Auto-claude-code-research-in-sleep (ARIS ⚔️🌙)
-orange?style=flat){kind=icon}
💡 Use ARIS as a skill-based workflow in Claude Code / Codex CLI / Cursor / Trae / Antigravity / GitHub Copilot CLI / OpenClaw / DeepSeek Harness, or get the full experience with the standalone ARIS-Code CLI — enjoy any way you like!
🐋 On DeepSeek Harness it installs as one plugin: dsh plugin --profile web add dsh-aris — all 82 skills unchanged, Codex still the independent reviewer. Setup and limits on the dsh-aris branch.
🌱 ARIS is a methodology, not a platform. What matters is the research workflow — take it wherever you go.
🤖 AI agents: Read AGENT_GUIDE.md instead — structured for LLM consumption, not human browsing.
🛡️ ARIS audits its own output → now Anti-Autoresearch audits everyone's. 61 signals — 46 integrity hack-patterns in 8 families, 13 AI-style impressions, 2 advisory — checked end-to-end into a deterministic, reviewer-ready report. Self-consistency + fabrication forensics, not an AI-text detector.
🧱 ARIS's reviewer is good — and it also proposed hashes nobody reads → HERO is the contract that stops that. Hashing, Edge cases, Rubrics, Overbuild — the four shapes agents over-defend in, as a ~550-token block for CLAUDE.md / AGENTS.md.
It bounds what the agent proposes, never what it looks for.
🎬 ARIS goes multimodal → ARIS-Movie-Director — hand it a rough story and get back a movie told in still frames, checked scene by scene (the reference run has 19 scenes). Long stories usually break when the model forgets earlier details or judges its own work — so ARIS keeps a research-wiki for memory and has other models check every frame.
🧭 The same loop also makes clean method / flow diagrams — the figure above was made with it. Entry points in ARIS-Movie-Director: /movie-pipeline and /method-figure, the skill that made this figure.
🎯 准备 2026 AI 秋招？ → 🌐 ARIS-in-AI-Offer · GitHub repo · 中文 README —— 23 篇双语 ML / LLM / 多模态 / 生成式 / Agent 面试 cheat sheet，每篇 = 公式推导 + 从零 PyTorch + 25 高频面试题（L1 / L2 / L3），全部由 ARIS 的 /render-html 自动生成。希望大家秋招轻松一点 🌱
📝 Three long-form blogs, cross-model collaborative writing via /render-html — Continuous DLM — a representation-perspective survey (2026 H1) · Cosmos 3 — understanding + generation in one Transformer (MoT) · Diffusion × representation × manifold learning.
🛰 Keep an eye on your agent windows — Claude Fleet (by @tianyilt; local read-only dashboard for many parallel Claude Code / Codex windows, full-text transcript search — worth a ⭐), or the lighter built-in ARIS-Monitor (a tiny always-on-top macOS widget that lights up 🔴 when a session waits for your approval; click to jump there).
ARIS-Monitor — built-in, no clone / no pip / no browser:
cd aris-monitor && ./run.sh
# a borderless panel floats top-right; click a row to jump to that terminal
Claude Fleet — full web dashboard:
git clone https://github.com/tianyilt/claude-fleet
cd claude-fleet && bash run.sh
# open http://127.0.0.1:7878 in your browser
🚀 Beyond 科研 → 任何 "研究"：ARIS-Anything 把 ARIS 的五步 loop（plan