Share encrypted secrets with your team. The server never sees a value.
Security projects
Loading…
Security projects
Public projects with traces of AI coding tools in their repositories, sorted by newest listing.
Security · 1,324 projectsReset filters
Secure Java applications with pac4j: authentication and authorization with OpenID Connect, SAML, CAS, OAuth and JWT across Spring Boot and other frameworks.
KiberOgoh UZ is a national cyber shield platform at the mahalla level. It protects citizens from online fraud and cyber threats.
AI translation
Raptor turns Claude Code into a general-purpose AI offensive/defensive security agent. By using Claude.md and creating rules, sub-agents, and skills, and orchestrating security tool usage, we configur
Xencodes is a virtual SMS verification platform. Search for the service you need, choose a country, and get a virtual number that receives your SMS verification code in seconds. Pay as you go in NGN,
Give your AI a passport: a name any wallet can read and a track record anyone can check. Your AI's first one is free.
Hawkeye Sterling — AML/CFT entity risk assessment for dealers in precious metals and stones: structured 0–30 risk scoring, CDD/SDD/EDD verdicts, on-device register and hash-chained audit log. All data
Document-based age verification for online platforms with white-label flows, privacy-first by design, fair billing, and seamless integration via API or packages.
Train your team to spot phishing before attackers do. Realistic simulations, real-time risk analytics, and one-click compliance reporting.
Council of AI is an independent AI-measurement body. Explore the current GSPC measurements, read the change record, verify signed evidence, use the feeds.
Manage, update, and secure all your devices like it's 2026
A digital security agent via WhatsApp. Links, CBU/CVU, phone numbers, emails, and files are analyzed in minutes.
AI translation
Check scam messages, fake job offers, links, phone numbers and UPI QR codes for free. Made in India.
Check emails and URLs instantly. Detect phishing, fake addresses, and malware domains — free, no signup.
Translation pending
Embrace a proactive approach with end-to-end cyber threat management, from anticipation to response.
Encryption hides what a message says. SentinelSpread also hides that it was sent: AES-256-GCM, a real GNU Radio spread-spectrum link, and steganography in ordinary images and audio. 20 working tools.
보이스피싱이 의심되는 통화를 AI가 실시간으로 들으며 위험을 감지하고, 판단을 잠시 멈춘 뒤 객관적 검증과 심리적 안정을 함께 돕습니다.
Translation pending
Static OAuth redirect relay that lets a self-hosted FiestaBoard on a home network complete sign-in. Served at fiestaboard.app/auth.
Translation pending
Paste AI-generated text, see the invisible characters hidden in it, and copy a clean version. Runs entirely in your browser.
See how realHuman scores your visit, and help test it.
Check an AI agent endpoint before you call it: a read-only, no-API-key trust check returning a machine-readable trustDecision from observed reliability evidence.
免费检测你的网络出口：注册 Muse 前先看会不会进等候名单；Muse、Claude、ChatGPT、Gemini 各自看到的 IP 在哪、能不能用；住宅还是机房、DNS / WebRTC 有没有泄露、Claude Code 终端走哪个出口。每条问题都写明怎么改，无需登录。
Translation pending
Open-source agentic DFIR. Agents divide the case on a shared board, write their own tools, and leave a hash-chained record you can put in front of a court. Free under the AGPL.
A public welfare project providing free proxy subscription links and VLESS / Shadowsocks nodes for easy copy-and-import use, along with free proxy software downloads and daily news.
AI translation
Nasiko helps enterprises account for what their AI agents cost, can access, and do, across every model and provider.
OSS SIEM + XDR Powered by Threat intelligence and real time correlation. Built for 24x7 Security Operations with Automated Threat Detection and Response
Every MCP tool call journaled with secrets redacted, risky ones held until you approve. Self-hosted, Apache-2.0.
Discover the power of Tyk AI Studio in controlling AI use, ensuring security, and optimizing workflows in your organization.
Your pull request got reviewed; the published tarball did not. Drydock diffs the exact npm, PyPI, or VS Code artifact and pins supply-chain findings to changed lines.
