GitHub repo leaderboard by stars, growth rate and activity.

• Tencent

  #1Tencent/AI-Infra-Guard

  A full-stack AI Red Teaming platform securing AI ecosystems via Agent Scan, Skills Scan, MCP scan, AI Infra scan and LLM jailbreak evaluation.

  Python6,215 starslast pushed 24 hours ago
• valqore

  #2valqore/valqore

  Safety-first guardrails for AI-driven cloud and Kubernetes operations

  Python1,935 starslast pushed 5 days ago
• Anil-matcha

  #3Anil-matcha/awesome-gpt-6-astra

  Evidence-backed use cases, prompts, integrations, evaluations, and safety notes for OpenAI GPT-6 Astra.

  —1,078 starslast pushed 5 days ago
• h5i-dev

  #4h5i-dev/h5i

  Fast, red-teaming browser built for AI agents, with direct HTTP traffic control, sandboxed execution, and auditable sessions. Pure Rust.

  Rust635 starslast pushed 1 hour ago
• decionis

  #5decionis/agent-safe-pipeline

  Reference architecture for AI agents that propose actions but cannot authorize them — immutable intent capture, an independent Decionis policy verdict (ALLOW/ESCALATE/BLOCK), verified human approval, and a SafeExecutor that consumes a single-use intent-bound grant.

  TypeScript532 starslast pushed Yesterday
• pegasi-ai

  #6pegasi-ai/reins

  Stop AI agents from doing things you didn't ask for.

  Python409 starslast pushed 4 months ago
• Atomburstofficial

  #7Atomburstofficial/geiger

  A Geiger counter for AI agents — one read-only command that inventories every agent, MCP server, plugin, and AI extension on a machine

  JavaScript77 starslast pushed Yesterday

#	Repo	Language	Stars	30-day trend	Last updated
1	Tencent Tencent/AI-Infra-Guard A full-stack AI Red Teaming platform securing AI ecosystems via Agent Scan, Skills Scan, MCP scan, AI Infra scan and LLM jailbreak evaluation.	Python	6,215	—	last pushed 24 hours ago
2	valqore valqore/valqore Safety-first guardrails for AI-driven cloud and Kubernetes operations	Python	1,935		last pushed 5 days ago
3	Anil-matcha Anil-matcha/awesome-gpt-6-astra Evidence-backed use cases, prompts, integrations, evaluations, and safety notes for OpenAI GPT-6 Astra.	—	1,078		last pushed 5 days ago
4	h5i-dev h5i-dev/h5i Fast, red-teaming browser built for AI agents, with direct HTTP traffic control, sandboxed execution, and auditable sessions. Pure Rust.	Rust	635		last pushed 1 hour ago
5	decionis decionis/agent-safe-pipeline Reference architecture for AI agents that propose actions but cannot authorize them — immutable intent capture, an independent Decionis policy verdict (ALLOW/ESCALATE/BLOCK), verified human approval, and a SafeExecutor that consumes a single-use intent-bound grant.	TypeScript	532		last pushed Yesterday
6	pegasi-ai pegasi-ai/reins Stop AI agents from doing things you didn't ask for.	Python	409		last pushed 4 months ago
7	Atomburstofficial Atomburstofficial/geiger A Geiger counter for AI agents — one read-only command that inventories every agent, MCP server, plugin, and AI extension on a machine	JavaScript	77	—	last pushed Yesterday

All · 11,474