A self hosted virtual browser that runs in docker and uses WebRTC.

Claude Code 泄露源码 - 本地可运行版本，新增跨平台桌面端软件补齐Computer Use（附带核心模块解析）

📻Terminal/ssh/sftp/ftp/telnet/serialport/RDP/VNC/Spice client(linux, mac, win)

微舆：人人可用的多Agent舆情分析助手，打破信息茧房，还原舆情原貌，预测未来走向，辅助决策！从0实现，不依赖任何框架。

🔬 Harness Vibe Research with Self-evolving AI Scientists

🧠 Cortex - Universal AI Agent Memory Service

Approaching (Almost) Any Machine Learning Problem中译版，在线文档地址：https://ytzfhqs.github.io/AAAMLP-CN/

The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.

Elevate your AI research writing, no more tedious polishing ✨

[NeurIPS 24] Incremental Learning of Retrievable Skills For Efficient Continual Task Adaptation

Code and data for "OBLIVIATE: Robust and Practical Machine Unlearning for Large Language Models"

Open-source Windows and Office activator featuring HWID, Ohook, TSforge, and Online KMS activation methods, along with advanced troubleshooting.

Towards a Unified View of Large Language Model Post-Training

Towards Robust and Parameter-Efficient Knowledge Unlearning for LLMs (ICLR 2025)

[ICLR 2025] "Rethinking LLM Unlearning Objectives: A Gradient Perspective and Go Beyond"

Bash is all you need - A nano claude code–like 「agent harness」, built from 0 to 1

Implementing DeepSeek R1's GRPO algorithm from scratch

[NeurIPS D&B '25] The one-stop repository for LLM unlearning

Existing Literature about Machine Unlearning

[ICLR 2025] A Closer Look at Machine Unlearning for Large Language Models

Official PyTorch Implementation for Continual Learning and Private Unlearning

[COLM 2025] LoRI: Reducing Cross-Task Interference in Multi-Task Low-Rank Adaptation

LoRAMoE: Revolutionizing Mixture of Experts for Maintaining World Knowledge in Language Model Alignment