The Cradle framework is a first attempt at General Computer Control (GCC). Cradle supports agents to ace any computer task by enabling strong reasoning abilities, self-improvment, and skill curation, in a standardized general environment with minimal requirements.
- ai-agent
- ai-agents-framework
- computer-control
- cradle
SAM with text prompt
The PyTorch-based audio source separation toolkit for researchers
- source-separation
- speech-separation
- audio-separation
- speech-enhancement
A PyTorch Library for Multi-Task Learning
- multitask-learning
- multi-task-learning
- pytorch
- python
Load and performance benchmark tool
Generate a docker-compose yaml definition from a running container
Painter & SegGPT Series: Vision Foundation Models from BAAI
- cvpr2023
- in-context-learning
- generalist-model
- generalist-painter
CTF challenge (mostly pwn) files, scripts etc
- appsec
- binary-exploitation
- capture-the-flag
- ctf
A nano replica of Jev: parallel decisions, dynamic candidates, and an end-to-end training pipeline.
Tensorflow implementation of Human-Level Control through Deep Reinforcement Learning
Translate full-length books and documents with Ollama, OpenAI-compatible, Gemini, Mistral, DeepSeek, Poe or OpenRouter. Preserves formatting. Resumes where you left off. No file size limits.
Using modified BiSeNet for face parsing in PyTorch
- face-parsing
- semantic-segmentation
- pytorch
- celeba-hq-dataset
An agent capable of self-evolving and dynamically hardening security
🚀 Cookiecutter Template for FastAPI + React Projects. Using PostgreSQL, SQLAlchemy, and Docker
Repository containing evidence of police brutality during the 2020 George Floyd protests
- police
- cop
- cops
- police-reports
Get your own Bitcoin & Lightning Node running - on a RaspberryPi with a nice LCD
A benchmark for evaluating LLMs on Chinese traditional fortune telling — Bazi (八字) and Ziwei Doushu (紫微斗数).
Modular Python framework for AI agents and workflows with chain-of-thought reasoning, tools, and memory.
Building a Neural Network-Native Engine (3N). Python authoring, C++ runtime, Vulkan/WebGPU. Windows, Linux, Android and Web.
Lighteval is your all-in-one toolkit for evaluating LLMs across multiple backends
- evaluation
- evaluation-framework
- evaluation-metrics
- huggingface
Awesome Reasoning LLM Tutorial/Survey/Guide
[NeurIPS 2025] An official implementation of Flow-GRPO: Training Flow Matching Models via Online RL
A tool that allows you to create vulnerable instrumented local or cloud environments to simulate attacks against and collect the data into Splunk
- attack-range
- attack-simulation
- adversary
- simulation
Fast, accurate and scalable probabilistic data linkage with support for multiple SQL backends
- record-linkage
- spark
- em-algorithm
- deduplication