7 Viral AI Agent Repos: 4 Checks Before You Install One
Seven popular AI agent repos, four checks before you install any of them (checked 20-21 Oct 2026; star counts change daily).
1. Who made it? Anthropic Cybersecurity Skills is an independent community project by @mukul975. Its README says "Not affiliated with Anthropic PBC".
2. Is it the right repo? Two separate curated lists are both called Awesome Harness Engineering (ai-boost and walkinglabs), and several repos use "Agent Memory"-style names. Match the GitHub owner, not just the name.
3. The licence. OpenViking is AGPL-3.0, which has conditions if you offer a modified version as a service. Browser Use, Scientific Agent Skills and Diagram Design are MIT; agentmemory and Anthropic Cybersecurity Skills are Apache-2.0. Read the licence before business use.
4. The real cost. Browser Use's code is MIT and free, but you pay for the AI model you connect to it. Its optional Browser Use Cloud starts from $0.02 per browser-hour (the project's own figure).
Also: agentmemory's "95.2% retrieval" and Scientific Agent Skills' "250,000+ scientists" are the projects' own claims. Diagram Design has a Claude Code plugin and also works with other agents.
Repos (all 7, public on GitHub):
Browser Use: browser-use/browser-use
agentmemory: rohitg00/agentmemory
Scientific Agent Skills: K-Dense-AI/scientific-agent-skills
Diagram Design: cathrynlavery/diagram-design
Anthropic Cybersecurity Skills (community project, not made by Anthropic): mukul975/Anthropic-Cybersecurity-Skills
Awesome Harness Engineering (two lists share the name): ai-boost/awesome-harness-engineering and walkinglabs/awesome-harness-engineering
OpenViking (AGPL-3.0): volcengine/OpenViking
Browser Use Cloud pricing: browser-use.com
Which check would have caught you out?
#AI #AIagents #GitHub #shorts
Made with AI-generated visuals and voice.
1 like · 44 views
AI 에이전트를 위한 최대 규모의 오픈 소스 사이버 보안 기술 라이브러리
818개의 실무급 사이버 보안 기술 · 34개의 보안 영역 · 6개의 프레임워크 매핑 · 26개 이상의 AI 플랫폼
mukul975/Anthropic-Cybersecurity-Skills
2 likes · 1 repost · 213 views
why bother listing ten... when 'Oh My Hermes' is all you need?
and he posted the wrong Oh My Hermes link. He's so stupid;
rlaope/oh-my-hermes
4 likes · 540 views
Equips AI agents with 818 structured cybersecurity skills mapped across six major frameworks, enabling senior-level security analysis within coding assistants.
mukul975/Anthropic-Cybersecurity-Skills t.co
37 likes · 6 reposts · 3,527 views
Defensive cybersecurity skills (Blue team)
Github: fatehMohamed14/anthropic-cybersecurity-skills-defensive, This is a fork from mukul975/anthropic-cybersecurity-skills.
The original repository is great. It includes 818 skills all together: detection playbooks next to live exploit code, credential crackers and C2 framework guides. Very useful for teams. Dangerous for others. Here is what is different:
🚫 𝟏𝟎𝟔 offensive skills removed - every exploit every C2 framework, every credential-cracking tool. 712 Skills that are purely defensive are left.
🔒 Safe by design - nothing in the skill path can run an attack. Use it for learning for authorized testing or right alongside production systems.
🧰 Per-skill tool manifest added - a machine- list of exactly which tool (Splunk, VirusTotal, Volatility, YARA…) each skill actually needs, so you know what to install before you try to run it.
📋 Curated, documented not just asserted - the removal criteria and the full list of what was cut are public in the repo so the "defensive-only" claim is auditable not just a README promise.
🔌 Bundled MCP servers - to-connect MCP servers, for [name the actual ones - e.g. VirusTotal, DNS/WHOIS lookups] so skills can call real tools out of the box instead of just describing them.
