76,356 visible repositories in the index
193–216 of 603 · Most stars
Villain is a high level stage 0/1 C2 framework that can handle multiple reverse TCP & HoaxShell-based shells, enhance their functionality with additional features (commands, utilities) and share them among connected sibling servers (Villain instances running on different machines).
Open-source evaluation toolkit of large multi-modality models (LMMs), support 220+ LMMs, 80+ benchmarks
[EMNLP 2022] An Open Toolkit for Knowledge Graph Extraction and Construction
Easily turn large sets of image urls to an image dataset. Can download, resize and package 100M urls in 20h on one machine.
TranslatedMulti-Platform Live Stream Automatic Recording Tool | Multi-platform live stream automatic recording client, based on FFmpeg, supports monitoring/scheduling/transcoding
Computing with Python functions.
Simple, online, and realtime tracking of multiple objects in a video sequence.
Massively Parallel Deep Reinforcement Learning. 🔥
Multi-protocol proxy management panel built with Python & FastAPI, deployable on Railway.
An open-source model family for long-form speech, dialogue synthesis, voice design, sound effects, and real-time streaming TTS
Multi-vendor library to simplify Paramiko SSH connections to network devices
Simple command line tool for text to image generation using OpenAI's CLIP and Siren (Implicit neural representation network). Technique was originally created by https://twitter.com/advadnoun
Transformers for Information Retrieval, Text Classification, NER, QA, Language Modelling, Language Generation, T5, Multi-Modal, and Conversational AI
[IJCV-2021] FairMOT: On the Fairness of Detection and Re-Identification in Multi-Object Tracking
Your First AI Agents Company
Harness LLMs with Multi-Agent Programming
Chinese and English multimodal conversational language model | 多模态中英双语对话语言模型
Fengshenbang-LM(封神榜大模型)是IDEA研究院认知计算与自然语言研究中心主导的大模型开源体系，成为中文AIGC和认知智能的基础设施。
An open-source framework for training large multimodal models.
[NeurIPS 2025] Open-source Multi-agent Poster Generation from Papers
Superfast AI decision making and intelligent processing of multi-modal data.
Paper2Agent is a multi-agent AI system that automatically transforms research papers into interactive AI agents.
Trackers gives you clean, modular re-implementations of leading multi-object tracking algorithms released under the permissive Apache 2.0 license. You combine them with any detection model you already use.
:stuck_out_tongue_closed_eyes: TensorFlowTTS: Real-Time State-of-the-art Speech Synthesis for Tensorflow 2 (supported including English, French, Korean, Chinese, German and Easy to adapt for other languages)