
A bounded guide to installing wanshuiyin/Auto-claude-code-research-in-sleep, verifying its Codex MCP reviewer bridge, and testing an initial research-wiki workflow before scaling compute.
Auto-claude-code-research-in-sleep (ARIS) provides a structured workflow for running autonomous machine-learning research inside Claude Code and Codex. The repository bundles 82 Markdown-only skills that guide an agent through literature review, idea generation, experiment logging, and manuscript drafting. The main architectural choice is an adversarial review loop: Claude Code acts as the primary executor while OpenAI's Codex CLI reviews intermediate outputs through a Model Context Protocol (MCP) server. 1skills/ directory. Each skill operates as a standalone instruction card with zero external database or daemon dependencies. Workflows feed into an append-only knowledge base called the Research Wiki (research-wiki/), which records literature summaries, generated hypotheses, and experimental results as interconnected Markdown notes. 2codex login. 2mactex on macOS or texlive-full on Linux) along with poppler to supply pdfinfo. If your initial testing focuses on idea discovery and paper reading, you can skip the TeX installation. 2git clone https://github.com/wanshuiyin/Auto-claude-code-research-in-sleep.git ~/aris_repocd ~/your-paper-project
bash ~/aris_repo/tools/install_aris.sh.claude/skills/, writes an installation manifest to .aris/installed-skills.txt, and configures CLAUDE.md. The manifest ensures that uninstallation or updates only touch files managed by ARIS, leaving custom project files intact. 2codex-cli 0.154 removed the built-in codex mcp-server command, ARIS provides its own execution server inside the repository:claude mcp remove codex -s user 2>/dev/null
claude mcp add codex -s user -- python3 "$HOME/aris_repo/mcp-servers/codex-exec/server.py"claude mcp list | grep codexcodex as connected. 2mkdir ~/test-aris-project && cd ~/test-aris-project
git init
touch CLAUDE.md
bash ~/aris_repo/tools/install_aris.sh~/test-aris-project. First, check that the cross-model bridge functions:Ask GPT via codex MCP: what is 1+1?/research-wiki initresearch-wiki/ folder structure, containing index.md, log.md, gap_map.md, and subdirectories for papers/, ideas/, and experiments/. 2/alphaxiv https://arxiv.org/abs/1706.03762research-wiki/papers/. 2/idea-discovery "mitigating catastrophic forgetting in low-rank adaptation fine-tuning"research-wiki/ideas/.research-wiki/ideas/. The document records both the proposed methodology and the reviewer's explicit counter-arguments. This dual perspective allows you to evaluate potential flaws before allocating GPU compute or writing code.Clear(UntilNewLine) only removes the trailing spinner characters while preserving rendered text. 3@oblivion-1521. Previous installer versions had automatically placed GitHub Copilot reviewer profiles into .github/agents/ for all projects, creating unnecessary configuration clutter for developers using Claude Code or Codex. The installer now only provisions these profiles when auto-review-loop is explicitly requested, and users can pass --no-agent-profiles to opt out entirely. 4docs/MODEL_COMBINATIONS.md, but navigating custom provider combinations requires manual editing of environment flags. 5/alphaxiv and /research-wiki init to explore the documentation format before connecting remote compute resources.| Field | Details |
|---|---|
| Pick | wanshuiyin/Auto-claude-code-research-in-sleep (ARIS), a cross-model research skill pack. 1 |
| Best for | Literature mapping, paper ingestion, hypothesis generation, and adversarial review loops. 1 |
| Primary hosts | Claude Code (executor) and Codex CLI (reviewer via MCP bridge). 2 |
| Install | Clone ~/aris_repo, run bash ~/aris_repo/tools/install_aris.sh, and register the Codex MCP bridge. 2 |
| Scope | 82 Markdown-only skills across idea generation, experiment logging, and LaTeX paper writing. 1 |
| License | MIT License for repository code and skill cards. 1 |
| First test | Run Ask GPT via codex MCP: what is 1+1?, initialize /research-wiki, and test /alphaxiv. 2 |
| Main caveat | Requires restarting Claude Code after MCP setup; custom model combinations require manual configuration. 25 |
| Adoption signal | 16.1k stars and active commits in September 2026. Weekly GitHub Trending did not list the repository. 1 |
github.com
github.com
このコンテンツはチャンネルが自動で生成しました。一言伝えるだけで、Neodrop があなたのために作り続けます。