AgentWard – Built for all, hardened for OpenClaw.
GitHub repository with 59 stars and 8 forks.
Language: TypeScript
Topics: agent-security, openclaw, openclaw-plugin, openclaw-security, defense-in-depth, llm-agent, llm-security, prompt-injection-defense
2026-06-05: 59 stars and 8 forks.
Open detection standard -- like Sigma, but for AI agents. 425 rules, shipped in Microsoft AGT, Cisco AI Defense, MISP, OWASP A-S-R-H. 97.1% recall on NVIDIA garak. NIST OSCAL Path 1.
GitHub repository with 250 stars and 32 forks.
Trending score: 0.94; stars gained: +2; forks gained: +0.
Language: TypeScript
Topics: agent-security, agent-threat-rules, ai-security, garak, llm-security, mcp-security
Metasploit for AI agents: scan, attack, and fix AI agents and MCP servers. Open source security toolkit.
GitHub repository with 30 stars and 2 forks.
Trending score: 0.35; stars gained: +0; forks gained: +0.
Language: TypeScript
Topics: tool, agent-security, ai-agents, ai-security, llm-security, mcp
One scan for AI risk. `opena2a review` checks an AI project across credentials, shadow agents, MCP servers, and dependencies, returns a score, and routes each finding to the tool that fixes it. Open source.
GitHub repository with 19 stars and 5 forks.
Trending score: 0.33; stars gained: +0; forks gained: +0.
Language: TypeScript
Topics: agent-security, ai-agents, ai-security, claude-code, compliance, copilot
Agentic framework for connecting LLMs to messaging platforms, with persistent memory, skills, scheduled tasks, self-healing supervision, and distributed multi-agent collaboration
GitHub repository with 6 stars and 0 forks.
Trending score: 0.05; stars gained: +0; forks gained: +0.
Language: TypeScript
Topics: agent-security, agent-swarm, agentic-ai, ai-agents, ai-assistant, ai-framework
An OWASP-aligned intentionally vulnerable platform for learning and testing AI, LLM, RAG, MCP, and Agentic AI security.
GitHub repository with 16 stars and 5 forks.
Trending score: 0.04; stars gained: +0; forks gained: +0.
Language: TypeScript
Topics: agent-security, ai-security, ctf, cybersecurity, docker, llm
Desktop app to manage markdown knowledge bases
GitHub repository with 15,823 stars and 1,080 forks.
Trending score: 5.36; stars gained: +947; forks gained: +53.
Language: TypeScript
🎨 Local-first, open-source Claude Design alternative. 🖥️ Native desktop app. ⚡ 259+ Skills · ✨ 142+ Design Systems 🖼️ Web · desktop · mobile prototypes · slides · images · videos · HyperFrames 📦 Sandboxed preview · HTML/PDF/PPTX/MP4 export 🤖 Claude Code / OpenClaw / Codex / Cursor / OpenCode / Qwen / Copilot / Hermes / Kimi & 17+ CLIs.
GitHub repository with 64,116 stars and 7,150 forks.
Trending score: 5.14; stars gained: +1,086; forks gained: +115.
Language: TypeScript
Topics: agent-skills, ai-agents, ai-design, byok, claude-code-for-design, claude-design
The open source coding agent.
GitHub repository with 173,822 stars and 20,947 forks.
Trending score: 5.07; stars gained: +1,032; forks gained: +175.
Language: TypeScript
An Open Source implementation of Notebook LM with more flexibility and features
GitHub repository with 29,634 stars and 3,363 forks.
Trending score: 5.05; stars gained: +972; forks gained: +114.
Language: TypeScript
Let's use AI to Earn!
GitHub repository with 20,941 stars and 3,139 forks.
Trending score: 4.90; stars gained: +455; forks gained: +58.
Language: TypeScript
Topics: auto-publish, douyin, electron-app, electron-react, kuaishou, tool
A modern GUI client based on Tauri, designed to run in Windows, macOS and Linux for tailored proxy experience
GitHub repository with 125,253 stars and 9,105 forks.
Trending score: 4.83; stars gained: +475; forks gained: +23.
Language: TypeScript
Topics: clash, clash-meta, clash-verge, linux, mac, mihomo
Capability-based agent runtime with fine-grained policies . Brokering access directly within the agent's operating context, with zero setup and zero latency
GitHub repository with 2,662 stars and 184 forks.
Trending score: 2.51; stars gained: +36; forks gained: +1.
Language: Rust
Topics: agent-sandbox, agent-security, ai-agent-sandbox, ai-agent-security, ai-agents, ai-security
A full-stack AI Red Teaming platform securing AI ecosystems via OpenClaw Security Scan, Agent Scan, Skills Scan, MCP scan, AI Infra scan and LLM jailbreak evaluation.
GitHub repository with 3,882 stars and 379 forks.
Trending score: 2.42; stars gained: +13; forks gained: +1.
Language: Python
Topics: agent, llm, scanner, security, vulnerability, agent-security
A local control plane for AI agents — see what they do, approve what matters, keep secrets out. Rust + Tauri + Chrome MV3.
GitHub repository with 388 stars and 24 forks.
Trending score: 1.67; stars gained: +2; forks gained: +0.
Language: Rust
Topics: agent-security, ai-agents, audit-log, desktop, llm, local-first
The security layer for AI coding agents : Skill governance, safe package recommendations, MCP/tools guardrails, secret protection, runtime policy enforcement and full audit visibility with a self-serve dashboard.
GitHub repository with 185 stars and 16 forks.
Trending score: 1.40; stars gained: +3; forks gained: +0.
Language: Python
Topics: cybersecurity, security, agent-security, agentic-ai, agents, ai-security
🛡️ A curated list of resources on agent skills security: attacks, defenses, frameworks, and benchmarks for securing AI agent tool use and skill ecosystems
GitHub repository with 16 stars and 15 forks.
Trending score: 1.07; stars gained: +1; forks gained: +2.
Topics: agent-security, ai-safety, awesome-list, llm-security, mcp, owasp
Credential vault for AI agents. Log in once via Oauth2 or API Key. Every agent stays authenticated — headless, no SaaS, agents never see your credentials.
GitHub repository with 51 stars and 7 forks.
Trending score: 1.02; stars gained: +4; forks gained: +0.
Language: Python
Topics: ai-agents, authentication, cli, headless, local-first, mcp