{"data":{"slug":"wanshuiyin-auto-claude-code-research-in-sleep","name":"Auto-claude-code-research-in-sleep","tagline":"Lightweight Markdown-only skills for autonomous ML research","github_url":"https://github.com/wanshuiyin/Auto-claude-code-research-in-sleep","owner":"wanshuiyin","repo":"Auto-claude-code-research-in-sleep","owner_avatar_url":"https://avatars.githubusercontent.com/u/76990859?v=4","primary_language":"Python","stars":15233,"forks":1336,"topics":["ai-research","ai-tools","aris","autonomous-agent","claude","claude-code","claude-code-skills","codex","deep-learning","gpt","idea-generation","llm","machine-learning","mcp","mcp-server","ml-research","openai","paper-review","paper-writing","research-automation"],"archived":false,"github_pushed_at":"2026-08-24T04:19:41+00:00","maintenance_label":"Very active","stars_delta_30d":1358,"url":"https://www.graphcanon.com/tools/wanshuiyin-auto-claude-code-research-in-sleep","markdown_url":"https://www.graphcanon.com/tools/wanshuiyin-auto-claude-code-research-in-sleep.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/wanshuiyin-auto-claude-code-research-in-sleep","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=wanshuiyin-auto-claude-code-research-in-sleep","description":"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.","homepage_url":null,"license":"MIT","open_issues":63,"watchers":21,"ai_summary":"ARIS provides cross-model review loops, idea discovery, and experiment automation, compatible with various LLM agents.","readme_excerpt":"# 1. Install skills — project-local symlinks (recommended)\ngit clone https://github.com/wanshuiyin/Auto-claude-code-research-in-sleep.git\nbash Auto-claude-code-research-in-sleep/tools/install_aris.sh ~/your-project   # symlinks ARIS skills into <project>/.claude/skills/\n\n---\n\n# (prefer a global install instead? cp -r Auto-claude-code-research-in-sleep/skills/* ~/.claude/skills/)\n\n---\n\n# (don't need all 82? --list-groups / --groups X,Y / --skills X — see \"Selective install\" below)\n\n---\n\n# Optional Codex mirror managed project install\nbash tools/install_aris_codex.sh ~/your-codex-project\n\n---\n\n### 10.2 Install Skills\n\n> 💡 **Recommended: project-local flat symlink install** (since 2026-04-20). Each ARIS skill is symlinked individually into `.claude/skills/<skill-name>`, so Claude Code's slash-command discovery picks them up. A manifest at `.aris/installed-skills.txt` tracks what ARIS installed — uninstall and reconcile only ever touch managed entries, never your own skills.\n>\n> 🤖 **Codex mirror route:** keep Claude on `install_aris.sh` / `smart_update.sh`. For Codex-native project installs, use `install_aris_codex.sh`; for copied Codex installs, use `smart_update_codex.sh`.\n\n```bash\n\n---\n\n# Install only what you need (#366 selective install; a bare TTY run opens a checkbox picker):\nbash ~/aris_repo/tools/install_aris.sh --list-groups                  # show the 10-group catalog\nbash ~/aris_repo/tools/install_aris.sh --groups paper-core,lit-search # install by group\nbash ~/aris_repo/tools/install_aris.sh --skills paper-writing         # by skill; hard pipeline deps auto-included\nbash ~/aris_repo/tools/install_aris.sh --exclude patent-pipeline      # opt out (declined; never re-asked on update)\n\n---\n\n# Symlink-style legacy install:\nbash ~/aris_repo/tools/install_aris.sh ~/your-project --from-old\n\n---\n\n# Copy-style legacy install (with possible local edits — chose strategy explicitly):\nbash ~/aris_repo/tools/install_aris.sh ~/your-project --from-old --migrate-copy keep-user\n\n---\n\n#   → keeps your nested .claude/skills/aris/ copy intact alongside the new flat install\nbash ~/aris_repo/tools/install_aris.sh ~/your-project --from-old --migrate-copy prefer-upstream","github_created_at":"2026-03-10T07:31:45+00:00","created_at":"2026-07-11T11:49:06.015549+00:00","updated_at":"2026-08-26T00:02:24.321298+00:00","categories":[{"slug":"ai-agents","name":"AI Agents","url":"https://www.graphcanon.com/categories/ai-agents","markdown_url":"https://www.graphcanon.com/categories/ai-agents.