Discover the toolingbehind modern intelligence
The operating system for AI infrastructure discovery. Search a live map of MCP servers, AI agents, LLM tools, automation systems, and developer infrastructure.
Paper2Agent
Paper2Agent is a multi-agent AI system that automatically transforms research papers into interactive AI agents with minimal human input.
2.2kstars
340forks
Jupyter Notebook
Quality signals
StaleNo testsNo CIThin docsNo licensePopular
AI summary
Auto-generated overview of what this skill does and when to reach for it.
Turns research papers into working AI agents with minimal setup.
Use this when
- You need a functional AI agent from a paper with no code changes
- You want to experiment with agent behavior without manual setup
- You’re studying a paper and want an interactive demo quickly
- You need to prototype agent workflows from research without coding
- You’re exploring multi-agent systems from papers
Don't use when
- The paper lacks clear structure or pseudocode
- You need a production-grade agent with strict reliability
- The paper’s method is too simple for multi-agent use
Capabilities
- Converts paper text into executable agent code
- Supports multi-agent collaboration from paper descriptions
- Generates interactive agent demos automatically
- Minimal human input required for setup
- Handles paper structure parsing and agent logic extraction
- Produces runnable agent implementations from research
Install
Universal installANY TOOL
$ npx skillcity@latest jmiao24/Paper2AgentAuto-detects the skill or MCP server in this repo and installs it for Claude Code, Codex, Cursor, Cline, OpenCode, Gemini CLI, Anti-Gravity, OpenClaw and Hermes.
Requires Node.js 18+ (ships with npx).
Prefer to set it up by hand? Clone the repository:
git clone https://github.com/jmiao24/Paper2Agent.git
Loading README…
Ask a simulated agent to run this skill. It loads the real SKILL.md and reasons over your task with NVIDIA.
paper2agent — sandboxAI sandbox
Pick a quick prompt below or type your own — watch the agent execute this skill step by step.
guest@skillcity:~$Try a prompt