GitHub repo leaderboard by stars, growth rate and activity.
A full-stack AI Red Teaming platform securing AI ecosystems via Agent Scan, Skills Scan, MCP scan, AI Infra scan and LLM jailbreak evaluation.
Safety-first guardrails for AI-driven cloud and Kubernetes operations
Evidence-backed use cases, prompts, integrations, evaluations, and safety notes for OpenAI GPT-6 Astra.
Fast, security-first headless browser for AI agents. Built for automation, red teaming, web testing, and scraping, with direct HTTP traffic control and auditable sessions. Pure Rust, no Chromium or V8.
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.
Stop AI agents from doing things you didn't ask for.
A Geiger counter for AI agents — one read-only command that inventories every agent, MCP server, plugin, and AI extension on a machine
| # | Repo | Language | Stars | 30-day trend | Last updated |
|---|---|---|---|---|---|
| 1 | 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 23 hours ago |
| 2 | Safety-first guardrails for AI-driven cloud and Kubernetes operations | Python | 1,935 | last pushed 5 days ago | |
| 3 | Evidence-backed use cases, prompts, integrations, evaluations, and safety notes for OpenAI GPT-6 Astra. | — | 1,078 | last pushed 5 days ago | |
| 4 | Fast, security-first headless browser for AI agents. Built for automation, red teaming, web testing, and scraping, with direct HTTP traffic control and auditable sessions. Pure Rust, no Chromium or V8. | Rust | 633 | last pushed 2 days ago | |
| 5 | 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 23 hours ago | |
| 6 | Stop AI agents from doing things you didn't ask for. | Python | 409 | last pushed 4 months ago | |
| 7 | 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