AI 开源项目榜。

An experimental node

Links to conference/journal publications in automated fact-checking (resources for the TACL22/EMNLP23 paper).

Tool for onnx->keras or onnx->tflite. Hope this tool can help you.

A TensorFlow implementation of DeepMind's Differential Neural Computers (DNC)

VS Code chat sidebar for local AI coding agents

ComfyUI wrapper for Trellis 2

Volumetric Human Teleportation (SIGGRAPH 2020 Real-Time Live) Monocular Real-Time Volumetric Performance Capture(ECCV 2020)

CUAD (NeurIPS 2021)

The open-source Render alternative — AI-native. Git push → build → deploy on your own infrastructure; agents are first-class users.

An index of my Claude Code related repos including a wide variety of starter templates for using Claude Code for common and more imaginative purposes!

⚡ DocsAgent — give your AI agents instant, private access to your personal knowledge base (Zotero, Obsidian, Apple Notes supported now, local docs on the road). Native C++ search core: BM25 + passage ranking in ~15 ms. MCP server for Claude, Cursor, Cline & any MCP client.

基於OpenVino-int8權重，精簡的QwenASR小工具，用於即時辨識以及字幕轉換使用

A simplified framework and utilities for PyTorch

Language model search engine built on a vector database and an anything key/value store.

OpenClip - AI-powered highlight extraction for long videos (AI 驱动的长视频精彩时刻提取工具)

LLM (Large Language Model) FineTuning

Selected ChatGPT demos, tools, articles, and more ✨

WeChat Mini-program plugin for TensorFlow.js

Vite plugin that enables a MCP server helping models to understand your Vue app better.

Code for the AAAI 2018 publication "SEE: Towards Semi-Supervised End-to-End Scene Text Recognition"

A Tree Search Library with Flexible API for LLM Inference-Time Scaling

Memory Enhanced Global-Local Aggregation for Video Object Detection, CVPR2020

IKEA Furniture Assembly Environment for Long-Horizon Complex Manipulation Tasks

A flexible, adaptive classification system for dynamic text classification

Official Code for ECCV 2024 paper — One-Shot Diffusion Mimicker for Handwritten Text Generation

Meta Agents Research Environments is a comprehensive platform designed to evaluate AI agents in dynamic, realistic scenarios. Unlike static benchmarks, this platform introduces evolving environments where agents must adapt their strategies as new information becomes available, mirroring real-world challenges.

Reimplementation of DDPG(Continuous Control with Deep Reinforcement Learning) based on OpenAI Gym + Tensorflow

An open-source Cotypist with macOS system wide AI autocomplete

TOROS Buffalo: A fast and scalable production-ready open source project for recommender systems