Repository Index

TensorLayerX: A Unified Deep Learning and Reinforcement Learning Framework for All Hardwares, Backends and OS.

• tensorlayerx
• tensorlayer
• tensorflow
• paddlepaddle

Implementation of "A Neural Algorithm of Artistic Style" by Tensorflow

Code for PaperRobot: Incremental Draft Generation of Scientific Ideas

• pytorch
• memory-networks
• generation
• end-to-end-learning

[Reimplementation Antol et al 2015] Keras-based LSTM/CNN models for Visual Question Answering

Open, source-backed catalog of computer-use agents: reviewed papers, GUI models, datasets, benchmarks, tools, and reusable JSONL/SQLite data.

• agent-evaluation
• agentic-ai
• ai-agents
• awesome

Awesome list of AI reverse engineering and rebuilds: what AI agents took apart and recreated, and which ones really used REA (Reverse Engineer Anything).

• ai-agents
• awesome
• awesome-list
• claude-code

Official implementation of “UniForge3D: Joint 3D Reconstruction and Generation in a Shared Anchor-Guided Space.”

An easy-to-use and lightweight API wrapper for Censys APIs.

• censys
• python3
• search
• pypi

A framework for continual learning and recursive self-improvement through harness adapter evolution.

AI Agent Identity and Access Management and Inference Firewall

• agent-identity
• ai-audit
• ai-firewall
• ai-gateway

Python implementation of the rulefit algorithm

scikit-learn inspired API for CRFsuite

RELATE is an Environment for Learning And TEaching

• web
• web-application
• course-management
• python

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

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

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

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

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

Kotti is a high-level, Pythonic web application framework based on Pyramid and SQLAlchemy. It includes an extensible Content Management System called the Kotti CMS.

CMake LSP Implementation

This is a Pytorch implementation of the paper: Self-Supervised Graph Transformer on Large-Scale Molecular Data

Lightweight Claude Code statusLine: 5h/7d rate-limit usage, reset countdowns, model + context window, prompt-cache age — one line, 3 styles × 9 themes, daemon fast-mode

• ai-tools
• claude-ai
• developer-tools
• monitoring

A lightweight Python SDK and CLI for evaluating recursive self-improvement (RSI) methods across agent benchmarks.

• ai-agents
• benchmarking
• llm-evaluation
• python

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

• rust
• uuid
• python
• uuid-generator

The official implementation of 3D Equivariant Diffusion for Target-Aware Molecule Generation and Affinity Prediction (ICLR 2023)

• ai-for-science
• diffusion-models
• drug-design
• equivariant-networks