安全项目
正在加载…
安全项目
在代码仓库中发现AI编程工具痕迹的公开项目，按最近收录排序。
安全 · 1,392个项目清除筛选
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.
翻译准备中
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.
翻译准备中
Live in-browser multi-person pose tracking and zone-based behavior detection. Runs entirely client-side, no backend, no upload.
翻译准备中
106 次精选的开源 AI 代理、MCP 服务器和 LLM 应用安全扫描——24 项已确认修复，本地优先运行，使用 Semgrep、Gitleaks、Trivy 和 pip-audit。
AI 翻译
The Kubernetes-native policy enforcement plane for MCP. Deterministic admission and egress policy, attributable audit, and SIEM export — MIT, self-hosted, no SaaS.
翻译准备中
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.
翻译准备中
Replays sandbox test results comparing how different Git workflow setups resist attacks
翻译准备中
AI 摘要 · 审核时修订
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.
翻译准备中
Open-source Aadhaar, PAN, GSTIN & UPI detection and reversible masking for AI prompts. Runs on your infrastructure. MIT.
翻译准备中
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
翻译准备中
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),
翻译准备中
The local-first credential vault your AI agents can use — but never see. 66 testable security constraints. Rust.
翻译准备中
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.
翻译准备中
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
翻译准备中
GDPR Breach Response Sentinel Agent Skill (open standard) — ENISA severity assessment, EDPB case matching, Art. 33/34 notification support, audit-ready .docx generation
翻译准备中
Read-only macOS notch + menu bar monitor for Claude Code and Codex. Open source, free, local-only. Risk-scores every tool call and tracks the footholds agents leave behind.
翻译准备中
A policy-enforcing filesystem for AI agents. Point it at a real project directory and it serves a filtered mirror — same paths, same sizes — deciding per read which face of each file to show.
翻译准备中
Low-latency bot detection for Apache 2.4 with proof-of-work challenges, shared-memory reputation, crawler policy, and built-in observability.
翻译准备中
Short-lived SSH certificates from your identity provider, for ssh, sudo, and the console.
翻译准备中
mcp-skills-vault installs MCP servers safely. mcp-trace shows what they're actually doing. Offline-first. No telemetry.
翻译准备中
Self-hosted MCP gateway: AI agents get audited, SSO-gated, read-only database access without ever holding a DB credential.
翻译准备中
SWARM: open-source multi-agent AI safety framework. Measure toxicity, governance gaps, and emergent risks with soft probabilistic labels.
翻译准备中
Belay is a local-first security layer at the tool-call boundary of AI coding agents. Deterministic, sub-100ms, fail-closed. Detect, block, and get notified — no LLM in the decision path.
翻译准备中
Hub + agent + 设备集成：实时数据包测量、基于进程的 L7/DNS 可视化、TimescaleDB + NATS 扩展架构、RBAC/SSO 以及符合 5651 标准的签名日志。开源、MIT 协议，可部署在您的自有基础设施中。
AI 翻译
A deny-by-default contract layer for AI agent tool calls - strict argument validation, ghost-argument stripping and self-healing retries, in-process and Pydantic-only
翻译准备中
Govern connected AI clients, models, and tools on your infrastructure. Centralize access policies and audit, then build custom capabilities on the SystemPrompt runtime.
翻译准备中
Free, open-source CLI and MCP server that keeps API keys in your OS keychain and serves them to Cursor, Claude Code, and Kiro. No cloud, no account, no .env file.
翻译准备中
AI security from risk map to reference architecture: the full CoSAI taxonomy, the MITRE mitigations that support its controls, and target-state architectures for every class of AI application.
翻译准备中
A rubber band around Claude's claws. Blocks rm -rf and other destructive commands before they run, so bypassPermissions mode is actually safe.
翻译准备中
Collective discovery for open cryptographic challenges. Contribute GPU time to a public elliptic-curve search, earn credit for verified work, share the prize when the answer is found.
翻译准备中
Choose the assets. Run applicable upstream security checks. Read one report organized by asset and priority.
翻译准备中
Test your vibe-coded apps, hunt down hallucinated packages, logic bugs, and secret leaks, and fix them in seconds. Works inside Cursor, Claude Code, GitHub Copilot, and Windsurf.
翻译准备中
Small Print is a nightly record of the tool descriptions, schemas and instructions that MCP servers, agent skills and plugins give your agent: every version hashed, every change diffed and graded by a
翻译准备中
Sane WordPress defaults with actionable Site Health reporting for security, privacy, performance, and core updates — including same-line security patches.