免费开源的 Windows 桌面工具，实时审计 OpenAI Codex 会话：高危命令、凭据访问、提示注入、投毒篡改、中转站偷换模型。只读日志，不代理、不装证书。
Translation pending
Verify Execution Receipts from Axeum Technologies using a receipt ID or public key
AI summary · website and README
Takes third-party HTML and produces HTML that is safe to embed in your web application. Fast and easy to configure.
Bitcoin-anchored proof a file existed. The file does not leave your browser.
tweetfeed.live MCP server (CF Worker) - 14 IOC threat-intel tools, 7 resources, 3 prompts, no auth, CC0 data. Endpoint: https://mcp.tweetfeed.live
Translation pending
Live IOC feeds for Threat Intelligence - URLs, domains, IPs, hashes. Real-time Twitter feeds, updated every 15 min.
Translation pending
Runs any program inside namespaces with no network interfaces, no routes, no DNS, plus capability dropping and a seccomp filter blocking network syscalls. Two Go modules, no runtime services.
Deterministic crypto inventory for Python wheels, with FIPS compatibility as one lens over it. It gathers evidence; it does not decide FIPS compliance.
Runs several independent, narrowly focused passes over every source file instead of one general “find bugs” prompt, then merges the results. Every file gets a recorded status and every failed pass is
ArgusAI is an AI-powered event detection system for home security. Analyze video feeds from UniFi Protect, RTSP, and USB cameras with multi-provider AI.
Tracyn records every action your AI agents take, pauses the risky ones for a human, and turns the trail into audit-ready evidence. One decorator to start.
Multi-OS sandbox to run AI agents with better constraints (it is not 100% secure, but enough)
Vault is an open-source iPhone and iPad app for the secrets you can't afford to lose: 2FA codes, private notes and crypto recovery phrases. Fully offline, with encrypted backups and protection for whe
Prove quem envenenou o modelo. Reputação imutável, auditável e sem autoridade central.
Translation pending
OAuth2 goodies for the Djangonauts!
Open-source VPN for speed, privacy, and censorship circumvention. Free to download on Android, iOS, Windows, macOS, and Linux.
OXO is a vulnerability scanning orchestrator that automatically binds tools together allowing for rapid scale.
One read-only query in your Supabase SQL editor. Every open policy, table and function, quoted from your database, with the fix and the undo. Free.
Prismor intercepts every tool call your AI agents make, enforces security policies, and logs a full audit trail. Works with all enterprise AI agents.
District Authorities must physically inspect at least ten percent of works under implementation every year. This ranks the works by risk, so that ten percent is chosen rather than assumed.
Enterprise gateway for git-distributed AI agent skill marketplaces — quarantined ingestion, hold-until-approved vetting, a read-only git facade, and an append-only audit ledger.
An AI-powered agentic red team framework that automates offensive security operations, from reconnaissance to exploitation to post-exploitation, with zero human intervention.
SIQ Agent Security：面向 Agent Skills 的可信执行安全运行时。Skill 引导接入、本地 Go 程序裁决、宿主钩子执行保护，以 Ed25519 与 SHA-256 绑定授权、参数与回执；0.4.0 签名正式版已发布。
Translation pending
See who your AI talks to and decide who it does not. All on your computer: no account, no server, open source. Windows, Linux and macOS.
Master your digital identity. Switch freely with one click.
Qualified eIDAS proof, open, automatable and protected by intangible statutes. A pilot is already running. White paper under review, call for partners.
AI translation
한국어 개인정보 비식별화 오픈소스 엔진 — 규칙+로컬 LLM 하이브리드 PII 탐지·마스킹 라이브러리, CLI, MCP 서버 (2026 오픈소스 개발자대회, 팀 마스킹테이프)
Translation pending
Check whether your email has been exposed in a data breach and get an AI-powered risk score with clear steps to reduce your exposure.
Signed receipts for vibe-coded data pipelines. Proves nobody changed your data, and shows the exact link if they did.
