Put your idea on trial in front of a jury of 12 Claudes. A free Claude Code skill.
Repository Index
47,133 repositories indexed
121–144 of 164 · Most stars
Autonomous OODA-loop pentesting agent. Hermes brain, Kali + Playwright tools over MCP, ATT&CK as the Orient language.
- ai-agents
- autonomous-agents
- kali-linux
- llm-agents
TranslatedTreat agents as functions, and write ideas as programs. Agent-native functional language with a CLI, Web IDE, goal-driven bots and live UI. Source-available; no AI training.
TranslatedBring the Codex imagegen workflow and prompt library to any agent; supports one-command installation with npm/pnpm, a companion skill, a standalone API, and a Qwen-Image compatible gateway.
- ai-agent
- codex
- image-generation
- npm-package
The first exam for code agents in the physical world: frozen robot tasks from many benchmark suites, each answered with a program and verified in a separate sandbox. Runs on Harbor.
- ai-agents
- benchmark
- coding-agents
- embodied-ai
How many bugs can LMs find & fix in large codebases?
Runtime defense against memory poisoning in AI agents (OWASP ASI06). Drop-in for LangChain, OpenAI Agents, AutoGen, CrewAI and mem0.
Watchtower | Self-hosted AI security assessment, asset intelligence, and evidence workflows.
- ai-agents
- attack-surface-management
- docker
- penetration-testing
CRAB (Clean Rebuild of Anything's Behavior): rebuild software from behavior, not source code. An MCP-powered toolkit for black-box observation, clean-room reimplementation, and behavioral verification.
- clean-room-reimplementation
- ai-agents
- behavioral-testing
- black-box-testing
A collection of AI Skills specialized in Django Backend development
Zeline — an open-source agentic AI framework developed by Zerolinear.
Autonomous desktop intelligence with MCU Ultron persona, mood-aware workspace orchestration, cyber security sentry, and full PC control.
- aegnts
- ai
- jarvis
- jarvis-ai
TranslatedSay "¥35, not spicy, no ice" → one answer + a copyable order card. Official calculate-price only. Zero-dependency MCP skill. McDonald's ordering Skill.
Save up to 30% of your AI coding tokens. Scubiee turns any codebase into searchable context for your AI coding agent. A local context engine for Cursor, Claude Code, Copilot, Codex, and more: semantic search, code relationships, live sync, MCP integration, and code that never leaves your machine.
TranslatedSimple Reviewer: a Codex skill for AI-assisted coding and Vibe Coding. Explain code, visualize workflows, and verify goals with evidence.
- ai-agents
- ai-assisted-coding
- code-explanation
- code-quality
TranslatedMcDonald's meal pairing decision Skill | Computes the top three optimal choices out of 1881 combinations, and tells you why they are not the others. Calorie control, dietary restrictions, and max-min fair allocation for group orders; the LLM does not take part in calculating money, and every number is traceable.
TranslatedA conversational AI Skill based on McDonald's official MCP, supporting meal recommendations, store price comparison, coupon lookup, nutrition calculation, and exploration records, and generating voxel-style shareable images through Python.
- ai-agent
- ai-skill
- coupons
- data-visualization
TranslatedAnyone can claim the coupons in 麦麦省 (Maimaisheng, "McMcSave"), but claiming a coupon doesn't mean the store downstairs will accept it. After claiming all coupons in one click, it checks store by store which coupons can actually be redeemed, and calculates the actual price paid after coupons, directly answering "which store to go to, which coupon to use, and how much you save". Based on McDonald's MCP.
TranslatedSee which McDonald's benefits are about to expire, which are worth using, and which are not worth spending money on just because they are expiring. A WorkBuddy Skill built on the official McDonald's MCP: read-only queries of coupons and points, and, based on your budget, up to two meal plans priced through the official interface. McDonald's coupon & points expiry assistant — a WorkBuddy Skill on the official McDonald's MCP. Read-only queries, official price calculation, max 2 budget-friendly plans.
- ai-agent
- mcdonalds
- mcp
- model-context-protocol
TranslatedMcDonald's MCP skill: list of orders pending review, progress toward good-review gift redemption, order top-ups to reach the invoice reimbursement threshold, single lucky draw confirmation. 99 tests, unofficial product.
Fault-injected tool environments with side-effect grading for evaluating and post-training LLM agents
Let agents control many desktop software directly from the cli, with one pip install, and no MCP servers.
- adobe-after-effects
- adobe-audition
- adobe-illustrator
- claude-code
Credential gateway for AI agents. Log in once via Oauth2 or API Key. Every agent stays authenticated — headless, no SaaS, agents never see your credentials.
Nosis is a lightweight personal agent runtime: per-session execution boundaries with OS-level sandboxing, computer use, a full built-in toolset, Skill / Plugin / MCP extensions, one runtime shared by GUI and TUI, and file-persisted sessions, plans, and memory.
- agent-framework
- agent-runtime
- agent-skills
- ai-agent