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: · · ·
❗ 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 point at Fable 5.1 (default stays Opus 5). v0.4.25: the Codex reviewer works again on codex-cli ≥ 0.154 (built-in codex exec bridge, nothing to register), /since takes you back to your last input, /resume lists sessions by index, Windows multi-line paste fixed (pending confirmation), 83 bundled skills on GPT-6-Astra.
v0.4.28 (2026-09-28) —
ARIS_REASONING_EFFORTnow works on the Anthropic channel (#446):low/medium/high/xhigh/maxfor the main session and subagents; unset, requests are unchanged.ARIS_MAX_TOKENSraises the output cap when a high effort runs into it.autoCompactEnabled: falsein settings turns automatic compaction off. 🐛 #444 tool calls through relays that send a{}placeholder no longer fail withinvalid tool input JSON. 🌐 System proxy on Windows / macOS is used without exportingHTTPS_PROXY(#401, by @JasmineLCY);NO_PROXY=*connects directly as before. Upgrading: if you already exportARIS_REASONING_EFFORT, have an OS proxy, or haveautoCompactEnabled: falsein settings, read the upgrade notes.v0.4.27 (2026-09-19) — launching and quitting the REPL no longer leaves an empty session file;
/resumelists only sessions with messages (#439 follow-up).v0.4.26 (2026-09-16) — Fable 5.1: the
fablealias now resolves toclaude-fable-5-1,/modellists Fable 5.1 first (Fable 5 stays selectable) and the system-prompt identity names it; the default executor remainsclaude-opus-5(the Mythos tier is $10/$50 vs Opus 5's $5/$25, so the default does not move). Savedexecutor_modelvalues are ids, not aliases, and are untouched. Pricing already matched onfable; a test pins 5.1. Tests unchanged (aris-cli 225 + 4 e2e / runtime 252 / tools 71 / commands 6). Codex MCP (gpt-6-astra xhigh) gate: GO.v0.4.25 (2026-09-16) — the reviewer-bridge release. codex-cli 0.154 removed
codex mcp-server, the entry point ARIS-Code'saris setuphad written into settings.json for every Codex review; on an updated codex every review call died. : / run as with nothing to register — no settings entry, a legacy entry is migrated in memory (env, defaults, , trust kept), an explicit Python-bridge entry is used as configured, thread records share with the Python bridge, 1800 s budget for audits, restores the old path; prints the effective backend. Found on the way: the model never received a Codex result's (it lives only in ), so could not continue a thread — results now start with a line. replays the user's last input and everything after it with the live formatters (display only; after and in batch mode too); a dim hint after turns with ≥ 8 tool calls (). Windows consoles deliver no paste event, so each pasted line became its own Enter — lines are now merged into the input and never auto-submitted, Ctrl+C discards the rest (; inferred from crossterm's source, pending confirmation on a Windows machine). lists sessions with indices and ages and accepts an index, a unique id prefix or a path; the last turn is replayed after loading. the -shim message carries the official native installer one-liner. (pin 3e49e63 → 4734364): , , 32 helpers (+, , ), repo-root bundled; reviewer doctrine and system prompt on (fallback gpt-5.6-sol → gpt-5.5), explicit directives win, results carry so HTTP rounds report to truthfully; gpt-6-astra pricing tier $10/$50 (cache write $12.50, read $1). Tests: api 35+6 / aris-cli 225 + 4 e2e / runtime 252 / tools 71 / commands 6, all green; live fresh + resume roundtrip on codex-cli 0.154.0. Codex MCP (gpt-6-astra): ultra design gate (2 rounds), xhigh implementation gate per step (5/2/2/2 rounds), final whole-diff gate (2 rounds) → GO.
中文版 README | English
🌙 Let Claude Code do research while you sleep. Wake up to find your paper scored, weaknesses identified, experiments run, and narrative rewritten — autonomously.
