How to use Research Workbench Assistant: what you can do with it

4 use cases

• Resume thesis work across new Codex chats

  Save checkpoints and next steps in your project so a new Codex chat can pick up where you stopped.

  • REPO z-liu-xiugou/research-workbench-assistant
  • Codex
  • Research
  • Intermediate
  View prompt

  In the research-workbench-assistant repo, use the research-workbench Skill in the project at <project-path> to initialize a workbench, save the current progress and next steps, then start a new chat and resume. Expected output: an ACTIVE_CONTEXT resume checkpoint in the project. Verify that unconfirmed plans are not recorded as confirmed.

  Share Email me this

• Find papers on Crossref and triage them as candidates

  Search Crossref by topic and year, save deduplicated candidates, and record keep or exclude reasons.

  • REPO z-liu-xiugou/research-workbench-assistant
  • Research
  • Intermediate
  View prompt

  In the research-workbench-assistant repo, run the discover command against the workbench at <workbench-path> with the query <topic> for years 2023 to 2025 and a limit of 10. Expected output: CANDIDATES.md and CANDIDATES.json with pending entries. Verify that no candidate is marked as read.

  Share Email me this

• Test the record workflow from the command line

  Run the bundled demo to see checkpoint and paper records created, resumed, and audited without Codex.

  • REPO z-liu-xiugou/research-workbench-assistant
  • Research
  • Intermediate
  View prompt

  In the research-workbench-assistant repo, run the init, record, resume, and audit commands with --root demo-workbench, using examples/checkpoint.json and examples/paper.json. Expected output: demo-workbench/ACTIVE_CONTEXT.md and a generated note in demo-workbench/notes/. Verify that the audit command completes without errors.

  Share Email me this

• Review project status in an offline HTML overview

  Generate a local HTML snapshot of checkpoints, tasks, candidates, and notes for a quick status check.

  • REPO z-liu-xiugou/research-workbench-assistant
  • Research
  • Beginner
  View prompt

  In the research-workbench-assistant repo, run the overview command on the workbench at <workbench-path> and confirm that OVERVIEW.html was created. Expected output: a static HTML snapshot with no external resource requests. Verify that the page is a snapshot and not a live view.

  Share Email me this

Quick start with Research Workbench Assistant

1. Check you have what it needs: A working local Codex installation with an account that can use it; Python 3.10 or newer; Git.
2. Open z-liu-xiugou/research-workbench-assistant on GitHub and read the README and license.
3. Run python -X utf8 scripts/install.py from the cloned repository to copy the research-workbench Skill into your user .agents/skills folder, then restart Codex if the Skill is not recognized.
4. Open your own research project in Codex and send: $research-workbench 请为这个项目初始化科研工作台。先了解我的研究目标，不要编造进展，也不要覆盖已有记录。
5. After a substantial piece of work, send: $research-workbench 请保存这次实质进展、证据位置和下一步，并更新续接断点。还没确认的方案不要写成已确认。
6. In a new chat, send: $research-workbench 继续上次研究。先读当前断点，只加载这次任务需要的资料。

These steps come from our top use case, Resume thesis work across new Codex chats, which also has a copy-paste agent prompt.

Using the Deduped MCP, get the setup steps for z-liu-xiugou/research-workbench-assistant

claude mcp add --transport http deduped https://dedupedai.com/mcp

Research Workbench Assistant alternatives · Best AI repos for Research

About this repo

• Who it is forGraduate students and researchers who work with Codex on a long project and lose track of progress when a chat ends.
• Why it is hot186 stars, launched 49 days ago
• LanguagePython
• Sourcegithub.com/z-liu-xiugou/research-workbench-assistant · Back to Hot repos

Requirements

• A working local Codex installation with an account that can use it
• Python 3.10 or newer
• Git

Related repos

• #8 this week REPO K-Dense-AI/scientific-agent-skills Scientific Agent Skills A library of 177 Agent Skills that give AI agents documented, validated guidance for scientific packages, databases, and research workflows.
• Trended earlier REPO NVIDIA/personaplex PersonaPlex PersonaPlex is NVIDIA's real-time, full-duplex speech-to-speech conversational model based on Moshi that controls persona through text role prompts and audio voice conditioning.
• Trended earlier REPO VectifyAI/PageIndex PageIndex PageIndex is a vectorless, reasoning-based RAG system that builds a tree index of long documents and lets an LLM search it like a human reader, with local and cloud SDK modes.