World's first open-source, agentic video production system. 12 production pipelines, 100+ tools, 700+ agent skill and production-knowledge files. Turn your AI coding assistant into a full video production studio.
Repository Index
67,262 visible repositories in the index
1–24 of 39 · Most stars
Training-free language model modification: Remove censorship, suppress slop, reduce sycophancy, and more
- abliteration
- llm
- transformer
- censorship-resistance
Open-source speech recognition toolkit for training, inference, streaming ASR, VAD, punctuation, speaker diarization pipelines, and OpenAI-compatible/MCP serving.
- pytorch
- speech-recognition
- paraformer
- punctuation
Use PEFT or Full-parameter to CPT/SFT/DPO/GRPO 600+ LLMs (Qwen3.8, DeepSeek-V4, GLM-5.1, InternLM3, Llama4, ...) and 300+ MLLMs (Qwen3-VL, Qwen3-Omni, InternVL3.5, Ovis2.5, GLM5.3, Gemma4, Llava, Phi4, ...) (AAAI 2025).
Enjoy the magic of Diffusion models!
ModelScope: bring the notion of Model-as-a-Service to life.
- nlp
- cv
- speech
- multi-modal
Copy any UI element for your agent
TranslatedThe pkuseg toolkit for multi-domain Chinese word segmentation
- chinese-word-segmentation
FunASR-powered video transcription, subtitle generation, and LLM-assisted clipping tool with a local Gradio UI.
- speech-recognition
- video-subtitles
- subtitles-generator
- speech-to-text
An AI-powered custom node for ComfyUI designed to enhance workflow automation and provide intelligent assistance
Translated:helicopter::rocket: A real-time product recommendation system built on Flink. Flink calculates product popularity and puts it into the Redis cache; it analyzes log information and puts user profile tags and real-time records into HBase. After a user initiates a recommendation request, the popularity ranking is re-ranked according to the user profile, and the two recommendation modules, collaborative filtering and tags, are combined to add associated products to each product in the newly generated ranking. Finally, a new user list is returned.
- flink
- recommander-system
- recommand
- flink-kafka
A Repository for Single- and Multi-modal Speaker Verification, Speaker Recognition and Speaker Diarization
- campplus
- speaker-diarization
- speaker-verification
- voxceleb
Low cost motion capture system for room scale tracking
- autonomous-robots
- bundle-adjustment
- computer-vision
- epipolar-geometry
PyBullet Gymnasium environments for single and multi-agent reinforcement learning of quadcopter control
- pybullet
- crazyflie
- robotics
- reinforcement-learning
Copy any text on your screen, stop retyping.
- macos
- productivity
- ocr
- textrecognition
How to Copy Text from Images ? Answer is TextSnatcher !. Perform OCR operations in seconds on Linux Desktop.
PyBullet CartPole and Quadrotor environments—with CasADi symbolic a priori dynamics—for learning-based control and RL
- gym
- pybullet
- reinforcement-learning
- control
Segment Anything for Microscopy
- microscopy-images
- segment-anything
- segmentation
- cell-segmentation
Translated[NovaNova Studio] An Agent-driven, full-workflow open-source platform that combines AI image generation, AI video generation, an infinite canvas, custom model APIs, AI comic dramas, AI short dramas, novel-to-script parsing, novel-to-short-drama conversion, a 3D director's console, user management, and credit management in one
- agent
- agentscope-java
- image-generation-ai
- infinite-canvas
Open-source AI interview assistant and meeting copilot: live answers during Zoom, Google Meet and Teams calls, on-device transcription, hidden from screen sharing. Free Cluely, Interview Coder and Final Round AI alternative for Windows, macOS, Linux.
Code for the Nature Scientific Reports paper "Pathologist-level classification of histologic patterns on resected lung adenocarcinoma slides with deep neural networks." A sliding window framework for classification of high resolution whole-slide images, often microscopy or histopathology images.
- histopathology-images
- microscopy
- sliding-windows
- medical-image-analysis
CellViT: Vision Transformers for Precise Cell Segmentation and Classification
- ai
- cell
- digitalpathology
- microscopy
TranslatedThe keyboard for the agent era: dictation, copy text from screen, translation, snaps and screen recordings for Claude Code, Codex and your other agents. Free, open source, Mac. 口喷鸡 (Kou Pen Ji, "mouth-spraying chicken").
- agent-skills
- claude-code
- codex
- screen-recording
Deep and Machine Learning for Microscopy
- microscopy
- materials
- machine-learning
- materials-science