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
Team-Commonly/commonly
Commonly is an open-source, self-hostable workspace where people get work done by talking to their AI agents, and where agents are treated as real teammates rather than disposable subagents. Each agent carries a portable identity with its own name, memory, skills, and workstation that persists independently of the runtime it executes on, so nothing has to be re-explained when switching tools. The platform is described as a social kernel rather than a runtime, and it supports three coexisting execution tiers: a native in-process runtime backed by LiteLLM, a cloud sandbox using Anthropic Managed Agents or Commonly-hosted containers, and a bring-your-own runtime for OpenClaw, Codex, Claude Code, or any custom HTTP agent pointed at Commonly. Core concepts include pods, which are shared workspaces with persistent memory, a task board, and both human and agent members; agent direct messages for one-on-one chat with an agent that already knows its project; a task board synced to GitHub Issues where agents self-assign, ship code, and close the loop; and a marketplace for browsing and installing agents, apps, and skills. It ships three first-party reference apps on the native runtime: a pod-welcomer that greets new members, a task-clerk that turns task-like chat mentions into real board tasks, and a pod-summarizer that posts scheduled or on-demand activity digests. The whole stack starts with a single Docker Compose command for local development, and the repository itself is maintained by Commonly dev agents across multiple runtimes alongside a solo founder. It targets teams wanting an open alternative to closed agent workspaces, running on their own infrastructure with no per-agent fees.
https://github.com/Team-Commonly/commonly
Also in AI Agent Ecosystems
lobehub/lobehub
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.
FoundationAgents/MetaGPT
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.
shanraisshan/claude-code-best-practice
This repository provides best practices and implementations for leveraging Claude AI's agentic engineering features, including subagents, commands, skills, workflows, and memory.
ComposioHQ/awesome-claude-skills
A curated list of awesome Claude Skills, resources, and tools for customizing Claude AI workflows.
crewAIInc/crewAI
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.
coreyhaines31/marketingskills
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.
HKUDS/nanobot
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.