Havuz

Offline pentest workflow tracker — turns nmap output into a port-aware, KB-matched recon checklist in under 30 seconds. Self-hosted, single

Post-quantum age key generation and paper backup tool with QR codes

Security-focused linter for Docker Compose files. Catches dangerous misconfigurations before they reach production. Grounded in OWASP and CI

Coding-agent tools on TypeSafe's Jev, measured in public. review-router: caught 13 of 13 CVE fixes a filename rule sent to a quick review. j

The agent that writes the code never reviews it. Spec-driven TDD with agent separation, adversarial QA, and dynamic rigor for Claude Code.

Find what's using a port, who started it (Claude Code, Cursor, Docker…), whether your network can reach it, and stop it safely. An lsof alte

Vulnerability scanning with your own scanners and threat feeds, plus a coding agent that opens the fix PR. CLI, GitHub Action, or scheduled

Zero-trust agentic AI platform. Supports SaaS and OnPrem (airgapped) deployments.

DPI-resistant SOCKS5/HTTP tunnel over TLS+WebSocket for self-hosted single-VPS setups

C2 server fingerprinter — Cobalt Strike, Sliver, Mythic, Havoc, Brute Ratel

dj - Dynamic JS File Extractor - intelligently detects dynamically loaded JavaScript files by statically analyzing website HTML and JS code

Agentless SOC & GRC — SIEM, FIM, MITRE ATT&CK, compliance over SSH. Nothing installed on servers. Web · Windows · Linux · Docker.

Amazon Bedrock AgentCore enterprise platform accelerator with AWS CDK, Terraform organization guardrails, MCP/A2A agents, security, memory,

Secrets management for AI agents: approve API keys and credentials on your phone with biometrics, delivered end-to-end encrypted into the ta

Local-first password, 2FA and recovery vault for Windows and Linux. Your vault is encrypted on your device and never sent to a server. AGPL.

AI code quality toolkit — deterministic linter for the AI coding era. 22 detectors, GitHub Action PR gate, zero LLM required.

The self-hosted token, certificate, license, and secret expiration manager with automated Certificate Lifecycle Management (CertOps) for tea

Six skills tell coding agents how to work. Two guards enforce the parts that should not depend on judgment.

Paste a redacted copy of your clipboard with one hotkey. Hides API keys, tokens, passwords and PII (900+ patterns) before they reach AI chat

Find and fix web-app vulnerabilities in one command — SAST + DAST + AI, for devs who aren't security experts.

Skill router and prompt-injection firewall for AI coding agents: gives Claude Code, Codex and Cursor the few skills, MCP servers and tools e

Experimental source-available SQLite/libSQL backend for human-and-agent-native workflows, with Studio and scoped MCP access.

Syna — offline-first LAN messenger. Kotlin Multiplatform, end-to-end encrypted (X25519 + AES-256-GCM), burn-after-reading, group chat, self-

Bounded repository context and verified patches for Codex and Claude Code. Explicit edit grants, source fingerprints, isolated worktrees, ac

Argus — the all-seeing eye for Microsoft 365. Self-hosted, Dockerized notification & reporting for IT admins and security teams.

CI-friendly CLI and API that fails builds when deployed URLs are missing or misconfigure HTTP security headers (HSTS, CSP, COOP, cookies...)

Safely run untrusted repos (fake-interview malware, infostealers, RATs) in a locked-down, ephemeral container. No host secrets reachable, ne

The AI security agent guards your code.

Your AI agent needs your API keys. It doesn't need to see them. tokenstash writes keys straight into .env.local for Claude Code, Codex, Curs

Solana's SOL-0XX security standard — bug-class rules distilled from $514M of real exploits, firing as you code in every AI tool, editor & CI

Security-hardened openclaw with auth gateway, AES-256 encryption and session management

Docker sandbox for the Claude Code CLI. Runs Claude against one project folder — including with --dangerously-skip-permissions — while your

Local guardrails for coding agents. Policy, approvals, 86 safety packs, OS sandbox, audit trail — no Docker.

Session-scoped GPT-5.6 agent routing for Claude Code

Agent-assisted vulnerability research across Rust, Android APKs, and AI agents: independent discovery, skeptical triage, verification, and p

Read-only Telegram MCP server. Search chats, read messages, and download attachments from any MCP client.

Policy-aware AI permission reviewer for OpenCode V1 and V2. Evaluates tool and command requests, allowing, denying with feedback, or escalat

One-click multi-instance Telegram web proxy installer (MTProxy + Caddy) for Debian/Ubuntu servers.

Real-time data anonymization for LLMs: secure your logs and conversations across cloud or local environments. Docker-ready & Multi-IA suppor

Detect and patch vulnerabilities in AI-generated Python code — VS Code extension

Git-aware secret & .env leak guard for TypeScript/Node — sub-second pre-commit scanning with the lowest false-positive rate.

Self-hosted CVE triage for your root servers: Trivy scans, LLM-judged exploitability, only the findings that matter.

Static security review for AI agent configs (LangGraph, CrewAI, OpenAI Agents, MCP): maps source-to-tool flows and flags untrusted input tha

Replayable proof that a bug fails before the patch and passes after it - a GitHub App that turns fix claims into verifiable evidence bundles

Run a command in a sandbox with the same flags on every OS — one capability model compiled to Seatbelt (macOS), gVisor (Linux), and AppConta

🔐 The local-only AI secret manager for the AI-coding era with MCP, CLI, Web UI, TUI, Chrome Extension and Mobile App. No cloud, No telemetry

PII masking middleware for DeepSeek Harness: anonymize names, phones, emails, ID cards, bank cards, keys, and addresses to placeholders befo

Self-hosted counter-surveillance for the networks you control: map device and network exposure, verify trusted routes, and hold sensitive ac

🛡️Self-hosted security analytics & threat detection for Discord servers. Real-time phishing, raids, spam detection. Privacy-first with GDPR

One command. Full stack. Zero compromise. — All-in-one Claude Code skill with 33 modes, 6-layer security, 23 hooks, and 75% token savings