Auto-claude-code-research-in-sleep
Lightweight Markdown-only skills for autonomous ML research
GraphCanon updated today · GitHub synced today · 26 views this month
Decision brief
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.
Good fit when
- 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
Avoid when
- 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
- Pricing:
- 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.
- Requirements:
- 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
Observed Jul 15, 2026 · Source: enrich:decision_facts
Verify the decision
Maintenance and security
Full trust report- Maintenance
- Very active (1d since push)
- As of today
- Provenance
- Not a fork · Personal account
- As of today
- Security (OSV)
- No lockfile
- As of 3d
Public GitHub metadata and optional OSV scans. Signals, not a guarantee. Trust methodology.
Install
pip install Auto-claude-code-research-in-sleepSimilar tools
Same-category neighbours. No typed graph edges are catalogued for this tool yet.
Evidence and technical details
Sourced facts, taxonomy, compatibility claims, README excerpt, and machine-readable endpoints.
Overview
ARIS provides cross-model review loops, idea discovery, and experiment automation, compatible with various LLM agents.
Capability facts
- Languages
- python
Source: github.language · Aug 26, 2026
Categories
Tags
README
1. Install skills — project-local symlinks (recommended)
git clone https://github.com/wanshuiyin/Auto-claude-code-research-in-sleep.git bash Auto-claude-code-research-in-sleep/tools/install_aris.sh ~/your-project # symlinks ARIS skills into /.claude/skills/
(prefer a global install instead? cp -r Auto-claude-code-research-in-sleep/skills/* ~/.claude/skills/)
(don't need all 82? --list-groups / --groups X,Y / --skills X — see "Selective install" below)
Optional Codex mirror managed project install
bash tools/install_aris_codex.sh ~/your-codex-project
10.2 Install Skills
💡 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.txttracks what ARIS installed — uninstall and reconcile only ever touch managed entries, never your own skills.🤖 Codex mirror route: keep Claude on
install_aris.sh/smart_update.sh. For Codex-native project installs, useinstall_aris_codex.sh; for copied Codex installs, usesmart_update_codex.sh.
---
# Install only what you need (#366 selective install; a bare TTY run opens a checkbox picker):
bash ~/aris_repo/tools/install_aris.sh --list-groups # show the 10-group catalog
bash ~/aris_repo/tools/install_aris.sh --groups paper-core,lit-search # install by group
bash ~/aris_repo/tools/install_aris.sh --skills paper-writing # by skill; hard pipeline deps auto-included
bash ~/aris_repo/tools/install_aris.sh --exclude patent-pipeline # opt out (declined; never re-asked on update)
---
# Symlink-style legacy install:
bash ~/aris_repo/tools/install_aris.sh ~/your-project --from-old
---
# Copy-style legacy install (with possible local edits — chose strategy explicitly):
bash ~/aris_repo/tools/install_aris.sh ~/your-project --from-old --migrate-copy keep-user
---
# → keeps your nested .claude/skills/aris/ copy intact alongside the new flat install
bash ~/aris_repo/tools/install_aris.sh ~/your-project --from-old --migrate-copy prefer-upstream
For agents
This page has a .md twin and JSON over the API.