wanshuiyin /Auto-claude-code-research-in-sleep

ARIS ⚔️ (Auto-Research-In-Sleep) — Lightweight Markdown-only skills for autonomous ML research: cross-model review loops, idea discovery, and experiment automation. No framework, no lock-in — works with Claude Code, Codex, OpenClaw, or any LLM agent.

★ 19,243⑂ 1,548👁 27⑃ 321● 162▤ 46
PythonMITCreated 2026-03-10
Download: v0.4.28v0.4.28 ↓0.4.282026-09-28
+46
Daily
19,243
stars
1,548
forks
27
watchers
321
prs
162
issues
46
releases

README

Auto-claude-code-research-in-sleep (ARIS ⚔️🌙)


  
    
  


 ·  ·  ·  ·  ·  ·  ·  · 💬 Join Community · 

🌱 ARIS is a methodology, not a platform. What matters is the research workflow — take it wherever you go.

💡 Use ARIS as a skill-based workflow in Claude Code / Codex CLI / Cursor / Trae / Antigravity / GitHub Copilot CLI / OpenClaw / DeepSeek Harness — enjoy any way you like!The executor drives, an independent model (Codex MCP by default) reviews. Alternative model combinations, including ModelScope-hosted models, need no Claude or OpenAI API.

📦 Those are the skills installed directly. Want it in one command? ARIS also ships as a standalone CLI and as plugins:  ·  ·  · 

🤝 SuperARIS — Your personal research agent with ARIS, powered by a team of agents.

Put ARIS workflows in the hands of a persistent team: your main agent coordinates, while engineering and writing run in parallel. Every member can read ARIS skills and project context on demand. Work directly with Codex on experiments and Gemini on ideas and writing, or choose an all-Codex team. The main agent follows up on deliverables; project files carry memory across sessions. Your existing MCP workers and independent reviewers stay in the loop.

Homepage · GitHub



Demo preview · click to watch the full 1080p video (~21 seconds).

❗ !IMPORTANT codex-cli 0.154.0 removed codex mcp-server — the entry point every ARIS reviewer call used. No impact on ARIS: the codex MCP server is now ARIS's own bridge over codex exec (mcp-servers/codex-exec/), same tools, same results, all 82 skills unchanged, ultra and per-thread resume intact. One re-registration is all it takes — already installed? → Quick Start step 2b · new install → step 2 · what changed.

🧩 The ARIS family — same method, other jobs. One line each; the details live in their own repos.

 — EasyAIOffer: 34 bilingual ML / LLM interview cheat sheets on one page — derivations, from-scratch PyTorch, 25 questions each. 希望大家秋招轻松一点 🌱

 ·  — two sides of one disease. HERO: a ~550-token block for CLAUDE.md / AGENTS.md against the four shapes agents over-defend in (Hashing, Edge cases, Rubrics, Overbuild), bounding what the agent proposes, never what it looks for. Anti-Autoresearch: 61 integrity signals into a deterministic, reviewer-ready report — fabrication forensics, not an AI-text detector.

 — ARIS goes multimodal: a rough story in, a movie told in still frames out, every scene checked by another model; the same loop draws clean method diagrams (/method-figure).

 — a tiny always-on-top macOS widget that lights up 🔴 when a session waits for your approval; cd aris-monitor && ./run.sh. Many windows? Claude Fleet by @tianyilt is the full dashboard.

🔥 ARIS-Code CLI — 独立安装版 · English | ⬇️ Download ·  — v0.4.28: ARIS_REASONING_EFFORT works on the Anthropic channel, tool calls through {}-placeholder relays fixed, OS proxy honoured. v0.4.27: launching and quitting the REPL leaves no empty session file. v0.4.26: the fable alias and /model now poin

Top issues

Latest release

v0.4.28 v0.4.28 2026-09-28
What's Changed
 fix(aris-cli): honor Windows and macOS system proxies by @JasmineLCY in https://github.com/wanshuiyin/Auto-claude-code-research-in-sleep/pull/401


Full Changelog: https://github.com/wanshuiyin/Auto-claude-code-research-in-sleep/compare/v0.4.27...v0.4.28

Snapshot: 2026-11-16T09:23:14Z · Data license Apache-2.0 · JSON