LLMs & Machine Learning
Language models, training, inference, RAG and ML frameworks. ยท 116 repositories
AI powered OSINT engine to discover and map 840+ social media identities across the web
AI-powered penetration testing assistant using local LLM on linux (Parrot OS)
Hypergraph is more powerful. Transform unstructured text into structured knowledge with LLMs. Graphs, hypergraphs, and spatio-temporal extractions โ with one command.
Build a modern LLM from scratch. Every line commented. Explained like we are five.
A curated collection of practical AI projects implementing OCR systems, RAG, AI agents, and other AI use cases.
A ~9M parameter LLM that talks like a small fish.
Switchyard lets LLM applications route traffic across models and providers while preserving native OpenAI and Anthropic API compatibility - enabling flexible model selection, benchmarking, and cost/performance optimization.
[KDD'2026] "VideoRAG: Chat with Your Videos"
A high-performance inference engine for AI models
DeepTeam is a framework to red team LLMs and AI agents.
Face Recognition, Face Liveness Detection, Face Anti-Spoofing, Face Detection, Face Landmarks, Face Compare, Face Matching, Face Pose, Face Expression, Face Attributes, Face Templates Extraction, Face Landmarks
Build applications that make decisions (chatbots, agents, simulations, etc...). Monitor, trace, persist, and execute on your own infrastructure.
๐ค Open-source, local-first alternative to Grok Bot, OpenAI dots and Claude Duet. Your own AI bots on any model: GPT, Claude, Gemini, Grok, DeepSeek, Kimi, GLM and 70+ more through one Modelflare key. Reach them in the app, WeChat or Feishu; they remember you, work in the background, run commands and use your computer. Pay per use.
Run a 1-billion parameter LLM on a $10 board with 256MB RAM
UniFace: A Unified Face Analysis Library for Python | Detection, alignment, landmarks, face-mesh, recognition, parsing, gaze, attributes and anti-spoofing under one API.
Add object detection, tracking, mobile notifications, and search to any security camera.
A LLM trained only on data from certain time periods to reduce modern bias
Router that virtually distributes inference across connected devices in the home.
PTQ-Level Efficiency, QAT-Level Accuracy | ่ฎญ็ปๅ้ๅ็ๆ็๏ผ้ๅๆ็ฅ่ฎญ็ป็็ฒพๅบฆ
[SIGGRAPH Asia 2026] 4DAnyone: Create Anyone in 4D from a Casual Monocular Video
AutoShorts is a local-first desktop application for turning long-form video or audio recordings into high-impact, vertical short-form clip candidates (9:16 portrait) with AI-powered viral moment ranking.
An AI copywriter that uses real copywriting skills + real marketing knowledge with human tone.
Official Inference Code of EAGLE-4
๐ The First Self-Improving agents with RL / Prompting Optimization