Security middleware
-
abtars
Agent harness connecting messaging platforms, with persistent memory, skills, scheduled tasks, self-healing supervision, and distributed multi-agent collaboration
-
ACYBER-Wayback-Machine-Downloader
📥 Download historical files from the Internet Archive Wayback Machine with our Python tool, supporting proxies, retries, and customizable settings.
-
bonklm
Enforce security guardrails for large language models in Node.js applications to manage risks and maintain safe usage across platforms and providers.
-
bv-mcp
Open-source DNS & email security scanner. One MCP endpoint, 57 checks, zero install. Cloudflare Workers.
-
claude-whatsapp
Connect your WhatsApp number to Claude Code to automate messages and manage conversations.
-
clauderabbit
ClaudeRabbit is a free, open-source security product protecting the open-source community from malware. We clone any public GitHub repo into an isolated sandbox, run it, and return one honest safety score.
-
cli
The Vibgrate CLI scans your codebase for upgrade drift — the gap between the dependency versions you run and the versions you should run. It produces a deterministic Upgrade Drift Score (0–100), a full context-aware dependency graph, and actionable findings enriched with AI-assisted upgrade guidance to help you maintain a healthy, secure codebase.
-
comis
Open-source security-first runtime for AI agents that learn and act across sessions.
-
conarium
Conarium AI — self-hosted governance layer between AI assistants and your real data. Deterministic PII masking, allow/deny policy, hash-chained audit, an Ed25519-signed receipt per access verifiable offline, coverage reconciliation against the DB's own query counters to surface gateway bypasses, and conformance vectors. MCP-native. MIT.
-
emilia-protocol
Consequence firewall for machine actions. EMILIA Gate verifies exact authority before money, code, permissions, infrastructure, or regulated state changes; the open protocol makes the evidence independently verifiable.
-
Gateflow
Physical access control systems today operate in isolation from marketing and business intelligence. Real estate developers, gated compounds.
-
github-command-center
Manage GitHub pull requests, issues, notifications, and local git tasks in one self-hosted app built with Go and React.
-
github-well-architected
Apply design thinking to build and ship your software securely and at scale with GitHub
Security TypeScript -
GrantTrace
Scenario-bound GitHub App REST permission contracts.
-
hackmyagent
Metasploit for AI agents: scan, attack, and fix AI agents and MCP servers. Open source security toolkit.
-
keel
A local-first, governed agent harness: high autonomy inside structurally-enforced boundaries (Autopilot, not YOLO).
-
libero
The open-source AI teammate for Slack. Self-hosted, credential-isolated, every tool call audited.
-
mcp-security-lab
Evidence-first security checks for Model Context Protocol (MCP) servers — a Claude for OSS Incubator project.
-
MCPScan
Scan and identify security issues in MCP servers to help strengthen defenses against potential attacks on AI agent connections.
-
npm-safe
本地优先的 npm 包供应链安全扫描引擎：静态与 LLM 分析、CLI、桌面 GUI、CI 集成。
-
pentest-mcp-server
Integrate penetration testing tools and payloads into your workflow through the Model Context Protocol using STDIO or HTTP.
-
project-R-score
A comprehensive development ecosystem featuring enterprise-grade tools, automation frameworks, and performance optimization utilities built with Bun and TypeScript.
-
ReinPlaner
Multi-Tenant SaaS für Reinigungsdienstleister mit RLS-isolierter Postgres, Drizzle, tRPC und Next.js 15 — selbstgehostet.
Security TypeScript -
rever-browser
AI agent browser for web reverse engineering
-
sdk-ts
Official JavaScript and TypeScript SDK for the platform, offering a modern, type-safe client with flexible configuration and seamless API integration.
-
sensitive-canary
Claude Code hooks that guard secrets and PII before they reach the Anthropic API
-
Sentris
No-Code Security Automation. Turn messy scripts into reliable, observable systems with drag & drop Visual Workflow Builder with agent driven collaberation.
-
SLMarena
SLMArena is a self-hosted benchmarking & red-teaming platform for local SLMs. Measure TTFT, tok/s, & latency while an automated frontier LLM judge evaluates accuracy, grammar, & prompt injection resilience in real time.
-
sober-coding
Analyze AI-generated code to find technical debt and get actionable fixes.
-
ssh-mcp-pro
TypeScript MCP server for controlled SSH operations, remote host workflows, command execution guardrails, and infrastructure automation.
-
svelte-vitals
A static code-health checker for SvelteKit — SEO, Performance, Correctness, Security, and Architecture, from source. Not a runtime Web Vitals reporter.
-
targate
AI-assisted pre-install security gate for npm packages — analyze, decide, and gate a dependency before it runs.
-
TenancyJS
Fail-closed, TypeScript-first multi-tenancy for Node.js - one tenant-isolation contract across Express, Next.js, AdonisJS & NestJS with Prisma, Knex, Lucid, TypeORM, Sequelize & Mongoose.
-
themoltnet
Accountable authority for autonomous agents
-
thesmos-governance
AI governance CLI, GitHub Action, VS Code extension & MCP server — 1,075 rules for Claude, Cursor, Copilot, Gemini, Codex.
-
triagekit
Backend-free repo triage in one self-contained HTML file — GitHub Dependabot alerts, code scanning, PRs & issues, scored and tiered. No server, no CDN; your token stays in the browser.
-
trustabl-action
GitHub Action that runs trustabl — static reliability/safety analyzer for AI agent SDKs (Claude, OpenAI, Google ADK, MCP). Gates CI on risk + severity.
-
upstream-radar
Scan and monitor DeepSeek Harness plugins: find exact dependency and compatibility problems, then keep a fixable report for authors and agents.
-
VibeCoder
Unattended GitHub issue-to-PR worker running Claude Code inside a strict containment boundary
-
Awesome-AI-Tools