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/ai-agents"},{"slug":"developer-tools","name":"Developer Tools","url":"https://www.graphcanon.com/categories/developer-tools","markdown_url":"https://www.graphcanon.com/categories/developer-tools.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/developer-tools"},{"slug":"evaluation-observability","name":"Evaluation & Observability","url":"https://www.graphcanon.com/categories/evaluation-observability","markdown_url":"https://www.graphcanon.com/categories/evaluation-observability.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/evaluation-observability"}],"tags":[{"slug":"ai-research","name":"ai-research"},{"slug":"autonomous-agent","name":"autonomous-agent"},{"slug":"idea-generation","name":"idea-generation"},{"slug":"ml-research","name":"ml-research"},{"slug":"research-automation","name":"research-automation"}],"trust":{"provenance":{"is_fork":false,"github_id":1177608268,"owner_type":"User","methodology":"github_public_v1","parent_repo":null,"near_duplicate_slugs":[]},"computed_at":"2026-08-26T00:02:23.577Z","maintenance":{"label":"Very active","score":96,"methodology":"github_public_v1","releases_90d":11,"days_since_push":1,"last_release_at":"2026-08-21T08:00:00Z","stars_delta_30d":1358,"open_issues_delta_30d":3},"security_summary":{"status":"no_lockfile","scanner":null,"low_count":0,"high_count":0,"last_scan_at":"2026-08-23T04:00:15.187Z","medium_count":0,"scan_profile":"none","critical_count":0}},"capability_facts":{"scan":{"source":"repo_scan","observed_at":"2026-08-26T00:02:24.017Z"},"languages":{"value":["python"],"source":"github.language","observed_at":"2026-08-26T00:02:24.017Z"},"license_spdx":{"value":"MIT","source":"github.license","observed_at":"2026-08-26T00:02:24.017Z"}},"decision_facts":{"hosting":null,"pricing":{"model":"freemium","summary":"Free to use under MIT license with no explicit pricing model indicated, though users might incur costs based on the AI models and services they choose to integrate."},"requirements":{"notes":["Compatibility with diverse language model agents without requiring lock-in or specific frameworks","Utilizes Markdown for skills, aiming at a lightweight automation layer on top of ML research tasks"],"min_ram_gb":null,"requires_docker":false},"constraints":{"min_ram_gb":null,"pricing_model":"freemium","requires_docker":false},"when_to_use":["When you are looking to streamline idea discovery, experiment automation, and cross-model review loops specifically within the context of Python programming for machine learning research","For users interested in leveraging an open-agent model system that allows flexibility with different LLM agents like Claude Code or Codex, without framework lock-in"],"when_not_to_use":["If you require a solution that is tightly integrated with a specific AI development platform or requires the use of proprietary models","When your research workflow demands real-time data analysis and visualization tools that Auto-claude-code-research-in-sleep does not directly support"],"source":"enrich:decision_facts","observed_at":"2026-07-15T09:04:15.784Z"},"constraint_facets":{"min_ram_gb":null,"pricing_model":"freemium","requires_docker":false},"decision_summary":[{"label":"Pricing","value":"freemium - Free to use under MIT license with no explicit pricing model indicated, though users might incur costs based on the AI models and services they choose to integrate."},{"label":"Requirements","value":"Compatibility with diverse language model agents without requiring lock-in or specific frameworks; Utilizes Markdown for skills, aiming at a lightweight automation layer on top of ML research tasks"},{"label":"Adopt for","value":"Auto-claude-code-research-in-sleep provides specialized Markdown-based utilities for automating and enhancing autonomous ML research by connecting various models in an open framework."},{"label":"License detail","value":"MIT License, allowing for broad usage without restrictions on commercial use."}]}}