DEDUPED Hot AI repos, turned into use cases Get the Monday 5
261 stars · Python

How to use Polaris: what you can do with it

What is Polaris? Polaris is a desktop app that runs the full AI research lifecycle locally, from literature survey and idea generation through GPU experiments, LaTeX paper writing, and paper review.

How do I use it? Open the Polaris desktop app and create a direction library, then write its inclusion statement, goals and exclusions through the AI interview; then add anchor papers so cold start can snowball citations from them into the library; let the Research Wiki ingest papers from OpenAlex, Semantic Scholar and arXiv and extract full text. Full steps below.

Trended earlier

View repo on GitHub

Third-party repos we don't own. AI-written use cases can be wrong. Disclaimer

What do you want to do?

4 use cases

  • Build a cross-linked wiki for a research direction

    Ingest papers from OpenAlex, Semantic Scholar and arXiv into a wiki that is compiled up front.

    View prompt
    Using the Polaris repo at ZJU-REAL/Polaris, set up a direction library for <research topic> and run cold start from the anchor papers <paper list>. Expected output: a count of ingested papers and a list of compiled wiki pages. Verify that each wiki page links to at least one concept backlink.

  • Run a GPU experiment on your lab server with a Voyage

    Let an experiment Voyage plan, code, smoke-test and iterate over SSH under budget caps.

    View prompt
    Using the Polaris repo at ZJU-REAL/Polaris, start an experiment Voyage on the GPU server <server name> for the study <study description>. Expected output: a completed run with metrics, logs and figures. Verify that every remote write was approved through the gate and that the budget caps were not exceeded.

  • Fact-check a draft paper's citations and numbers

    Verify each citation for existence and support, and check every number against the experiment record.

    View prompt
    Using the Polaris repo at ZJU-REAL/Polaris, run Paper Review on the manuscript <paper project name>. Expected output: a citation report with existence and support labels and a number fact-check list. Verify that any citation marked fabricated is removed or fixed before the paper is marked as passing.

  • Query your research library from Claude Code or Cursor

    Expose Polaris's read-only tools as an MCP server so coding agents can search your knowledge base.

    View prompt
    Using the Polaris repo at ZJU-REAL/Polaris, connect the MCP server for project <project name> to <claude-code, codex or cursor>. Expected output: the agent lists papers from that project that match the query <search query>. Verify that the results come only from the chosen project and that no write tool was called.

Quick start with Polaris

  1. Check you have what it needs: A computer where the Polaris desktop app can run (the README says new releases are desktop-only); A model source: an agent you already use, such as Claude Code, Codex or Gemini CLI, or a model API key; For experiments: SSH access to a GPU server and your own SSH credentials.
  2. Open ZJU-REAL/Polaris on GitHub and read the README and license.
  3. Open the Polaris desktop app and create a direction library, then write its inclusion statement, goals and exclusions through the AI interview.
  4. Add anchor papers so cold start can snowball citations from them into the library.
  5. Let the Research Wiki ingest papers from OpenAlex, Semantic Scholar and arXiv and extract full text.
  6. Open the compiled wiki pages and check the TL;DR, method and concept links for a few papers.

These steps come from our top use case, Build a cross-linked wiki for a research direction, which also has a copy-paste agent prompt.

Use this in your AI agent

Ask your agent

Using the Deduped MCP, get the setup steps for ZJU-REAL/Polaris

Add Deduped to Claude Code once

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

Cursor, ChatGPT, others

Polaris alternatives · Best AI repos for Research

About this repo

  • Who it is forBuilt for a single researcher working on their own computer who wants to run long research tasks that can be paused, resumed and checked.
  • Why it is hot261 stars
  • LanguagePython
  • Sourcegithub.com/ZJU-REAL/Polaris · Back to Hot repos

Requirements

  • A computer where the Polaris desktop app can run (the README says new releases are desktop-only)
  • A model source: an agent you already use, such as Claude Code, Codex or Gemini CLI, or a model API key
  • For experiments: SSH access to a GPU server and your own SSH credentials
  • A research direction or topic you want to explore

Add this badge to your README

Maintain Polaris? Show readers where to find these use cases. Use cases on Deduped

Markdown 

[![Use cases on Deduped](https://dedupedai.com/badge/ZJU-REAL/Polaris.svg)](https://dedupedai.com/use-cases/zju-real-polaris/?utm_source=github&utm_medium=badge&utm_campaign=ZJU-REAL-Polaris)

HTML 

<a href="https://dedupedai.com/use-cases/zju-real-polaris/?utm_source=github&amp;utm_medium=badge&amp;utm_campaign=ZJU-REAL-Polaris"><img src="https://dedupedai.com/badge/ZJU-REAL/Polaris.svg" alt="Use cases on Deduped" height="20"></a>

A static image, no tracking script. About the badge

Questions about Polaris

What is Polaris?

Polaris is a desktop app that runs the full AI research lifecycle locally, from literature survey and idea generation through GPU experiments, LaTeX paper writing, and paper review. It is an open-source project on GitHub: https://github.com/ZJU-REAL/Polaris.

How do I use Polaris?

Open the Polaris desktop app and create a direction library, then write its inclusion statement, goals and exclusions through the AI interview; then add anchor papers so cold start can snowball citations from them into the library; let the Research Wiki ingest papers from OpenAlex, Semantic Scholar and arXiv and extract full text. The use cases on this page give the full steps and a copy-paste agent prompt for each job.

Who is Polaris for?

Built for a single researcher working on their own computer who wants to run long research tasks that can be paused, resumed and checked.

What can I do with Polaris?

4 use cases so far, for example: Build a cross-linked wiki for a research direction; Run a GPU experiment on your lab server with a Voyage; Fact-check a draft paper's citations and numbers. Each has steps and a copy-paste agent prompt.

What do I need to run Polaris?

A computer where the Polaris desktop app can run (the README says new releases are desktop-only); A model source: an agent you already use, such as Claude Code, Codex or Gemini CLI, or a model API key; For experiments: SSH access to a GPU server and your own SSH credentials; A research direction or topic you want to explore.

What are alternatives to Polaris?

Other hot AI repos in Research: Scientific Agent Skills, PersonaPlex, PageIndex, Book to Skill, Scientific Figure Library.

Is Polaris safe to run?

Deduped does not own, audit or vouch for it. Read the README and license, run it on your own systems first and review every command before you run it.