Security middleware
-
ai-code-reviewer
🔍 AI-powered automated code review tool that analyzes syntax, performance bottlenecks, and security flaws in pull requests.
-
Certance-Field
Cut your GitHub Copilot token bill, locally. Certance Field compresses oversized context before it reaches the model, redacts and scans for secrets, and exports audit evidence. No cloud, no external calls.
-
depup
Drop-in npm packages with all dependencies updated to latest. 1000+ packages, refreshed every 4 hours.
-
etheram
🔧 Develop, compile, and deploy smart contracts effortlessly with the Etheram plugin for Atom, enhancing your Ethereum programming experience.
-
hacksimulator
Browser-based terminal simulator voor ethisch hacken leren - Veilige omgeving voor Nederlandse beginners
-
herdr-guard
Cross-agent command policy for Herdr: audit, alert, and interrupt dangerous shell commands
-
huqan
Local-first, deterministic verification layer for AI claims, memory writes, and risky actions.
-
mcp-sentinel
🛡️ Secure MCP server that lets AI cloud services (Claude, ChatGPT, Gemini, Cursor) remotely control Linux servers. HTTP/SSE transport · API key + JWT auth · IP whitelist · 20 tools · role-based access · audit logs.
-
nsauditor-ai
NSAuditor AI — Open-source, AI-powered network security scanner. 27 plugins, CVE matching, MITRE ATT&CK mapping, verified vulnerabilities, continuous monitoring, MCP integration. Zero data exfiltration. MIT licensed.
-
openclaw-codex-agent
Implement a contract-first dev workflow that plans, runs, verifies, and fixes code tasks for reproducible, auditable, and verifiable development.
-
patient-zero
Supply-chain attack scanner for the agent era. Triage in 30s with `npx patient-zero`, block malicious installs before postinstall runs, or drop into CI as a GitHub Action. Covers npm + Python + MCP agent configs. Free, MIT, no signup, no telemetry.
-
tenant-isolation-postgres
Multi-tenant isolation in PostgreSQL: RLS row scope + a privileged-column trigger that closes the gap RLS cannot express + security-definer metering. 15 integration tests execute the attacks and assert they fail.