翻译准备中
The archive feature Graylog Open is missing — self-hosted, streaming, with independent compliance audit.
翻译准备中
AI Ops for Bring Your Own Agent (BYOA) teams. Audit coworker harnesses with doorman dashboard, mine prompt history for capability needs, and block rogue tools at the gate.
翻译准备中
Install Know Your Agent with npx in minutes. Offline demo, MCP gate, local free console, or enterprise hosted. No private protocol.
翻译准备中
Daily Internet.nl standards measurements of a real fleet, made by the unmodified internetnl CLI against a self-hosted netnl facade.
翻译准备中
Your agent knows a lot about you. Sanctuary keeps that information private. A firewall for your AI agent that runs on your own Mac, enforcing what it can reach at the operating-system level with keys
翻译准备中
Self-hosted, metadata-only visibility and guardrails for the AI coding tools your engineers use. Never prompt text, never source code.
翻译准备中
一次验证，随处访问。通过加密令牌和跨链消息（ICM）在 Avalanche® 区块链上获取 KYC、KYB 和 KYA 合规凭证。非托管，仅软件，无 PII 存储。
AI 翻译
Local-first pentest agent: Go daemon + React dashboard + Codex/Claude Code/Pi runtimes, scoped projects, Blackboard, sandbox runners
翻译准备中
Orca Security provides agentless, workload-deep, context-aware cloud infrastructure security and compliance through our comprehensive cloud security solution all in a single platform.
翻译准备中
Verify Pakistani online stores and sellers before you pay, and file structured fraud disputes when something goes wrong. A free public database of reported scams, blacklisted brands, and dispute outco
翻译准备中
Walletbeat is an Ethereum wallet rating site. It aims to provide a trustworthy, up-to-date source of information about the state of the Ethereum wallet ecosystem
翻译准备中
Agents generate actions. rv authorizes them before they run. Hook-grade allow/deny for Grok, Pi, OpenCode, Claude, OpenClaw, Hermes, Codex, and Cursor.
翻译准备中
Open-source security audit for your AI agents: the skills they run, exposed secrets, risky MCP config, and unsafe updates. Runs on your machine.
翻译准备中
BitGraph allocates an unused position before it receives a file's SHA-256 fingerprint, then binds the fingerprint to that position and consumes it. The proof is a file you keep. It verifies offline.
翻译准备中
Open-source cryptographic receipts, identity, and audit trails for AI agent sessions. Like TLS certificates, but for agents.
翻译准备中
File transfer, datarooms and deposit boxes. End-to-end encrypted. Hosted in Europe.
翻译准备中
ASCII-only by default, no escape parser, a paste warning and reveal modes, memory-safe. An opt-in TUI mode runs ssh, vim and htop, still filtering every character. Copy commands in and text out withou
翻译准备中
Master prompts that turn any AI coding agent into a swarm of specialist auditors — evidence-bound, adversarially verified, filed as GitHub issues in German or English.
翻译准备中
One compiled binary puts guardrails under the agent you already run: a destructive tool call is denied before it executes, every milestone needs a contract a human approved, and every execution leaves
翻译准备中
Free, open-source CLI for scanning, SBOM generation, vulnerability auditing, and AI-agent-driven dependency analysis.
翻译准备中
Verified agent actions: authorization policy, signed receipts, and audit evidence for AI agent tool calls. One command to protect any MCP server.
翻译准备中
Local-first session transfer on macOS: Chromium browsers, ChatGPT Codex, experimental Cursor import, encrypted Grok Bot export, and optional Browserless Cloud.
翻译准备中
Glaurung is a pre-1.0, AI-native reverse-engineering toolkit with a fast Rust core, a Python API, optional agent workflows, and provenance-aware SQLite project files.
翻译准备中
Turn an AI eval result into one portable, offline-verifiable receipt and chain it: eval receipt, decision receipt, outcome receipt. Ed25519 + RFC 6962 Merkle, no server, no network.
翻译准备中
Harness, manifest, backend. Manager token stays out of the child environment. Bitwarden SM, 1Password, pass, sops. macOS and Linux.
翻译准备中
Audit the Agent Skills installed on this machine for security, trustworthiness, spec conformance, context cost, and trigger quality, then produce a graded…
翻译准备中
An agent escape can be built from actions your guard already approved. plumbline scores the sequence, not the step.
翻译准备中
Enforce what an agent can do, prove what it did, and watch for what slipped through. Open, composable, verifiable.
