Young Python growth, turned up in the cybersecurity patch. Fresh from the seed bed.
In the maintainer's words Learn cloud security by building it! An open-source homelab teaching Zero Trust, DevSecOps, IaC, and cloud architecture from the ground up.
~1013 stars a month (new, 41d ago, top 5% in homelab)
A young find from in the security patch, rooted in TypeScript. A seedling, new this season.
In the maintainer's words OpenAI's Codex Security CLI and TypeScript SDK for finding, validating, and fixing security vulnerabilities. npm: https://www.npmjs.com/package/@openai/codex-security
~3282 stars a month (new, 4 months ago, top 30% in cli)
A young Python specimen, spotted in the devsecops patch. Barely out of the soil.
In the maintainer's words Autonomous Offensive Security, Bug Bounty & Red Teaming Agent Framework powered by Hermes Agent, specialized reasoning skills, and multi-model LLM orchestration.
~338 stars a month (new, 3 months ago, top 16% in devsecops)
A young find from in the security patch, rooted in Python. Barely out of the soil.
In the maintainer's words Open-source AI pentester that proves every finding. Machine oracles re-run each exploit; verified bugs ship a proof capsule you can replay yourself.
~240 stars a month (new, 8 months ago, top 21% in vulnerability-scanner)
Spotted in the devsecops patch, a young specimen rooted in Go. A seedling, new this season.
In the maintainer's words High-performance secrets scanner. CLI, Go library, Burp Suite extension, and Chrome extension. 487 detection rules with live credential validation.
~78 stars a month (new, 10 months ago, top 49% in devsecops)
Young Rust growth, turned up in the devsecops patch. Barely out of the soil.
In the maintainer's words Open-source antivirus and firewall for AI agents: block risky tools, secret access, prompt injection, malicious packages, MCP servers, plugins, and skills at runtime.
~141 stars a month (new, 8 months ago, top 32% in devsecops)
A young find from in the self-hosted patch, rooted in Elixir. A seedling, new this season.
In the maintainer's words Let AI agents investigate and operate infrastructure through declared actions, bounded by policy and host-side checks. Approvals when required, with an audit trail.
~78 stars a month (new, 6 months ago, top 52% in devsecops)
A young Python specimen, spotted in the claude-code patch. A seedling, new this season.
In the maintainer's words AI security review CLI: SAST, secret scanning, SCA, threat modeling and architecture review with Claude Code, Copilot, Codex, Gemini, Cursor or an API key. Reads your design docs, Confluence and Jira…
~132 stars a month (new, 3 months ago, top 35% in devsecops)
Young Python growth, turned up in the mcp patch. Barely out of the soil.
In the maintainer's words Production-grade MCP server giving Claude 27 security intelligence tools across 21 APIs — CVE lookup, EPSS scoring, CISA KEV, MITRE ATT&CK, Shodan, VirusTotal, and more.
~244 stars a month (new, 7 months ago, top 22% in devsecops)
Spotted in the mcp patch, a young specimen rooted in JavaScript. A seedling, new this season.
In the maintainer's words The independent security agent for AI-written software. Finds issues, investigates whether they are real, and shows you the evidence. Deterministic core, no API key needed, JSON and SARIF output.
~90 stars a month (new, 10 months ago, top 42% in devsecops)
A young find from in the claude-code patch, rooted in Python. Fresh from the seed bed.
In the maintainer's words Self-hosted runtime control plane for AI agents. Observe or HITL approve or Block rogue tool calls before it executes: secret leaks, prompt injection, supply chain etc in a local dashboard. Agent agn…
~64 stars a month (new, 9 months ago, top 56% in devsecops)
A young find from in the ai-agents patch, rooted in Python. Fresh from the seed bed.
In the maintainer's words Open-source AI security verification for model artifacts, live endpoints, MCP servers, and recorded agent traces. Reproducible evidence for release decisions.
~54 stars a month (new, 4 months ago, top 59% in devsecops)
Young Go growth, turned up in the devsecops patch. Barely out of the soil.
In the maintainer's words Open-source AI agent framework for security engineering across AWS, GCP, Azure, Kubernetes, GitHub & GitLab: AI-powered security review, findings triage, detection and response.
pushed today
~47 stars a month (new, 5 months ago, top 69% in devsecops)
A young Python specimen, spotted in the security patch. A seedling, new this season.
In the maintainer's words Autonomous agentic AI for CRA (Cyber Resilience Act) compliance: scans repos, triages findings, opens Jira tickets, and auto-fixes vulnerabilities via PR.
~116 stars a month (new, 3 months ago, top 39% in devsecops)
Found in the llm patch: a young Python specimen. Barely out of the soil.
In the maintainer's words Open-source red-team testing for AI agents. 320 bundled probes with OWASP LLM Top 10, MITRE ATLAS, and NIST AI RMF mappings. Selected probes use recorded browser requests, MCP tool calls, or mock pay…
pushed today
~37 stars a month (new, 6 months ago, top 82% in devsecops)
Spotted in the ai-agents patch, a young specimen rooted in TypeScript. Barely out of the soil.
In the maintainer's words Access control for AI agents. Set what Claude Code, Codex, Gemini, Cursor and any MCP server are allowed to do, review risky actions before they run, and keep every action on the record.
pushed today
~25 stars a month (new, 9 months ago, top 85% in devsecops)
A young find from in the vulnerability-scanner patch, rooted in Python. Fresh from the seed bed.
In the maintainer's words Open-source cybersecurity analysis agent for Claude Code. Scans projects for vulnerabilities across all OWASP 2025 Top 10 and CWE Top 25 categories. 11 security domains, 60+ secret patterns, parallel…
pushed 26d ago
~41 stars a month (new, 7 months ago, top 75% in devsecops)
A young Python specimen, spotted in the devsecops patch. A seedling, new this season.
In the maintainer's words PYA (Protect Your Ass): security audit plugin for Claude Code. 9 specialist agents, a dated threat feed, verified findings, offline by default.
pushed 28d ago
~38 stars a month (new, 7 months ago, top 79% in devsecops)