quantitative research. It pulls data from multiple plug‑in sources, routes capabilities, computes 68 technical indicators with Polars, runs 25+ built‑in (and custom/AI‑generated) stock‑selection strategies, provides factor editing, mining, and back‑testing (including minute‑level simulation), and offers real‑time monitoring with voice/Feishu alerts. The stack uses FastAPI, DuckDB/Parquet, Polars, and a React 18 front‑end; optional AI integration works via any OpenAI‑compatible API. The README details quick‑start Docker commands, dev mode, and configuration via a `.env` file.

AIRI is an open‑source platform for creating and running AI‑driven virtual characters (digital companions/VTubers). It combines LLM chat, speech‑to‑text, multi‑provider TTS, VRM / Live2D avatar animation, and game‑playing hooks (Minecraft, Factorio, etc.) and runs on browsers, desktop (Electron with CUDA/Metal), and mobile (PWA/Capacitor).

A family of open-source voice AI models for long-form speech recognition and synthesis, capable of handling up to 60-90 minutes of audio in a single pass.

A voice timbre conversion framework that uses retrieval-based features to transform voices with high fidelity and low latency.