The largest open-source cybersecurity skills library for AI agents mukul975/Anthropic-Cybersecurity-Skills
22 likes · 4 reposts · 1,597 views
@Teknium btw I found these skills for cyber security audit mukul975/anthropic-cybersecurity-skills
1 like · 9 views
Mentions
7 Viral AI Agent Repos: 4 Checks Before You Install One Seven popular AI agent repos, four checks before you install any of them (checked 20-21 Oct 2026; star counts change daily). 1. Who made it? Anthropic Cybersecurity Skills is an independent community project by @mukul975. Its README says "Not affiliated with Anthropic PBC". 2. Is it the right repo? Two separate curated lists are both called Awesome Harness Engineering (ai-boost and walkinglabs), and several repos use "Agent Memory"-style names. Match the GitHub owner, not just the name. 3. The licence. OpenViking is AGPL-3.0, which has conditions if you offer a modified version as a service. Browser Use, Scientific Agent Skills and Diagram Design are MIT; agentmemory and Anthropic Cybersecurity Skills are Apache-2.0. Read the licence before business use. 4. The real cost. Browser Use's code is MIT and free, but you pay for the AI model you connect to it. Its optional Browser Use Cloud starts from $0.02 per browser-hour (the project's own figure). Also: agentmemory's "95.2% retrieval" and Scientific Agent Skills' "250,000+ scientists" are the projects' own claims. Diagram Design has a Claude Code plugin and also works with other agents. Repos (all 7, public on GitHub): Browser Use: browser-use/browser-use agentmemory: rohitg00/agentmemory Scientific Agent Skills: K-Dense-AI/scientific-agent-skills Diagram Design: cathrynlavery/diagram-design Anthropic Cybersecurity Skills (community project, not made by Anthropic): mukul975/Anthropic-Cybersecurity-Skills Awesome Harness Engineering (two lists share the name): ai-boost/awesome-harness-engineering and walkinglabs/awesome-harness-engineering OpenViking (AGPL-3.0): volcengine/OpenViking Browser Use Cloud pricing: browser-use.com Which check would have caught you out? #AI #AIagents #GitHub #shorts Made with AI-generated visuals and voice.
AI 에이전트를 위한 최대 규모의 오픈 소스 사이버 보안 기술 라이브러리 818개의 실무급 사이버 보안 기술 · 34개의 보안 영역 · 6개의 프레임워크 매핑 · 26개 이상의 AI 플랫폼 mukul975/Anthropic-Cybersecurity-Skills
why bother listing ten... when 'Oh My Hermes' is all you need? and he posted the wrong Oh My Hermes link. He's so stupid; rlaope/oh-my-hermes
Equips AI agents with 818 structured cybersecurity skills mapped across six major frameworks, enabling senior-level security analysis within coding assistants. mukul975/Anthropic-Cybersecurity-Skills t.co
Defensive cybersecurity skills (Blue team) Github: fatehMohamed14/anthropic-cybersecurity-skills-defensive, This is a fork from mukul975/anthropic-cybersecurity-skills. The original repository is great. It includes 818 skills all together: detection playbooks next to live exploit code, credential crackers and C2 framework guides. Very useful for teams. Dangerous for others. Here is what is different: 🚫 𝟏𝟎𝟔 offensive skills removed - every exploit every C2 framework, every credential-cracking tool. 712 Skills that are purely defensive are left. 🔒 Safe by design - nothing in the skill path can run an attack. Use it for learning for authorized testing or right alongside production systems. 🧰 Per-skill tool manifest added - a machine- list of exactly which tool (Splunk, VirusTotal, Volatility, YARA…) each skill actually needs, so you know what to install before you try to run it. 📋 Curated, documented not just asserted - the removal criteria and the full list of what was cut are public in the repo so the "defensive-only" claim is auditable not just a README promise. 🔌 Bundled MCP servers - to-connect MCP servers, for [name the actual ones - e.g. VirusTotal, DNS/WHOIS lookups] so skills can call real tools out of the box instead of just describing them.
The largest open-source cybersecurity skills library for AI agents mukul975/Anthropic-Cybersecurity-Skills
@Teknium btw I found these skills for cyber security audit mukul975/anthropic-cybersecurity-skills