wanshuiyin
Yang Ruofeng Joined Jan 2021 425 followers View on GitHub
- Stars
- 20,967
- across 15 public repos
- Rank
- #1,183
- of 327,612 users, top 0.4%
- Up 39 places this week
Repositories with 50+ stars
| Rank | Repository | Language | Stars |
|---|---|---|---|
| 2,493 | 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 —... | Python | 19,038 |
| 79,139 | HERO = Hashing · Edge cases · Rubrics · Overbuild — the four shapes coding agents over-defend in. A paste-in contract that stops them. Works with Claude Code, Codex, Antigravity, Cursor, Copilot,... | Python | 829 |
| 98,934 | Bilingual (中文+EN) ML / LLM / diffusion / agent interview cheat sheets for AI 秋招 — generated by ARIS /interview-cheatsheet, rendered by /render-html into single-file HTML, reads anywhere — plus a... | Python | 651 |
| 300,951 | Don't trust an autoresearch paper at face value. Reviewer-side integrity forensics (self-consistency + fabrication), deterministic verdict. 61 signals: 46 integrity hack-patterns (families A–H,... | Python | 181 |
| 552,769 | SuperARIS — Your personal research agent with ARIS (Auto Research In Sleep), powered by a team of agents. | Python | 85 |
| 597,949 | Agentic, long-horizon visual generation: a fuzzy story → a cross-model-audited image-based movie. Brings ARIS's research-wiki + multi-agent debate to multimodal generation (intelligence lives in... | Python | 77 |
| 746,444 | Generalizing ARIS from 科研 to 研究 — same five-step loop (plan · draft · adversarial review · iterate · persist) applied beyond academic research to investment DD, legal, market, self-directed... | Markdown | 58 |
| 839,060 | Agentic loop image generation without diffusion or autoregressive image models. Coding agents draw in p5.js, using iterative refinement and adversarial visual review for high-fidelity art and... | HTML | 50 |
Among 327,612 users
16k–25k stars: 808 users, including wanshuiyin
Stars along the bottom, and users in each band on a log scale
Where the stars are
Languages
- Python 20.9k stars, 99% · 6 repos
- Markdown 58 stars, <1% · 1 repo
- HTML 50 stars, <1% · 1 repo
When they were made
8 repos with 50+ stars, made in 2026
Quick stats
- Next rank
- +24 stars to reach #1,182
- Next milestone
- +28,655 stars to reach the top 0.1%
- Public repos
- 15, 8 with 50+ stars
- Popular repos
- 1 over 1k stars, 1 over 10k stars
- Top repo
- Auto-claude-code-research-in-sleep, #2,493 of all repos, 91% of stars