Repository Index

honeyλ - a simple, serverless application designed to create and monitor fake HTTP endpoints (i.e. URL honeytokens) automatically, on top of AWS Lambda and Amazon API Gateway

• honeytoken
• honeypot
• security
• deception

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

AWSDoor is a red team automation tool designed to simulate advanced attacker behavior in AWS environments

Prompt-injection firewall for LLM applications — 33 input detectors, 9 output scanners, federated ed25519-signed threat-intel feed. Apache 2.0, 1040 tests, F1 96.0% with 0% false positives. Docker, GitHub Action, LangChain/LlamaIndex/CrewAI integrations.

• agentic-ai
• ai-safety
• fastapi
• langchain

One isolated Lima VM per GitHub project — sandboxed Claude Code/Codex, Docker, Node, signed git

• ai-agents
• claude-code
• developer-tools
• lima

🛡️ Static security scanner (SAST) for Ansible playbooks, roles, and collections. 1,000+ rules across 30+ categories detecting malicious code, RCE, hardcoded credentials, and supply-chain risk. Outputs SARIF, CycloneDX SBOM, and GitLab SAST. SLSA Build Level 3, Sigstore-signed.

• ansible
• ansible-playbook
• devsecops
• infrastructure-as-code