Shubhamsaboo/awesome-llm-apps
A curated collection of impressive LLM-powered AI applications featuring RAG, AI Agents, Multi-agent Teams, and open-source models from leading AI providers like OpenAI, Anthropic, and Google Gemini.
Awesome AI Agents › AI Agent Ecosystems
invisible_dots is an open-source, self-hosted alternative to assistant products like OpenAI Dots, Meta Muse, Grok Bot, Manus and Claude Cowork. Each Dot a user creates runs on a hardware-accelerated virtual machine of its own, with a Linux desktop, a terminal, a persistent disk, and a copy of the project's hardened Firefox browser, invisible_playwright_mcp, that keeps separate identities, cookies and logins per browsing profile and resists anti-bot fingerprinting. The VM sleeps when idle and wakes for the next message, task, or scheduled automation. A Dot writes its own notes and how-to skills to its home folder as it works, the way Claude Code does, and reads them back on later tasks, so repeated chores get faster over time. Users can attach their own MCP servers, local programs or remote URLs, with credentials kept out of the stored configuration, and every tool call is gated by a per-tool permission of allow, ask, or deny; an ask waits in an inbox that survives a restart. Tasks and recurring automations are queued with priorities and start times, which also schedules when the Dot's VM needs to be running. State is durable across crashes: a restart or forced kill never loses an accepted message or re-runs a tool call that was already in flight. Users reach a Dot through a web UI, a CLI, an HTTP API with live events, Telegram, or an opt-in WhatsApp integration. Setup requires Node 24+, Go 1.25+, Git, x86-64 hardware virtualization, and an OpenRouter key; QEMU and KVM, or the Windows Hypervisor Platform, provide the VM acceleration. The project is MIT-licensed and explicitly alpha-status, built by the same author as dots and forked from HKUDS/nanobot.
https://github.com/feder-cr/invisible_dots
A curated collection of impressive LLM-powered AI applications featuring RAG, AI Agents, Multi-agent Teams, and open-source models from leading AI providers like OpenAI, Anthropic, and Google Gemini.
LobeHub is a platform that enables users to find, build, and collaborate with AI agent teammates that evolve with them, facilitating multi-agent collaboration and transforming productivity through AI-driven workspaces.
MetaGPT is a multi-agent AI framework that simulates a software company by assigning GPT-based roles to collaboratively automate software development from natural language requirements.
This repository provides best practices and implementations for leveraging Claude AI's agentic engineering features, including subagents, commands, skills, workflows, and memory.
A curated list of awesome Claude Skills, resources, and tools for customizing Claude AI workflows.
CrewAI is a fast, flexible Python framework for orchestrating autonomous, role-playing AI agents that collaborate to solve complex tasks, offering both high-level simplicity and low-level control for enterprise-grade AI automation.
A library of Agent Skills markdown files giving Claude Code, Codex, Cursor and other coding agents marketing know-how: CRO, copywriting, SEO, paid ads, analytics and growth engineering.
nanobot is an open-source, lightweight personal AI agent, providing a WebUI, chat channels, tools, memory, and model routing for long-running workflows and automation.