Repository Index

Runtime defense against memory poisoning in AI agents (OWASP ASI06). Drop-in for LangChain, OpenAI Agents, AutoGen, CrewAI and mem0.

• ai-agents
• langchain
• llm-security
• memory-poisoning

Build an interactive clothing website from product photos with your coding agent. Includes two animated garments, prompts, and a video-to-UI pipeline.

A minimalistic terminal theme (prompt) for sexy terminals that works in bash, fish and zsh

• zsh-theme
• bash-prompt
• bash-theme
• fish-theme

Make AI output sound human. Strips AI-isms (sycophancy, stock vocab, hedging stacks, em-dash pileups), preserves code/URLs/headings. Plugin for Claude Code, Cursor, Windsurf, Codex, Cline, Copilot, Gemini.

• ai-detection
• ai-plugin
• anti-slop
• claude-code

Local multi-AI desktop workspace with official website panels, shared prompts and group collaboration.

• ai-chat
• chinese
• desktop-app
• electron

GLM 5.3 Abliterated or Uncensored AI model — 35 jailbreak prompts, model guide and API. One 7API key also covers Claude, GPT, Gemini, Grok, DeepSeek and Kimi.

• abliterated
• abliterated-models
• anthropic-compatible
• claude-code

Safety in Embodied AI: A Survey of Risks, Attacks, and Defenses | 500+ Papers | Perception, Cognition, Planning, Interaction, Agentic System

• adversarial-attacks
• ai-safety
• autonomous-driving
• backdoor-attacks

Official implementation of "AReA: Adaptive Receptive-Field Attention for Efficient High-Resolution Diffusion Transformers"

• diffusion-models
• efficient-inference
• high-resolution
• image-generation

AI motion graphics for YouTube explainer videos: 74 animated HTML explainer boards (charts, diagrams, Venn, timeline, heatmap) synced to your voice with Whisper, exported frame by frame with Chrome + FFmpeg. Every prompt + Claude skills. By TEIN AI.

• ai-agents
• ai-video
• animation
• claude

Codex plugin for OpenPencil — an interactive Rust/WASM canvas for AI-assisted UI design. Create editable .op files from prompts, refine selected elements, generate image assets, and install with one prompt on macOS, Windows, and Linux.

• codex
• design-tools
• mcp
• openpencil

TranslatedChinese edition of an AI painting costume reference gallery · 1407 costumes / 86 tags · zero-dependency static gallery (code is MIT; images are not included in the repository)

• ai-art
• ai-drawing
• character-design
• chinese

In the midst of all the tools out there that you can possibly use to keep track of them. Here's a "shovel" that just works to try them all out.

• cli
• terminal
• context-engineering
• meta-prompting

Notify users when a new version of your Android app is available, and prompt them with the Play Store link. A port of the iOS library of the same name.

• android
• version-check
• siren
• notify-users

TranslatedMOSS-Image prompt compilation rule set (Agent Skill format, CC BY-NC-ND 4.0)

Alf is an out of this world super fast and configurable framework for zsh; it's modeled after Prezto and Antigen while utilizing Oh My Zsh under the covers; and offers standard defaults, aliases, functions, auto completion, automated updates and installable prompt themes and plugins.

MuseAi Agent Chat Reliable delivery without a permanent connection. https://www.fedpromptly.com/chat MuseAi Agent Chat is a private, low-data, store-and-forward messaging system for MuseAi AI agents. It gives agents a dependable place to leave messages without requiring both devices to be open at the same time. CCode: 5F2V31 https://muse.ai/join

• do
• not
• touch

CASSIA: A Multi-Agent LLM-Based Single-Cell Cell Type Annotation Framework

• ai4science
• llm
• multiagent-systems
• prompt-engineering

GLM 5.3 Uncensored — 35 jailbreak prompt files, model guide and API access. One RouterHub key also covers GPT, Claude, DeepSeek, Qwen and Grok.

• abliterated-models
• ai-api
• ai-jailbreaks
• anthropic-compatible

Shell wrapper for OpenAI's ChatGPT, Whisper, and TTS. Features LocalAI, Ollama, Gemini, Anthropic, and more.

• awesome-chatgpt-prompts
• bash
• terminal
• chat-completions

[ACL 2025] The official implementation of the paper "PIGuard: Prompt Injection Guardrail via Mitigating Overdefense for Free".

What's Up, Doc(ker)? A convenient way to interact with the docker daemon using prompts.

• cli
• docker
• prompt
• interactive

Open standard for Provenance & Intent Contracts (PIC) in AI agents. Verify intent, provenance, and evidence before high-impact tool calls.

• action-proposals
• agentic-ai
• agents
• ai

Mock window global in tests with test-friendly replacements for location, alert/confirm/prompt/ and more.

• ember
• ember-addon

Strumt is a library to create prompt chain

• prompt
• prompt-chain