95 packages found
It is a comprehensive resource hub compiling all LLM papers accepted at the International Conference on Learning Represe
Local-first personal agentic OS and everything app for coding, knowledge work, web design, automations, and artifacts.
The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development f
Official companion repository for our survey "A Survey of the OpenClaw Ecosystem: From Platform Extensibility to Constra
Local-first production-readiness system for AI-built apps: read-only audit, evidence-based 0-100 score, guided fixes, le
Veto MCP — gives every major AI CLI (Claude Code, Codex, Gemini, Cursor, Windsurf) a council of 49 specialist agents + 9
rUvOS — the agentic operating system. A single static Rust binary that runs as an MCP server, giving Claude Code persist
A memory engine for conversational AI agents, inspired by neuroscience and Buddhist psychology
Security, cost, and health governance proxy for MCP infrastructure — YAML policy engine, OAuth 2.1/OIDC, web dashboard,
One command. Full stack. Zero compromise. — All-in-one Claude Code skill with 33 modes, 6-layer security, 23 hooks, a
Comprehensive toolkit extending Claude Code with 70+ slash commands, specialized AI agents, and automation workflows. Fe
🛡️The governance runtime for AI agents. Intercept actions, enforce guard policies, require approvals, and produce audit
Automated security investigation tool using Microsoft MCP Servers, GitHub Copilot, Python Modules and custom copilot-ins
Governed shared memory for AI agent fleets — multi-agent, multi-tenant, MCP-native. Trust tiers, keystone policies, audi
A curated list of tools, papers, and datasets for applying AI to cybersecurity tasks. This list primarily focuses on mod
@anthropics✓ OfficialSkills for threat modeling, scanning, triage, patching, plus an autonomous scanning harness you can /customize
Claude Code / Codex / AI configs for the expert Solana builder. CLAUDE.md, agents, commands, hooks, rules, skills and se
Open-source AI agent firewall for MCP security and agent egress. Scans mediated HTTP, MCP, A2A, and WebSocket traffic fo
Leave things better than you found them! This claude skill seamlessly integrates iterative feedback across your claude s
AI builds faster than anyone, with no skin in the game and no memory of yesterday. How do you govern that? With X2, deci
Run Claude in self-improving loops to optimize measurable goals.
This pattern describes how to implement a Model Context Protocol (MCP) server that integrates three industry-standard se
Fully autonomous AI Agents system capable of performing complex penetration testing tasks
A fully local, autonomous AI penetration-testing agent powered by Gemma 4-12B and a Flask MCP tool server. Runs recon, a
A Claude Code skills and project-team toolkit repository for standardized workflows, governance automation, and quali
DockaShell is an MCP server that gives AI agents isolated Docker containers to work in. MCP tools for shell access, file
Bug bounty agent framework for Claude Code, Codex, Gemini, Cursor, Windsurf, Copilot, and OpenClaw — 48 agents, 26 comma
Open, audit-grade agentic data quality framework with portable industry packs
Eleven Claude Code skills ported to OpenCode: code-review, security-review, feature-dev, frontend-design + 7 more. One c
Agentic SWMM is an automated, auditable, and memory-informed framework for reproducible stormwater modelling, integratin
Decision audit trail + persistent memory for AI trading agents. Outcome-weighted recall, SHA-256 tamper detection, 17 MC
GUARDRAIL - MCP Security - Gateway for Unified Access, Resource Delegation, and Risk-Attenuating Information Limits
A 3-stage safety guardrail agent for LLM coding assistants (Claude Desktop, Cursor, CodeX) via MCP protocol.
Curated marketplace of AI skills, agents, and rules for cloud, zero-trust, and compliance-aware engineering - works with
A Model Context Protocol server for Firebird 2.5 – 5.0, written in Delphi with the official `fbclient` driver. It lets a
Protect against malicious open source packages 🤖
Agentic AI research papers, benchmarks, frameworks, and tools curated across 24 domains.
Claude Skills for Governance, Risk, & Compliance (GRC): Expert-level compliance guidance for ISO 27001, SOC 2, FedRAMP,
ToolHive is an application that allows you to install, manage and run MCP servers and connect them to AI agents
Exemplo de uso da ferramenta MCP Audit (APIsec) em um pipeline do Azure DevOps. Testes realizados com vários tipos de MC
Exemplo de uso da ferramenta APIsec MCP Discovery and Audit em um pipeline do Azure DevOps. Testes realizados com vários
Teaches Claude to use a dozen visualization-building tools — raster, SVG, web, video, terminal, interactive, gaze plots,
AI-Powered Paid Advertising Audit & Optimization — 190 checks across 5 platforms, AI creative scoring, live API connecto
Open-source AI security platform providing perimeter defense for LLMs and AI agents through swarm analysis, policy enfor
AI-powered smart contract forge — generate, audit, fix & compile contracts with 8-agent security analysis, x402 payments
@awslabs✓ OfficialOSCAL tools for AI agents
Comprehensive paid advertising audit & optimization skill for Claude Code. 250+ checks across Google, Meta, YouTube, Lin
Open-source toolkit for the QVeris capability routing network: CLI, MCP server, Python SDK, skills, and REST API docs fo
A coding agent CLI hook that acts as a safety net, catching destructive git and filesystem commands before they execute.