High-quality single file implementation of Deep Reinforcement Learning algorithms with research-friendly features (PPO, DQN, C51, DDPG, TD3, SAC, PPG)
- wandb
- reinforcement-learning
- pytorch
- python
99,825 visible repositories in the index
49–72 of 659 · Most stars
High-quality single file implementation of Deep Reinforcement Learning algorithms with research-friendly features (PPO, DQN, C51, DDPG, TD3, SAC, PPG)
MemoryBear Equip AI with human-like memory capability
A Comprehensive Toolkit for High-Quality PDF Content Extraction
the LLM vulnerability scanner
The no-magic web API and microservices framework for Python developers, with a focus on reliability and performance at scale.
Pure bash script to test and wait on the availability of a TCP host and port
Multi-user anti-filtering panel, with an effortless installation and supporting more than 20 protocols to circumvent filtering plus the telegram proxy.
A Claude Code skill bundle for bug hunting and external red-team work - 82 skills, 15 slash commands, 681 disclosed-report patterns curated across 24 core vulnerability classes, plus enterprise identity + infrastructure attack matrices.
A template for PostgreSQL High Availability with Etcd, Consul, ZooKeeper, or Kubernetes
DoWhy is a Python library for causal inference that supports explicit modeling and testing of causal assumptions. DoWhy is based on a unified language for causal inference, combining causal graphical models and potential outcomes frameworks.
Uniform Manifold Approximation and Projection
Trail of Bits skills for security research, vulnerability detection, and audit workflows
Codebase intelligence for AI and humans: code health scores, auto-generated docs, git analytics, dead code detection, and architectural decisions via MCP.
Build autonomous AI agents in Python.
Ingest, parse, and optimize any data format ➡️ from documents to multimedia ➡️ for enhanced compatibility with GenAI frameworks
A framework for efficient model inference with omni-modality models
High-quality multi-lingual text-to-speech library by MyShell.ai. Support English, Spanish, French, Chinese, Japanese and Korean.
A supercharged Git/GitHub command line interface (CLI). An official integration for GitHub and GitHub Enterprise: https://github.com/works-with/category/desktop-tools
Open-source observability for your GenAI or LLM application, based on OpenTelemetry
A full-stack AI Red Teaming platform securing AI ecosystems via Agent Scan, Skills Scan, MCP scan, AI Infra scan and LLM jailbreak evaluation.
TranslatedA summary and organization of the various kinds of knowledge that a natural language processing (NLP) engineer needs to accumulate, including interview questions, all kinds of foundational knowledge, engineering skills, and so on, to improve core competitiveness
Centralized network visibility and continuous asset discovery. Monitor devices, detect change, and stay aware across distributed networks.
The Open Source Feature Store for AI/ML
TranslatedDeepAudit: An AI hacker team for everyone, putting vulnerability discovery within reach. Beginners can deploy and run it with one click, with autonomous collaborative auditing + automated sandbox PoC verification. Supports private deployment with Ollama and one-click report generation. Supports relay stations. Making security no longer expensive and auditing no longer complicated.