forensicmike
Follow
Stars
A library to interact with services exposed by iOS
agent runtime security - zero trust, zero setup, zero latency agent sandboxing
SmallWorld is an environment for streamlined harnessing of binary code for the purpose of dynamic analysis.
[NeurIPS'25 Spotlight] Official implementation of "JavisGPT: A Unified Multi-modal LLM for Sounding-Video Comprehension and Generation"
Soprano: Instant, Ultra-Realistic Text-to-Speech
Caption free adapter that maps DINOv3 image embeddings into CLIP space so you can do zero-shot text -> image or image -> text with CLIP’s text tower
Build your own visual reasoning model
A lightweight, powerful framework for multi-agent workflows
Temporal Action Annotation Tool – A flexible and customizable tool for annotating time-based events in videos. Define your own action types, navigate seamlessly, and export data for analysis.
LightGlue: Local Feature Matching at Light Speed (ICCV 2023)
This repository contains demos I made with the Transformers library by HuggingFace.
A CPU Realtime VLM in 500M. Surpassed Moondream2 and SmolVLM. Training from scratch with ease.
Local UI to run and train LLMs and diffusion models. Supports GGUF, MLX, Qwen3.8, DeepSeek-V4.1, MiniMax-H3, Gemma 4, FLUX and more.
[NeurIPS 2025 Spotlight] Reasoning Environments for Reinforcement Learning with Verifiable Rewards
Minimal reproduction of DeepSeek R1-Zero
The first AI agent that builds permissionless integrations through reverse engineering platforms' internal APIs.
A Lightweight Face Recognition and Facial Attribute Analysis (Age, Gender, Emotion and Race) Library for Python
✨✨Latest Advances on Multimodal Large Language Models
Pytorch implementation of Transfusion, "Predict the Next Token and Diffuse Images with One Multi-Modal Model", from MetaAI
Various training scripts used to train bigasp
Hide Module "frida-agent.dll", Only for Windows.
CLI for backing up AWS Cogntito User Pools
AppAgent: Multimodal Agents as Smartphone Users, an LLM-based multimodal agent framework designed to operate smartphone apps.
Windows implementation of the ddcutil Linux program for querying and changing monitor settings, such as brightness and color levels.
IDA pro plugin to find crypto constants (and more)
Audio generation using diffusion models, in PyTorch.