Yuzu places agentic colleagues inside your endpoint estate — reasoning over Windows, Linux, and macOS in real time.
Vero is open-source zero-knowledge compliance for AI agent payments. Agents prove eligibility — not identity. MIT licensed. FATF R.15/R.16 aligned. Built on the Open Wallet Standard. Fork it on GitHub
Open-source privacy and approval gateway for AI assistants (MCP): human approval, local PII checks and audit for Gmail, Drive, Slack, Salesforce, Jira and more.
Open-source antivirus for AI agents: block risky tools, secret access, prompt injection, malicious packages, MCP servers, plugins, and skills at runtime.
CyberArena is a live benchmark where two AI agents fight an attack-and-defense CTF: each one exploits the other's vulnerable service while patching its own, round after round. Watch live matches, repl
Check EVM transactions and signatures for security risks before signing
AI summary · website and README
Records agent tool sequences on the laptop, attests coverage, forwards to your SIEM. Apache-2.0.
Point Claude Code, Codex, and VS Code at your org's governed AI gateway
AI summary · website content
CRANE — self-hosted compliance management for the EU Cyber Resilience Act. SBOM analysis, vulnerability tracking, release gates and audit trails in one auditable platform.
Browse live police cameras on a map, filter by department, and build a video wall
Translation pending
AI summary · website and README
Hikyo is a fully open-source, self-hosted control plane that makes configuration state explicit across every environment.
Write a team's threat model as text files in git, compiled and checked automatically
Translation pending
AI summary · revised during review
Buy virtual numbers for OTP & SMS verification across 200+ countries and 1,000+ platforms — pay-per-use, instant delivery, developer-friendly API.
A .NET C# library for building secure, end-to-end encrypted communication applications with industry-standard encryption protocols.
Control who may authorize AI agents to execute real-world actions
Translation pending
AI summary · README
AI cloud video management for the cameras you already own: live streaming, 23 detections and scheduled virtual patrol rounds with a compliance record.
Task-scoped warrants that narrow as agents delegate. Every hop signed, every chain verifiable offline.
Translation pending
本物のAWSでBattleとChallengeを開催。チーム別環境、毎分採点、ランキング、再利用できる問題カタログを備えたApache 2.0のOSSです。
Translation pending
Streamline incident management with a comprehensive frontend that offers intuitive dashboards, investigation workflows, and real-time notifications for efficient response.
KeePassXC Material for Windows: downloads, documentation, and release provenance.
AgentAvow gives any tool, MCP server, or package a signed, verifiable safety grade. Check it free, verify it offline, and get alerted the moment it changes.
Decentralized, self-sovereign identity: a key you hold, people who vouch for you, and social recovery. Built as a spec and a small library for the identity network that
Open-source customer due diligence risk checks for any legal entity. Powered by GLEIF, OpenSanctions, national company registries and the Beneficial Ownership Data Standard.
Orion is a Live DVD for incident handling, forensics, and intrusion analysis
Vulnerability diagnosis and remediation for web systems serving PMEs and fintechs. OWASP Top 10 · TLS · LGPD art. 46. Open source tool suite.
AI translation
Open-source credential broker that issues short-lived SSH, AWS, GitHub, and Kubernetes credentials after FIDO2 hardware verification.
SOVP is a deterministic AI infrastructure certification standard: 180+ parameters, a three-state verdict, Ed25519-signed. U.S. Patent Pending.
Translation pending
Your scanners find issues. This finds the way in: the route from internet exposure, through too much privilege, to a sensitive asset - caught in the pull request that opens it.
Esver OS turns repeated company workflows into verified executable skills. Visage keeps identity local. Mr. Haven keeps capital programmable.
Translation pending
Intelligent Identity & Account Management System with AI-powered automation
Translation pending
Your .env files hold only references. The real values live in an encrypted vault on your machine. No account, no cloud, no telemetry.
Open source ecosystem to regain control over one's rights, identity, security, and economy.
