GMGN OpenAPI skills for AI Agent — query tokens, wallets, and market data, and execute on-chain trades across Solana, BSC, and Base.
Repository Index
140,194 visible repositories in the index
97–120 of 143 · Most stars
Implementation of plug in and play Attention from "LongNet: Scaling Transformers to 1,000,000,000 Tokens"
- artificial-intelligence
- attention
- attention-is-all-you-need
- attention-mechanisms
Rainbow CSV - Vim plugin: Highlight columns in CSV and TSV files and run queries in SQL-like language
- csv
- tsv
- vim-plugins
- sql-like
Learning Correspondence from the Cycle-consistency of Time (CVPR 2019)
Flashing Itead Sonoff devices with custom firmware via original OTA mechanism
Inspect, visualize and intervene on any operation in any neural network. Capture every activation and gradient, the full computational graph and 800+ metadata fields without changing model code. Supports PyTorch, JAX, TensorFlow, MLX, PaddlePaddle and tinygrad. Validated on 6400+ models. Built for researchers and their AI agents.
- activations
- computational-graph
- deep-learning
- explainable-ai
A Pytorch Implementation of "Neural Speech Synthesis with Transformer Network"
- text-to-speech
- tts
- transformer
- attention-plots
A bidirectional recurrent neural network model with attention mechanism for restoring missing punctuation in unsegmented text
- punctuation
- recurrent-neural-networks
- theano
- attention
A Multi-Agent Trading System Based on Internal Contest Mechanism
The project integrates the RAG and FAQ dual mechanisms, introduces intent recognition, dynamic adaptive retrieval, and the RAGAS automated evaluation system, achieving a transformation from empirical optimization to data-driven optimization.
Brain-inspired Cognitive Intelligence Engine (BrainCog) is a brain-inspired spiking neural network based platform for Brain-inspired Artificial Intelligence and simulating brains at multiple scales. The long term goal of BrainCog is to provide a comprehensive theory and system to decode the mechanisms and principles of human intelligence and its evolution, and develop artificial brains for brain-inspired conscious living AI in future Human-AI symbiotic Society.
- brain-inspired-computation
- brain-simulations
- computational-neuroscience
- spiking-neural-networks
The Fulcrum Keyboard is an ergo-mechanical split keyboard with extra thumb functionality. It has 20 keys, two rotary encoders, and two 5-way switches.
- circuitpython
- ergomechkeyboards
- ergonomic-keyboard
- keyboard
Implementation of MagViT2 Tokenizer in Pytorch
- artificial-intelligence
- attention-mechanisms
- deep-learning
- transformers
based on yolo-high-level project (detect\pose\classify\segment\):include yolov5\yolov7\yolov8\ core ,improvement research ,SwintransformV2 and Attention Series. training skills, business customization, engineering deployment C
- yolov5
- deepstream
- pytorch
- object-detection
MORAN: A Multi-Object Rectified Attention Network for Scene Text Recognition
- scene-text
- scene-text-recognition
- image-deformation
- image-rectification
[CVPR25 Oral (Top 3.3%)] Official code for paper "Reconstructing Humans with a Biomechanically Accurate Skeleton".
- cvpr2025
- human-mesh-recovery
TimeCopilot: the Agentic Forecasting Framework. Built on LLMs and Time Series Foundation Models, it lets you forecast, cross-validate, and detect anomalies using multiple foundation models through a single API. From finance and energy to web analytics, TimeCopilot turns natural-language queries into production-ready forecasts.
- agentic-ai
- llms
- time-series
- agent-based-modeling
[IGARSS'22]: A Transformer-Based Siamese Network for Change Detection
- change-detection
- remote-sensing
- siamese-network
- transformer-encoder
for mass exploiting
- hacking-tool
- rce
- weblogic
- google-search
[CVPR 2021, Oral] PREDATOR: Registration of 3D Point Clouds with Low Overlap.
- point-cloud
- registration
- 3dvision
- transformer
Build high-performance AI models with modular building blocks
- transformers
- pytorch
- attention-mechanism
- attention-model
Implementation of the Point Transformer layer, in Pytorch
- artificial-intelligence
- deep-learning
- attention-mechanism
- point-cloud
Optimal Motion Generation-tools: motion planning made easy
[ICLR2025 Spotlight🔥] Official Implementation of TokenFormer: Rethinking Transformer Scaling with Tokenized Model Parameters
- architecture
- foundation-models
- llm
- scaling-methods