jmiao24/Paper2Agent

This page introduces an external open-source repository. It is not an HDATF product.

What it does

A multi-agent system that turns a research paper, along with its code repository if available, into an interactive AI agent. It coordinates parallel specialist agents to produce MCP servers and skills.

How it helps ATF

LabChin links searched sources to experiment plans, and this could be a reference for turning a paper and its code into tools an agent can call. Its split into parallel specialist agents with a verification step is also worth comparing for Harness.

License

MIT Permissive. Commercial use and changes are allowed if the copyright notice is kept.

More in this category

• felinics/Memoh
  An open-source multi-agent platform giving each agent its own cloud workspace with filesystem, browser, network and long-term memory. Agents stay online, can be reached through chat apps such as Telegram, and Claude Code or Codex can run inside the workspaces.
• EvoMap/AutoResearch
  An agent workflow for AI and machine learning research, from an idea through experiment planning, execution, result analysis and independent review. Plans, code, logs, metrics and review reports are saved to disk so researchers can take over.
• alphaXiv/OpenResearch
  A local-first workspace that turns coding agents such as Claude Code or Codex into research agents. Each research direction gets its own agent session and git worktree, and experiment runs, logs and results stay tied together.
• google/artemis
  ARTEMIS turns natural-language instructions into automation on real or emulated Android devices. Through MCP, coding assistants such as Claude Code can drive test devices and collect logs and screenshots.
• Tencent/BrowserSkill
  BrowserSkill is a CLI and browser extension that lets AI agents such as Claude Code or Codex use the user's logged-in browser in a separate window. The agent can ask the user to take over for captchas or logins.

Only repositories in the ranked Trendshift lists are included, and the lists are used only to find candidates. We do not copy their ranks. Descriptions, licenses and star counts come from each GitHub repository. The notes are our own reading. We have not tested these projects, and a place on a trending list does not prove quality.