Starred repositories
BullshitBench measures whether AI models challenge nonsensical prompts instead of confidently answering them, created by Peter Gostev.
DatePicker is an interactive calendar built with Iced. It lets the user pick a date in the calendar.
Mellea is a library for writing generative programs.
PyTorch building blocks for the OLMo ecosystem
Modeling, training, eval, and inference code for OLMo
JailbreakBench: An Open Robustness Benchmark for Jailbreaking Language Models [NeurIPS 2024 Datasets and Benchmarks Track]
AI agents running research on single-GPU nanochat training automatically
Give your AI agent access to your live Chrome session — works out of the box, connects to tabs you already have open
Local UI to run and train LLMs and diffusion models, including Qwen3.8, Kimi K3, MiniMax-H3, Gemma 4, DeepSeek-V4, FLUX and more.
Use PEFT or Full-parameter to CPT/SFT/DPO/GRPO 600+ LLMs (Qwen3.6, DeepSeek-V4, GLM-5.1, InternLM3, Llama4, ...) and 300+ MLLMs (Qwen3-VL, Qwen3-Omni, InternVL3.5, Ovis2.5, GLM4.5v, Gemma4, Llava, …
Towards Self-Evolving Proactive AI with Perpetual Memory
A research framework for evaluating proactive AI assistants through active user simulation
[NeurIPS'25] ContextAgent: Context-Aware Proactive LLM Agents with Open-World Sensory Perceptions
tmux config with built-in terminal automation and agent-to-agent communication.
Recommend new arxiv papers of your interest daily according to your Zotero libarary.
A curated collection of AI agent research papers released in 2026, covering agent engineering, memory, evaluation, workflows, and autonomous systems.
Purifying Generative LLMs from Backdoors without Prior Knowledge or Clean Reference
Safety Alignment Can Be Not Superficial With Explicit Safety Signals
The original nirholas/claude-code before DMCA and take down. Once everything is cleared, it will return. Working with Anthropic and Github to get everything back.
A Dynamic Environment to Evaluate Attacks and Defenses for LLM Agents.
Code for the paper "Defeating Prompt Injections by Design"
Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞
A minimal, secure Python interpreter written in Rust for use by AI
Open-source 24/7 Cowork app for OpenClaw, Hermes, Claude Code, Codex, OpenCode and 20+ more CLI Agent | Customize your assistants | Team them up｜Star if you like it!