HRM-Text is a 1B text generation model based on the HRM architecture, strengthened by task completion and latent space reasoning.
- large-language-models
- pretraining
- hierarchical-reasoning-model
- hrm
Repository Index
81,588 visible repositories in the index
2,833–2,856 of 5,873 · Most stars
DeepMind's Tacotron-2 Tensorflow implementation
- tacotron
- tensorflow
- paper
- python
Filters to block and remove copycat-websites from DuckDuckGo, Google and other search engines. Specific to dev websites like StackOverflow or GitHub.
- ublock-origin
- ublock
- dev
Microsoft’s GraphRAG on local models (Ollama, LM Studio), with an API and apps for indexing, prompt tuning, query and graph visualization.
Testcontainers is a Python library that providing a friendly API to run Docker container. It is designed to create runtime environment to use during your automatic tests.
- python
- python3
- testing
- testcontainers
A high-quality PDF to Markdown tool based on large language model visual recognition. 一款基于大模型视觉识别的高质量PDF转Markdown工具
【TMM 2025🔥】 Mixture-of-Experts for Large Vision-Language Models
- large-vision-language-model
- mixture-of-experts
- moe
- multi-modal
[CVPR 2025] MMAudio: Taming Multimodal Joint Training for High-Quality Video-to-Audio Synthesis
- audio
- audio-synthesis
- computer-vision
- deep-learning
Agent skill: design any process, idea, or problem into an ICM workspace (folder structure as agent architecture), or restructure an existing folder into one
An agentic company research tool powered by LangGraph and Tavily that conducts deep diligence on companies using a multi-agent framework. It leverages OpenRouter on the backend for rapid inference with any leading model.
A Python module for decorators, wrappers and monkey patching.
Fill-in-your-own-data framework for YouTube / short-form video automation: CapCut JSON + ffmpeg tooling + an onboarding questionnaire. Ships with zero private data.
- capcut
- content-creation
- creator-tools
- ffmpeg
ICCV2019 - Learning to Paint With Model-based Deep Reinforcement Learning
Let Claude (or any LLM) actually watch a video — scene-aware, deduplicated frames + transcript, from a URL or local file. Runs locally, MIT.
Accompanying code for Paperspace tutorial series "How to Implement YOLO v3 Object Detector from Scratch"
- pytorch-tutorial
- pytorch-implmention
- object-detection
- yolo
One brain, many harnesses. Portable .agent/ folder (memory + skills + protocols) that plugs into Claude Code, Cursor, Windsurf, OpenCode, OpenClaw, Hermes, or DIY Python — and keeps its knowledge when you switch.
Master the fundamentals of machine learning, deep learning, and mathematical optimization by building key concepts and models from scratch using Python.
detrex is a research platform for DETR-based object detection, segmentation, pose estimation and other visual recognition tasks.
- detr
- object-detection
- pytorch
- dino
The Fable Workflow: how Claude Fable 5 worked, distilled into skills any model can run, with the eval that keeps it honest. Think / act / prove.
Library to scrape and clean web pages to create massive datasets.
- artificial-intelligence
- natural-language-processing
- nlp
- text-mining
Local typed decisions, contrastive data curation, and model evaluation.
A local dashboard for tracking your Claude Code token usage, costs, and session history. Pro and Max subscribers get a progress bar. This gives you the full picture.
No-code multi-agent framework to build LLM Agents, workflows and applications with your data
- ai
- generative-ai
- llm-chain
- llm-framework
Deep learning PyTorch library for time series forecasting, classification, and anomaly detection (originally for flood forecasting).
- deep-learning
- pytorch
- time-series-forecasting
- time-series