LockKnife: The Ultimate Android Security Research Tool. A unified TUI workspace and headless CLI for deep Android security research, built for researchers and hackers. Powered by Python orchestration and a Rust-accelerated core, enabling AI agent–driven hacking, credential recovery/cracking, APK analysis, intelligence gathering, runtime inspection.
- adb
- android-hacking
- android-security
- foss
Universal LLM Gateway: One API, every LLM. OpenAI/Anthropic-compatible endpoints with multi-provider translation and intelligent load-balancing.
Embedding, NMT, Text_Classification, Text_Generation, NER etc.
- nlp-pytorch
- text-classification
- nmt
- seq2seq
The repository host gives no description.
A3C LSTM Atari with Pytorch plus A3G design
Implementation of ChatGPT RLHF (Reinforcement Learning with Human Feedback) on any generation model in huggingface's transformer (blommz-176B/bloom/gpt/bart/T5/MetaICL)
An experimental open-source attempt to make GPT-4 fully autonomous.
Official implementation for the paper "DoLa: Decoding by Contrasting Layers Improves Factuality in Large Language Models"
It won't fix your bug. It'll fix you. The debugger that hands the question back instead of the answer.
自动化 SRC 漏洞挖掘系统:FOFA 资产测绘 + LLM 多 worker 自主挖掘/审核/情报沉淀。Powered By StanleyNull
🎓 AI 科研论文写作助手 - 30 个 Prompt 模板覆盖论文写作全流程。支持中英文翻译、润色、文献综述、投稿回复、基金申请等。
- academic-writing
- ai-writing
- openclaw
- paper-writing
Google Hangouts bot
LLM-authored task-specific Jev harnesses with optional full-trajectory reward reflection and GEPA evolution.
面向中文大模型价值观的评估与对齐研究
🤖 A prototype assistant for writing and thinking
Pax is a Jax-based machine learning framework for training large scale models. Pax allows for advanced and fully configurable experimentation and parallelization, and has demonstrated industry leading model flop utilization rates.
Efficient and easy multi-instance LLM serving
LangGraph template for a simple ReAct agent, with MCP tools support and robust test suites.
- deepwiki
- langchain
- langchain-python
- langgraph
Deliver safe & effective language models
Fast, exact inference for StartLux-Decision models on NVIDIA GPUs: the released GGUF files on int8 and 4-bit tensor cores, behind the /v1/systemone API, with up to 5.3× lower latency than vLLM in FP8 and bit-identical answers.
- calibration
- cuda
- cuda-graphs
- decision-making
A Curated Collection of resources for applied AI engineering (work in progress).
Use ArXiv ChatGuru to talk to research papers. This app uses LangChain, OpenAI, Streamlit, and Redis as a vector database/semantic cache.
A Large-Scale Multimodal Car Dataset with Computational Fluid Dynamics Simulations and Deep Learning Benchmarks
- 3d-geometry
- aerodynamics
- car-design
- cfd
从0到1构建一个MiniLLM (pretrain+sft+dpo实践中)