Repository Index

Deep Learning Resources and Tutorials using Keras and Lasagne

TranslatedOne zero-dependency MCP gateway CLI for every server and agent skill. Token optimization, tool discovery and context compression: 71,929 -> 581 tokens (-99.2%, measured), schemas stay out of context. One config for Claude Code, Codex, Cursor, every agent. 561KB, pure Python. | Zero-dependency CLI: manages all MCP tools and skills, and tool discovery saves 99.2% of tokens.

• mcp
• claude
• claude-code
• cursor

GEARS is a geometric deep learning model that predicts outcomes of novel multi-gene perturbations

Crop Yield Prediction with Deep Learning

Implementation for PolarNet: An Improved Grid Representation for Online LiDAR Point Clouds Semantic Segmentation (CVPR 2020)

Reinforcement learning library(framework) designed for PyTorch, implements DQN, DDPG, A2C, PPO, SAC, MADDPG, A3C, APEX, IMPALA ...

• reinforcement-learning
• deep-learning
• pytorch
• pytorch-reinforcement-learning

🧱 Experimental library for building inference engines

• inference
• llm
• cuda
• gpt-oss

Repository for the PyOpenGL Project

Trading Environment(OpenAI Gym) + DDQN (Keras-RL)

• keras-rl
• deep-reinforcement-learning
• trading
• keras

Auditable code review skill for Claude Code and Codex: four independent probes, evidence-backed findings, and a JSON-derived merge gate.

• agent-skills
• ai-code-review
• claude-code
• code-review

TranslatedAn AI avatar for real-time voice/text conversations with idols from "The iDOLM@STER Shiny Colors": original Japanese voice + Chinese subtitles, recalling the original story, memory shared across characters; supports Google/GitHub login and bring-your-own key, one-command deployment with Docker Compose (inspired by LAPLACE Eidolon)

• ai-companion
• character-ai
• fastapi
• idolmaster

Limon is a sandbox developed as a research project written in python, which automatically collects, analyzes, and reports on the run time indicators of Linux malware. It allows one to inspect Linux malware before execution, during execution, and after execution (post-mortem analysis) by performing static, dynamic and memory analysis using open source tools

OPAL: a reactive optimizer. A coding agent rewrites the optimizer while your model trains.

• deep-learning
• llm-agents
• optimizer
• pytorch

Credentials catching honeypot

• honeypot
• deception
• security
• security-tools

MicroPython drivers for Waveshare e-paper modules

• micropython
• waveshare
• epaper
• eink

:sunrise: A comprehensive, cutting-edge open-source framework for next-generation Transformers/LLM, with compute-matched benchmarking and a platform for autonomous architecture research.

• auto-research
• benchmark
• deep-learning
• language-models

Experimental Nikon Z8 C 3.11 firmware patch builder: 3:2 open-gate N-RAW, desqueeze, ProRes/H.265 quality controls, N-Log/S-Log3/Log3G10, RAW pre-capture, and in-camera pixel-shift merging.

• firmware
• firmware-patching
• h265
• n-raw

Fast, drop-in replacement for Python's uuid module, powered by Rust.

• rust
• uuid
• python
• uuid-generator

Power rename/refactor tool for CLI and agent use

• python
• renames
• regular-expression
• refactoring

SolarRenderer: Few-Step Generative Reference Rendering

An agent that compiles git maintenance chores into reusable programs, then decides whether to replay them by running checks rather than by guessing the task looks familiar

• agent-architecture
• git-automation
• llm-agents
• program-synthesis

Keep docker hosts tidy

Electronic Health Record Analysis with Python.

• scverse
• electronic-health-record
• electronic-medical-record
• ehr

TranslatedA Bilibili command-line tool designed for AI Agents: QR code login, watching videos, commenting, direct messages, posting updates, uploading videos, all with JSON output

• agent-skills
• ai-agent
• automation
• bilibili