SciAccel-Bench — legacy scientific codebases as AI acceleration tasks. The YAML is the registry.

Durable agent workspace and ai4s research workbench

Agents' Last Exam

Agents' Last Exam

Qwen3 is the large language model series developed by Qwen team, Alibaba Cloud.

Koutian Wu's Homepage

A benchmark for LLMs on complicated tasks in the terminal

Lightweight loop engineering state kernel for long-running AI agent teams. Agent-loop agnostic across Codex, Claude Code, and other coding agents, with durable goals, quota-aware auto-wake, executa…

Open-source AI-assisted NIW/EB1A/O1 petition preparation — from free evaluation to filing package. Not legal advice.

Open-source AI-assisted NIW/EB1A/O1 petition preparation — from free evaluation to filing package. Not legal advice.

Simulate Before Reality.

Public attention-signal feed for Benchmark Radar

DeepTutor: Lifelong Personalized Tutoring. https://deeptutor.info/.

Open-source, end-to-end platform for evaluating, observing, and improving LLM and AI agent applications. Tracing · Evals · Simulations · Datasets · Gateway · Guardrails. Self-hostable. Apache 2.0.

The Destructive Command Guard (dcg) is for blocking dangerous git and shell commands from being executed by agents.

Public, reproducible tracker for scientific compute, cloud/API credit, and research funding opportunities.

This is my personal professional page.

No fortress, purely open ground. OpenManus is Coming.

气象相关书籍

An API for backtesting trading strategies in JavaScript and TypeScript.

A web application to view the percentage difference and do financial technical analysis on real-time cryptocurrency data using flask web framework, ccxt trading api and tulipy library.

Universal SEO skill for Claude Code. 13 sub-skills, 7 subagents, extensions system with DataForSEO MCP integration. Technical SEO, E-E-A-T, schema, GEO/AEO, and strategic planning.

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…

Kimi Code CLI — The Starting Point for Next-Gen Agents

Energy Exascale Earth System Model source code. NOTE: use "maint" branches for your work. Head of master is not validated.

Git Source Code Mirror - This is a publish-only repository but pull requests can be turned into patches to the mailing list via GitGitGadget (https://gitgitgadget.github.io/). Please follow Documen…

Kimi Code CLI is your next CLI agent.

Skills that teach AI coding agents (Claude Code etc.) to use university HPC clusters safely — deploy, submit, monitor SLURM jobs via SSH. Currently: Tufts. Contributions welcome.