explaingit

wanshuiyin/aris-anything

12Audience · researcherComplexity · 3/5Setup · moderate

TLDR

ARIS-Anything extends the ARIS auto-research loop (plan, draft, adversarial AI review, iterate, save to wiki) beyond academia to any structured investigation: investments, legal research, medical literature, market analysis, and journalism.

Mindmap

mindmap
  root((aris-anything))
    Core Loop
      Plan the question
      Draft an answer
      Adversarial AI review
      Iterate on feedback
      Save to persistent wiki
    Domains
      Investment due diligence
      Legal research
      Medical literature
      Market and product research
      Journalism verification
    Built On
      ARIS skill library
      75 plus research skills
      Multi-AI model setup
    Platforms
      Claude Code
      Codex CLI
      Cursor
Click or tap to explore — scroll the page freely

Code map

Detail Auto

An interactive map of this repo's files and how they connect — its source is parsed live in your browser. Click Visualize to build it.

filefunction / class

Things people build with this

USE CASE 1

Run investment due diligence by feeding a research question through the ARIS adversarial AI loop and saving findings to a persistent wiki for future reference.

USE CASE 2

Conduct a medical literature review with automatic adversarial critique between two different AI models to catch gaps and biases in the analysis.

USE CASE 3

Apply the 75+ pre-built research skills from the ARIS library to structured tasks like market research, journalism source verification, or engineering post-mortems.

USE CASE 4

Use the plan-draft-review-iterate workflow for any knowledge-work domain with Claude and GPT alternating as critic and author.

Tech stack

ClaudeGPTClaude CodeCursor

Getting it running

Difficulty · moderate Time to first run · 30min

Requires API keys for at least two AI providers (e.g. OpenAI and Anthropic) to run the adversarial review loop between different models.

In plain English

This repository is an extension of a project called ARIS, which stands for Auto Research in Sleep. The original ARIS system was built to automate academic research: it takes a research question, drafts work using one AI model, then has a different AI model from a different company critique that work, and iterates until the output is solid. This repository, ARIS-Anything, explores applying that same loop to non-academic tasks. The five-step loop at the center is: plan the question, draft an answer, review it adversarially using a separate AI (for example, having Claude review something GPT wrote, or vice versa), iterate on the feedback, and then save the findings to a persistent wiki so future work builds on what was already learned rather than starting from scratch. The Chinese terms in the description capture the idea: the original ARIS covered academic science (one specific shape of inquiry), while this repo explores all other structured investigation. The domains the README maps out include investment due diligence, legal case research, medical literature reviews, market and product research, self-directed learning, journalism source verification, and engineering incident post-mortems. Each of these gets matched to specific named workflows from the main ARIS library, which contains 75 or more pre-built research skills. The main ARIS repo the project builds on already has around 10,000 GitHub stars and was featured as the top paper on HuggingFace Daily Papers. ARIS-Anything is positioned as the next expansion: same methodology, different application areas. Several domain-specific sibling repos are planned, including ones for long-form video generation, product requirement documents, design critique, and a benchmarking harness for measuring research agent performance. These are described as scheduled rather than promised, with code to follow. The codebase runs across seven or more platforms including Claude Code, Codex CLI, and Cursor. The README is also available in Chinese. This is primarily a conceptual and workflow repository: the value is in the structured methodology and the named skill library, not in a deployable application.

Copy-paste prompts

Prompt 1
Using the ARIS-Anything adversarial loop, research this question: 'What are the main risks of investing in B2B SaaS companies in the EU in 2025?' Have GPT draft the answer and Claude critique it, then iterate twice.
Prompt 2
Walk me through applying the ARIS-Anything plan-draft-adversarial-review-iterate loop to the legal question: 'What are the GDPR implications of storing EU user data in US data centers?'
Prompt 3
Apply the ARIS-Anything methodology to write a product requirements document for a mobile expense tracker app. Use two AI models in the adversarial review step and save the final output to the persistent wiki.
Open on GitHub → Explain another repo

← wanshuiyin on gitmyhub — every repo by this author, as a profile.

Verify against the repo before relying on details.