AI translation
Approval gates and runtime authorization for AI coding agents. Decide what agents such as Claude Code, Codex and Cursor may do, what is denied, and what requires human approval — decided before integr
A short, vendor-neutral guide to what a hardware security key actually does — FIDO2 passkeys, TOTP, smart-card (PIV), and OpenPGP — how to set one up, and where to read the real standards.
vet402 buys what x402 endpoints actually sell, verifies fulfillment against the seller's own declaration, and publishes the results with evidence.
Fully client-side WASM web disassembler and viewer. Vibe-coded with ❤️ by Claude.
Translation pending
A secure execution layer for code you can't fully trust — built security-first for AI agents.
AI 보조 보안 개발 도구킷. 보안 스캐너 · ISMS-P PDCA 대시보드 · 자산 관리 · 컴플라이언스 자동화. KakaoTalk·Slack·SNS 링크 공유 미리보기 지원.
Translation pending
AI-powered scam detection and prevention website tailored for elderly people in Malaysia.
A personal blog publishing records of automating home lab security and backup operations using AI.
AI translation
AI summary · revised during review
A self-hosted OpenID Connect provider with a bundled OpenLDAP directory and a web management UI. One login for your modern apps, one LDAP directory for the rest, no phone-home.
Git push proxy — validation, approval and audit in front of your SCM
AI Agents to simplify, streamline, and strengthen your regulatory processes. We currently support regulators like SEBI, RBI, SEC, FINRA, FCA, SAMA, MAS, AMFI.
Secure how software is built in the age of AI agents. Govern what agents use, control what they do, and ensure trusted output - without slowing development.
A sanctions-screening audit: which way of comparing names, and where you set the bar, measured on your own alert history.
Slips, a free software behavioral Python intrusion prevention system (IDS/IPS) that uses machine learning to detect malicious behaviors in the network traffic. Stratosphere Laboratory, AIC, FEL, CVUT
Share the already authenticated session, encrypted with AES individually. The recipient joins with one click. You revoke whenever you want.
AI translation
Logto adds multi-tenancy, enterprise SSO, and RBAC to your SaaS or AI apps. All with OIDC and OAuth 2.1 made simple, fast, and developer-friendly.
The StackRox Kubernetes Security Platform performs a risk analysis of the container environment, delivers visibility and runtime alerts, and provides recommendations to proactively improve security by
A fruit-fly escape reflex, compiled to 173 NAND gates and 6 latches, evaluated gate by gate in your browser inside a voxel world.
A unified, one-command SSO Manager + OIDC proxy stack for home labs and small businesses. Wires together a self-hosted identity provider and a reverse proxy with one setup.sh.
Upload a photo, detect faces with multiple models, blur them, and strip metadata — privacy-first face anonymization.
Free read-only Lite lists every custom Wazuh rule that never fired and the likely reason, including rules dropped at load (7617/7619).
A web management tool that supplements the Wazuh Dashboard: agents, groups, cluster nodes, rules and decoders, ready-made detection packs, API users and logs. Bilingual English / 繁體中文, AGPL-3.0.
Translation pending
Your infrastructure, off the map. The qURL Connector hides your apps and APIs from public scans. One API call creates a private access link for a person or AI agent, with the scope, expiry, and sessio
OSS-Fuzz - continuous fuzzing for open source software.
ThreatLens simulates realistic SOC investigations across identity, endpoint, email, and cloud — and grades your investigation against a hidden ground truth. Not a SIEM. A cyber range for analysts.
Upload. Secure. Retrieve anytime. Keep a private, independent copy of the content your business depends on.
Maester is a test automation framework to help you stay in control of your Microsoft security configuration.
Evidence-first network configuration auditing: every authoritative finding cites the configuration line that proves it.
Check an OpenCloud instance for known vulnerabilities, missing hardening, weak security headers and available updates. Free to use, with no account required.
