alphaXiv/OpenResearch

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

What it does

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.

How it helps ATF

A reference for LabChin, which links a research question, experiment plan, notes and report. Its git-based experiment tracking and evidence kept next to each run are worth comparing with how Harness checks results with evidence.

License

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

More in this category

• 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.
• 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.
• TencentCloud/Octop
  Octop is a self-hosted, multi-user AI assistant with multiple agents, an expert library, persona templates, OAuth and MCP connectors, and RAG over documents. Users chat through a web dashboard, messaging apps or HTTP APIs.
• jmiao24/Paper2Agent
  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.
• monid-ai/monid
  Monid gives an AI agent one base URL and key to reach 2,000+ tools across 72+ providers, including web search and scraping. This repo is the declarative connector layer describing each endpoint's inputs, outputs and per-call usage.

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.