Superpowers is a repository about an agentic skills framework and software development methodology for AI-assisted software engineering.
Open Source: #agents
Catalog projects marked with #agents. Tags work as dedicated landing pages, so related tools are easier to find and connect.
This collection holds 37 projects with a combined 3,017,704 GitHub stars. Main languages: Python, TypeScript, JavaScript.
About AI agents
Agents are the step after chatbots: systems that do not just answer but plan, call tools, and carry a task to completion. The field is young and turbulent, standards are still forming — which makes living open source implementations especially valuable.
Collected here are agent frameworks, multi-agent orchestrators, and ready assistants. Watch the last-commit date: in this field, six quiet months already mean falling behind.
Repositories
ECC is a young JavaScript project around a performance optimization system for agentic AI coding harnesses, skills, memory, and developer tooling.
Langflow is a visual builder for AI agents and workflows with Python components, API/MCP servers, and deployment-focused features.
Dify is a production-oriented low-code platform for agentic workflows, RAG, orchestration, and LLM applications.
LangChain is an agent engineering platform and Python framework for LLM applications, integrations, agents, and RAG workflows.
Awesome LLM Apps collects runnable language-model application examples: agents, RAG, voice scenarios, and MCP integrations.
Awesome MCP Servers is a catalog of MCP servers for connecting AI agents to files, databases, browsers, SaaS products, and developer tools.
MCP Servers is the official set of Model Context Protocol reference servers for connecting AI clients to files, Git, databases, and services.
autoresearch is Andrej Karpathy’s experiment with AI agents that automatically run research around single-GPU nanochat training.
TradingAgents is a Python framework for experimenting with multi-agent LLM approaches to market analysis, risk, and portfolio decisions.
claude-mem is a persistent memory system for AI agents that captures session context and injects relevant fragments into future runs.
LobeHub is a platform for working with AI agents, knowledge, and collaborative task organization around large language models.