GameDay testing for MCP servers. Four named experiments over the JSON-RPC wire, in a sandbox, with scripted and local-model seats. Receipts, tapes and a dataset come out. The oracle is the wire, not t
VpnHood is a free, open-source VPN designed to be undetectable, even in restrictive networks — disguising traffic as ordinary browsing to get past firewalls.
Holdcall sits between your agent and its MCP tools. It decides every call on your machine, shows you the real arguments before anything dangerous runs, and keeps a record you can verify offline.
A small key that plugs into USB. Touch it to unlock, approve and authenticate — never a password.
🏆This is the Open Source Security Foundation (OpenSSF) Best Practices Badge (formerly Core Infrastructure Initiative (CII) Best Practices Badge)
AI translation
Verified provenance entries and immutable historical timelines on Avalanche.
Translation pending
Every connection across the organisation, wherever it runs, protected against tomorrow's decryption. Control stays in-house, always.
Translation pending
Get real SIM-based temporary phone numbers instantly. Receive SMS verification codes for 1,300+ services across 150+ countries. Pay only when a code arrives — automatic refund if it doesn't.
Translation pending
Arcjet is the AI agent runtime security platform. Discover the agents running in your organization, enforce policy across every action, prompt, and tool call, and keep the evidence to prove what happe
Analyze JavaScript/TypeScript code in the browser to detect security vulnerabilities without uploading the code to a server.
AI translation
AI summary · website and README
Manage your Keycloak from your AI assistant: clusters, realms, apps, SSO, custom domains, WAF, webhooks and SIEM. One command, browser sign-in, no API key.
Infrastructure that turns AI agent decisions into signed records. The record stays on your machine.
Verifiable provenance on every AI verdict. Open source. On-premise. No cloud dependency.
Translation pending
Detection rules (Sigma-compatible core), real-time Endpoint Security, behavioural scoring, AI coding guardrails, and Agent Traces — W3C TRACEPARENT correlation between AI-agent activity and kernel eve
Automated data broker opt-out runner — removes your personal info from 30+ people-search sites on a monthly schedule
Agadar — scam-message detection for Sorani Kurdish and Iraqi Arabic, with the reasoning shown. Runs entirely in your browser. Python, scikit-learn, char n-grams.
Security scanner for AI agents, MCP servers and agent skills.
TrustTab verifies which of your site's forms are safe and correctly structured for AI agents to act on, and issues a badge anyone can check.
Wazuh is a free and open source security platform that unifies XDR and SIEM protection for endpoints and cloud workloads.
An open standard letting a nonprofit publish, from its own domain, a machine-readable declaration of the giving destinations it authorizes. Consumed by AI agents through W3C WebMCP.
13 layers of defense in depth, subscription metadata encryption, zero frontend frameworks, and a Lite edition of only 8MB. Built on Tauri v2 + Rust, open source and free.
AI translation
A multi-client subscription conversion backend evolved from subconverter, focused on enhancing Mihomo Provider, remote resources, security, and multi-platform deployment.
AI translation
Działa na Twoim komputerze. 98,9% pełnych nazwisk, 23 rodzaje numerów, podmiany odwracalne.
Translation pending
Lightweight, fast web security proxy built in Rust. Capture, replay, fuzz, and scan.
DIY airgapped hardware wallet that uses QR codes for communication with the host
See where any domain stands in the BlackVeil Global Security Index, or run 17 NIST-aligned checks free — then verify, fix and continuously monitor it.
Cognitive Deterministic Memory Security OS for Agentic AI that reaches backward through time to find the quiet change behind today's failure, not the lookalike. Intelligence is not a cloud subscriptio
Security scanner for AI agent skills. Detect vulnerabilities, malicious patterns, security risks, prompt injection, data exfiltration, and supply-chain risks in Claude Code, Codex, and MCP skills befo
Custom Bash and Python scripts used to automate various penetration testing tasks including recon, scanning, enumeration, and malicious payload creation using Metasploit. For use with Ubuntu. Limited
OpenAI's Codex Security CLI and TypeScript SDK for finding, validating, and fixing security vulnerabilities. npm: https://www.npmjs.com/package/@openai/codex-security
An execution-authority gateway for AI agents and APIs. It intercepts consequential HTTP actions, asks Decionis whether they are authorized, and forwards exactly the authorized request once on a single
pinact is a CLI to edit GitHub Workflow and Composite action files and pin versions of Actions and Reusable Workflows. pinact can also update their versions and verify version annotations.
