SWE-agent takes a GitHub issue and tries to automatically fix it, using your LM of choice. It can also be employed for offensive cybersecurity or competitive coding challenges. [NeurIPS 2024]

Claude Code is an agentic coding tool that lives in your terminal, understands your codebase, and helps you code faster by executing routine tasks, explaining complex code, and handling git workflo…

Hy3 (295B A21B), a leading reasoning and agent model in its size, with great cost efficiency.

Automated Academic Research Workflow Skill. From direction exploration, literature review, and idea development to experiment design, code implementation, and paper writing.

Catch your AI agents when they lie about what they shipped — verifies claims against git instead of believing the agent.

Use Codex from Claude Code to review code or delegate tasks.

Data recipes and robust infrastructure for training AI agents

Scalable toolkit for efficient model reinforcement

The official repo of the paper: $delta$-mem: Efficient Online Memory for Large Language Models

Native macOS menu bar app to use your Claude Code & ChatGPT subscriptions with AI coding tools - no API keys needed

Wrap Antigravity, ChatGPT Codex, Claude Code, Grok Build as an OpenAI/Gemini/Claude/Codex compatible API service, allowing you to enjoy the free Gemini 3.1 Pro, GPT 5.5, Grok 4.3, Claude model thro…

A unified AI model hub for aggregation & distribution. It supports cross-converting various LLMs into OpenAI-compatible, Claude-compatible, or Gemini-compatible formats. A centralized gateway for p…

From Automated Idea Factory to Realization

Gym-Anything: Turn any Software into an Agent Environment

Multi-agent deliberation skill for Claude Code: ask the same question through multiple models and analytical lenses, then synthesize

Intercept and inspect Coding Agent API traffic from Claude Code, Codex CLI, Gemini CLI, Cursor CLI, OpenCode, Kimi/Kimi Code, Pi, and Hermes in a local trace viewer.

E2B Desktop Sandbox for LLMs. E2B Sandbox with desktop graphical environment that you can connect to any LLM for secure computer use.

本人的科研经验

Ongoing research training transformer models at scale

Lightweight coding agent that runs in your terminal

VeOmni: Scaling Any Modality Model Training with Model-Centric Distributed Recipe Zoo

🐚bash/POSIX-compatible shell implemented in Rust 🦀

The universal proxy platform

Training library for Megatron-based models with bidirectional Hugging Face conversion capability

Ongoing research training transformer models at scale