翻译准备中
Block prompt injection before your AI agent reads it. Open source, local first, MIT licensed.
翻译准备中
Durable, per-user memory for AI agents that resists injection and confabulation. Structural quarantine of third-party claims, grounded-or-silent abstention, supersession without erasure. One SQLite fi
翻译准备中
Semantic SBOM & CBOM diff in Rust. Compare CycloneDX/SPDX, score compliance, and enrich with OSV/KEV data. Fast, CI-ready.
翻译准备中
The security agent for vibe-coded apps. Kelp probes your backend the way an attacker would and hands you the fix — ready to paste back into your AI tool.
翻译准备中
Aegis ShellGuard 是用 Rust 编写的 AI 编码代理的 shell 防护栏。rm -rf、git reset --hard 和 DROP TABLE 等命令等待您的批准；安全命令在 2 毫秒内通过。
AI 翻译
Security coaching and compliance training in Slack and Microsoft Teams, plus open-source skills for AI coding agents.
翻译准备中
See every device on your home network - including the Zigbee, Z-Wave, Matter and Bluetooth LE ones an IP scan cannot find. Self-hosted, MIT, with two-way Home Assistant integration.
翻译准备中
An Arch-based Linux distribution that runs a local LLM as a system service: AI-native shell, wlroots Wayland desktop, security monitor, kernel module. No cloud, no API keys.
翻译准备中
Free and open source. An AI reads the security alerts your tools raise, tells you which ones matter, and asks before it does anything. Runs on your own computer.
翻译准备中
ProofLedger anchors SHA-256 hashes of your files to Polygon and Bitcoin, by API or the free web tool, establishing a neutral record of what existed and when. The file never leaves your machine and any
翻译准备中
Don't trust one AI. Verify with five. Multi-model research, claim verification, video authenticity, and governance — with audit trails.
翻译准备中
Search usernames across a wide range of platforms, check emails and passwords against breach data, and investigate domains, DNS, and IP addresses — accurate, fast, and private.
翻译准备中
在几分钟内将 HailBytes 安全工具部署到 AWS 或 Azure。提供一键部署模板，适用于 HailBytes 安全意识培训平台和 HailBytes 攻击面管理平台。
AI 翻译
LightNVR for one home or an entire campus: managed cloud NVR hosting, professional on-premises deployments, and MSP delivery across both. Bring your existing RTSP and ONVIF cameras.
翻译准备中
Scan any public GitHub repo for security vulnerabilities, exposed secrets, and code quality issues.
翻译准备中
VEYRNOX removes the #1 crypto attack surface by design. 8-digit PIN, Shamir-sharded backup on Safety Plus. iOS and Android.
翻译准备中
A free, public radar for newly-issued TLS certificates on domains that impersonate Indian banks, payment apps and government portals.
翻译准备中
Winsock Packet Editor (WPE x64) 是一款开源的 Winsock 封包拦截与编辑软件、可自适应 32 / 64 位目标程序、支持修改并转发任意终端程序的网络封包
Deep launch-readiness audit that catches what AI builders ship and fake. Runs in your own agent. A watchdog re-verifies every pass.
翻译准备中
Get verified on TETA+PI. Businesses, journalists, and artists verified via registry + C2PA + Bitcoin become discoverable by AI agents through the MCP protocol.
翻译准备中
Create a Technocore did:key identity from your Solana wallet, publish it where anyone can verify it, and keep the receipts. Open source, no account, no server.
翻译准备中
OpenGuardrails — next-generation AI runtime security. Secure every action your AI agent takes: the tool call, the system it reaches, the credential about to leave. From $10/month as SaaS, or privately
翻译准备中
Ledgato independently authorizes consequential agent actions at protected boundaries, then verifies and records what happened.
翻译准备中
OAuth, SAML SSO, social login, and FGA in one self-hosted NuGet package. See the dashboard, run the Todo sample, and ship in minutes.
翻译准备中
Your guided post-quantum cryptography transformation journey. Learn PQC fundamentals, assess your quantum risk, and migrate your cryptography infrastructure in full compliance with NIST, ANSSI, BSI, a
翻译准备中
用 Firezone 替代 VPN，这是一款基于 WireGuard® 的开源零信任访问平台。将用户连接到任何位置、任何资源。立即免费试用。
AI 翻译
Bitwarden 是面向个人、团队和企业的可信开源密码管理器。安全地存储、共享并管理密码、通行密钥和机密。免费即可开始。
AI 翻译
Free IP lookup tool. Instantly get information on any IP address: geolocation, ISP, VPN detection, and more. No account required.