A maritime monitoring system for the waters around Taiwan based on CSIS methodology, integrating SAR satellite and AIS data to track dark vessels and suspicious maritime activities
AI translation
Single-file browser client for the Have I Been Pwned API. No API key, no backend. Passwords are hashed locally and only a 5-character SHA-1 prefix is ever sent.
Vero is a verifiable credibility layer for people and organisations publishing online, built on Midnight. Prove a relevant credential or accountability claim — and choose what you reveal.
Online signature verification from stroke dynamics, benchmarked on SVC2004.
Translation pending
Recover ZecWallet Lite seeds, zcashd wallet.dat files, and standalone Sapling or Sprout keys with a local-first desktop flow.
Free sanctions screening, PEP checks, and adverse media search tool. Plus a comprehensive AML Knowledge Hub covering MLR 2017, POCA 2002, and FCA compliance. Built for compliance professionals.
Scan any Base coin for rugs before you buy: a 0–100 safety score in the feed.
Something feels off? Check the vibe. A second opinion for messages, profiles, invitations and offers: warning signs of scams, grooming, coercion and exploitation, and where to get help.
Live in-browser multi-person pose tracking and zone-based behavior detection. It runs entirely client-side with no backend and no uploads required.
AI translation
106 curated security scans of open-source AI agents, MCP servers and LLM apps - 24 confirmed fixes, run local-first with Semgrep, Gitleaks, Trivy and pip-audit.
Plataforma SaaS completa para adequação à Lei Geral de Proteção de Dados
Translation pending
The Kubernetes-native policy enforcement plane for MCP. Deterministic admission and egress policy, attributable audit, and SIEM export — MIT, self-hosted, no SaaS.
Sandboxes isolados e descartáveis para agentes de IA: MCP, CLI, dashboard web e app nativo de macOS. Rede desligada por padrão, allowlist de domínios e trilha de auditoria. Go + SwiftUI.
Translation pending
Detect and anonymize sensitive entities in text using LLM-powered workflows
Replays sandbox test results comparing how different Git workflow setups resist attacks
Translation pending
AI summary · revised during review
Face ID-style unlock for Omarchy: the infrared camera recognises you at the lock screen, at sudo and in polkit, while your password stays the real key.
Open-source Aadhaar, PAN, GSTIN & UPI detection and reversible masking for AI prompts. Runs on your infrastructure. MIT.
Not everyone is a developer. Not everyone has to be.
Translation pending
The primary threat is accidental destruction — an agent that misreads a path and deletes the wrong folder — not a determined attacker. Network isolation is secondary and off by default; an AI CLI that
Agentic AI Platform for Enterprises. Securely connect all your data and systems. Operate trusted AI with built-in security and governance.
CI/lock collects trusted telemetry across every checkpoint between commit and production — CI/CD builds, security scans (SAST/DAST/SBOM), runtime + cluster integrity (Falco, Linkerd mTLS, kube-bench),
Translation pending
The local-first credential vault your AI agents can use — but never see. 66 testable security constraints. Rust.
AI Agent City is the operations layer for the agent economy: spending limits, monitoring, security, trust, and discovery for AI agents. Human-readable and machine-readable.
Custos demo wallet — mô phỏng và giải thích giao dịch Solana Devnet trước khi ký.
Translation pending
GDPR Chapter V Transfer Impact Assessment skill for Claude — EDPB six-step methodology, CNIL three-way Step 3, four essential guarantees, 12 country profiles, balanced Art. 49 analysis, RoPA interchan
Translation pending
Built it? Time to show it.
One command in your project folder. Built with AI is enough; AI features are optional.
/nomorevibeSee how to list