# yeyuxin777/baoyan-agent-benchmark

> An open benchmark of 70 Chinese-language tasks for evaluating AI agents in graduate admissions advising and application planning, with rubrics and reference programs.

- Magnitude: 1.8 out of 10 — Steady
- Stars: 127 total · +20 stars measured 2026-10-13, 17:36–20:11 UTC, ≈ 23 by evening
- Star trust: star growth looks organic
- Category: AI agents · Language: Python · License: MIT · Created: 2026-10-12 · Last push: 2026-10-13
- GitHub: https://github.com/yeyuxin777/baoyan-agent-benchmark · Page: https://gitnova.dev/en/r/yeyuxin777/baoyan-agent-benchmark

## Useful for

- Run the benchmark to compare agent configurations on graduate admissions tasks
- Evaluate how an agent updates advice when student information changes in two-stage tasks
- Check recommendation quality against rubrics and reference programs

## Why it’s here

- Star-counter measurements on 2026-10-13 (UTC), 17:36–20:11: 107 → 127 stars (+20). This is the change over that interval.
- Estimated end-of-day forecast: about +23 stars, using observed gains and the previous day.
- The repository is 1 day old and already has 127 stars. With less than two weeks of history, there's no usual pace to compare the spike against yet.
- Top new repositories this week: #169.

## Star trust

Star growth looks organic.

Star-trust labels are heuristics based on the repository’s behavior, not a check of every stargazer.

## Numbers

- Forks: 0
- Issues and pull requests: 0
- Watchers: 0
- Average over the last week: 12 per day
- Usual pace: too little history (under two weeks)
- Stars in the last hour (measured): 0

## Stars per day, last 2 days (oldest → newest, today is partial)

2026-10-12 … 2026-10-13: 0, 20

## Spotted in now

- Top new repositories this week: #169

## More in this category

1. **morluto/rea** — 9.5 · Breakout · AI agents · TypeScript · +46,433 stars measured 2026-10-13, 00:01–20:01 UTC, ≈ 54,890 by evening
   A reverse-engineering tool that lets AI agents inspect apps and native binaries: it connects agents to Hopper or Ghidra via MCP and CLI, helping explain how a feature works and rebuild it in your own project.
   Full card: https://gitnova.dev/en/r/morluto/rea.md
2. **onehumanbeing/esp32-iphone-agent** — 8.0 · Early signal · AI agents · Python · +895 stars measured 2026-10-13, 00:01–20:01 UTC, ≈ 1,055 by evening
   Lets an AI model drive a real iPhone via an ESP32-S3: the screen is mirrored over AirPlay while the board emulates a USB mouse and keyboard. No Mac, Xcode, Apple developer account or jailbreak required.
   Full card: https://gitnova.dev/en/r/onehumanbeing/esp32-iphone-agent.md
3. **Alishahryar1/free-claude-code** — 7.6 · Breakout · AI agents · Python · +1,073 stars measured 2026-10-13, 00:01–20:01 UTC, ≈ 1,271 by evening
   A local proxy and Admin UI that connects 54 model providers (including free tiers) to 10 coding agents such as Claude Code, Codex, Cline and Aider. Lets you run agents with any model from terminal, IDE, browser or messenger.
   Full card: https://gitnova.dev/en/r/Alishahryar1/free-claude-code.md
4. **Gen-Verse/RSI-Anything** — 6.5 · Early signal · AI agents · HTML · +169 stars measured 2026-10-13, 00:01–20:01 UTC, ≈ 205 by evening
   A framework for recursive self-improvement of agents using world models: a propose → predict → select → evaluate → learn → retain loop applied to code repair, GUI tasks, lab planning, reaction optimization and immune science.
   Full card: https://gitnova.dev/en/r/Gen-Verse/RSI-Anything.md
5. **Fei2411/DeepSeek-Bot** — 6.5 · Breakout · AI agents · JavaScript · +300 stars measured 2026-10-13, 00:01–20:01 UTC, ≈ 356 by evening
   A DeepSeek Harness (DSH) plugin that turns DSH Web and Desktop into a multi-agent collaboration workspace, letting multiple agents communicate, coordinate and run in parallel.
   Full card: https://gitnova.dev/en/r/Fei2411/DeepSeek-Bot.md

---

Magnitude (0–10) measures how fast and how unusually interest in a repository is growing right now. It is not a quality score.
Days are UTC. “So far today” is a fact; “expected by the end of the day” is a forecast.
Summaries and use cases are written by an LLM (DeepSeek V4.1 Flash) from the README and may be inaccurate: verify specific claims (benchmarks, speed, hardware) in the repository itself.
Data as of 2026-10-13 20:17 UTC, updated every 30 minutes.