🪶 Radically lightweight — no infrastructure, zero lock-in. The entire skill layer is plain Markdown files. No framework to learn, no database to maintain, no Docker to configure, no daemon to babysit. Every skill is a single
SKILL.mdreadable by any LLM — swap Claude Code for Codex CLI, OpenClaw, Cursor, Trae, Antigravity, Copilot CLI, Windsurf, or your own agent and the workflows still work. Fork it, rewrite it, adapt it to your stack.
💭 Why not self-play with a single model? Using Claude Code subagents or agent teams for both execution and review is technically possible, but tends to fall into local minima — the same model reviewing its own patterns creates blind spots.
Think of it like adversarial vs. stochastic bandits: a single model self-reviewing is the stochastic case (predictable reward noise), while cross-model review is adversarial (the reviewer actively probes weaknesses the executor didn't anticipate) — and adversarial bandits are fundamentally harder to game.
💭 Why two models, not more? Two is the minimum needed to break self-play blind spots, and 2-player games converge to Nash equilibrium far more efficiently than n-player ones. Adding more reviewers increases API cost and coordination overhead with diminishing returns — the biggest gain is going from 1→2, not 2→4.
Claude Code's strength is fast, fluid execution; Codex (GPT-6-Astra xhigh) is slower but more deliberate and rigorous in critique. These complementary styles — speed × rigor — produce better outcomes than either model talking to itself.
🧿 Want the strongest possible reviewer? Add
— reviewer: oracle-proto any skill to route reviews through GPT-5.5 Pro via Oracle MCP. Pro-level reasoning for proof verification, experiment auditing, and final stress tests. Works with API key or free browser mode. Setup →
Contents
- More Than Just a Prompt
- What's New · changelog
- Quick Start · install + first run
- Features
- Score Progression (Real Run)
- Community Showcase — Papers Built with ARIS
- Awesome Community Skills & Extensions
- Workflows · 13 named pipelines (W1 / W1.5 / W2 / W3 / W4 / W5 / W6 / Wiki / WM + Effort / Assurance / Oracle)
- Setup · prerequisites / install / update / usage / GPU server config
- Customization · per-skill config knobs
- Alternative Model Combinations · GLM / MiniMax / Kimi / etc.
- Community
- Citation
- Star History
- Acknowledgements
- License
1. 🎯 More Than Just a Prompt
These are full pipelines — you can also use each workflow independently. Already have an idea? Skip to Workflow 1.5. Have results? Jump to Workflow 3. Got reviews? Jump to Workflow 4. Want persistent memory? Enable Research Wiki. See Quick Start for all commands and Workflows for the full breakdown.
Basic mode — give ARIS a research direction, it handles everything:
/research-pipeline "factorized gap in discrete diffusion LMs"
🔥 Targeted mode — got a paper you want to improve? Give ARIS the paper + the code:
/research-pipeline "improve method X" — ref paper: https://arxiv.org/abs/2406.04329, base repo: https://github.com/org/project
ARIS reads the paper → finds its weaknesses → clones the codebase → generates ideas that specifically fix those weaknesses with that code → runs experiments → writes your paper. Like telling a research assistant: "read this paper, use this repo, find what's missing, and fix it."
Mix and match:
ref paperonly = "what can be improved?",base repoonly = "what can I build with this code?", both = "improve this paper using this code."
🛠️ Build a feature — already know what to build?
/research-implement-feature "add KV-cache reuse to the decoder" — base repo: https://github.com/org/project
Spine first, then one feature at a time, each with a runnable check. Every choice the request left open is written to an assumption ledger before the code that depends on it, and a different model family then reads the raw diff for the ones that went undeclared. It reports "the checks passed", never "the method works". Contributed by @heroarmor.
🔥 Rebuttal mode — reviews just dropped? Don't panic. ARIS reads every concern, builds a strategy, and drafts a rebuttal that's grounded, structured, and under the character limit:
/rebuttal "paper/ + reviews" — venue: ICML, character limit: 5000
Three safety gates — rebuttal will NOT finalize if any fails:
- 🔒 No fabrication — every claim maps to paper/review/user-confirmed result
- 🔒 No overpromise — every promise is user-approved
- 🔒 Full coverage — every reviewer concern is tracked
Two outputs: PASTE_READY.txt (exact char count, paste to venue) + REBUTTAL_DRAFT_rich.md (extended version for manual editing).