翻译准备中
The core objective of Homebase is to revolutionize the concept of digital identity by creating a decentralized, lifelong, safe, and secure online home for every
翻译准备中
SafeDep helps teams detect malicious packages, protect AI agents, and govern open source risk across developer machines, CI/CD pipelines, and production workflows.
翻译准备中
Generate a random passphrase from the EFF wordlist or common English words. Self-contained, works offline, never touches the internet.
翻译准备中
认识 ICPanda DAO、PANDA、Anda、TokenList 和 dMsg：Chrome 扩展，用于保管机密、共享加密文件以及跨应用签名。
AI 翻译
Decide what your team can share with connected AI tools. Free and open source for macOS, Windows and Linux.
翻译准备中
Code-enforced capabilities for local agents: wallets, servers, payments — inside walls the model can't talk its way around.
翻译准备中
Streams Salesforce Event Monitoring into Grafana Loki — Pub/Sub API, SOQL and EventLogFile ingestion, cardinality-disciplined by default.
翻译准备中
An AI agent trading a Binance account gets no credential, only a mandate. Every executed order is reconciled against what was actually authorised.
翻译准备中
Enterprise multi-agent fraud investigation platform with deterministic safety guardrails and evidence-grounded reasoning.
翻译准备中
A cookie consent banner you can install in ten minutes. It asks your visitors before any tracker starts. 34 languages, Google Consent Mode v2, a cookie scanner and a consent log. Open source, MIT.
翻译准备中
A signed, tamper-evident record of what your agent actually did, written to your machine first.
翻译准备中
Firma y verifica documentos PDF gratis, 100% en tu navegador: tu certificado .p12 nunca sale de tu equipo. Sin registro, open source, cumple LOPDP.
翻译准备中
Native VPN clients for Windows, Android, and Linux with WireGuard speed, kill switch controls, and DNS leak protection.
翻译准备中
Iedereen bouwt de koperskant van de AI-agent-economie (identiteit, spend-limits, betaalrails). Tokenizen bouwt de verkoperskant: een ondertekend, feitelijk bewijs dat het geleverde overeenkomt met wat
翻译准备中
通过接收 2.4 GHz WiFi 和 Bluetooth 上的 Remote ID 广播，被动检测附近的无人机，并实时推送至您的 Android 手机。
AI 翻译
DFOS is an open protocol for identities, signed records, and delegated permissions that any compatible application can verify for itself.
翻译准备中
Independent software by Alfon. Content blockers that decide on your device what reaches your screen. No accounts, no telemetry.
翻译准备中
Identity, badges, and policy enforcement for the A2A protocol — in two lines of code. Open source.
翻译准备中
Mint per-user, revocable Claude/agent skills from a Cloudflare Worker — the API secret bakes itself into the skill at download time. HMAC-derived keys, never stored; one-integer revocation; no app-lev
翻译准备中
Protect native OpenAI, Anthropic, and Google Gemini traffic with PII controls, audit trails, usage metering, and budget enforcement.
翻译准备中
Aletheore is more than a scanner. Free deterministic CLI audits (secrets, vulnerabilities, licenses, dead code, git hotspots) plus a hosted GitHub App: automated PR reviews on Aletheore Flash ($8/mo),
翻译准备中
Phantom helps keep provider values out of the managed dotenv and MCP path for Claude Code, Cursor, Windsurf, and Codex, with exact-route HTTP credential injection.
翻译准备中
agentdesktop is the open-source governance layer for AI agents on desktops: discover every agent harness, MCP server, and skill across your fleet, replace API keys on disk with short-lived gateway ide
翻译准备中
Issue and verify KH-SQR signed QR codes on this device, offline. A sandbox: its keys protect nothing.
翻译准备中
Knowledge and information sharing and discovery agent. Cast spells and skills, interface with the world. Understanding as key—storage, identity, confidential compute, ZK credential composition. Share
翻译准备中
A fast, single-file email viewer. Drop an .eml to read the message, headers and attachments — with SPF, DKIM and DMARC authentication analysis. Nothing uploaded.
翻译准备中
The six permission modes including the new auto mode, how allow/deny rules actually match, what the sandbox bounds, which hooks fire when, what bypassPermissions still enforces, and where the native m
翻译准备中
做出来了，现在该展示了。
在项目文件夹中执行一条命令即可。只要由AI辅助制作，就不必具备AI功能。
/nomorevibe查看收录流程