After acceptance — your paper is in, now prepare the presentation:
/paper-slides "paper/" # → Beamer PDF + PPTX + speaker notes + Q&A prep
/paper-poster-html "paper/" # → measurement-gated HTML/CSS poster → print-ready PDF
💡 From idea to paper to podium — one toolchain. 🌱
2. 📢 What's New
⚠️ Any entry that touches skills:
bash tools/smart_update.sh --applypulls it.
- 2026-10-07 — 🧮 From a mathematical statement to a checked Lean proof — new
/lean-formalizefor Claude Code and Codex. Develop proof routes, connect intermediate lemmas to the original theorem, and deliver reproducible Lean sources with statement and axiom checks. Cross-family reviews target the statement, key arguments, and final assembly. Integrated into five proof/research skills; use it when requested or a concrete proof obligation benefits from formal verification. (#461) - 2026-10-05 — 🔌 New Grok and Gemini / Antigravity MCP bridges — use your existing CLI login to read files and resume conversations from Claude Code or Codex. (#454)
- 2026-09-28 — 📚 Real papers stop being reported as hallucinated citations (#445, #447, #450; thanks @ilya-pershin and @AfonsoZhang). arXiv sometimes refuses Python's HTTP client with a 406 for minutes while
curlgets through;verify_papers.pyread that refusal as "paper not found" and one user saw a 47% hallucination rate on 38 real papers. A 406 now goes throughcurl, and a refusal (406 / 401 / 403) isverify_pending, neverunverified. SetSEMANTIC_SCHOLAR_API_KEYand title checks use it. Seen a suspicious hallucination rate recently? Re-run with--no-cacheonce. Also in this round: five skills can now actually invoke the sub-skills their text tells them to (#440, ); concurrent watchdog registrations no longer overwrite each other (, ); is described as the regular reviewer tier it is (, ).
-
2026-09-07 — 🧠 Default reviewer is now
gpt-6-astra. Every reviewer call that pinnedgpt-5.6-solnow pinsgpt-6-astra; the two effort tiers (ultra for the seven deep audits, xhigh everywhere else) are unchanged, and so is the executor — whatever agent you run ARIS in. No access to the model yet? The capability fallback triesgpt-5.6-sol, thengpt-5.5, both at xhigh — nothing to configure. -
2026-09-06 — 🧹 The installer stops dropping Copilot profiles into every project (#431, thanks @oblivion-1521). Since 2026-08 every run symlinked two Copilot reviewer profiles into your
.github/agents/whether or not anything used them — dead files for Claude Code and Codex users, broken links if you committed them. Now they are deployed only whileauto-review-loopis installed;--no-agent-profilesswitches them off for good (undo with--agent-profiles). Your next re-run removes the links the installer created earlier; files you wrote yourself are never touched. -
2026-09-03 — 📣 Papers are launches, not progress reports (rules adopted from anti-defensive-writing-Skill by @Adkid-Zephyr — 🌟 it). The writing contract gains four rules: organize the narrative around the strongest genuine advantage; pick the contest the paper wins; unfavorable numbers stay in the tables, explained as a tradeoff where the evidence supports that and stated neutrally where it does not — never narrated as a defeat; every experiment carries an argumentative duty or leaves the main line; abstract and introduction open with problem → gap → idea → strongest result, and the conclusion never ends on new self-negation.
/auto-paper-improvement-loopflags the same defects. Indexed under Awesome Community Skills. -
2026-08-26 — 🧯 Two over-defense leftovers (#425).
/research-review— the one reviewer prompt that never got the scope-limits block — now carries it, and its brief ends with "if the work holds up, say so clearly" instead of bare brutality; the adversarial stance itself is untouched. no longer dies overnight on a missing : ideas, experiments, analysis and the narrative report are venue-independent and run to completion — only paper formatting defers, stamped clearly for a later resume. It had also been declaring while forbidding silent defaults; the default is gone.