Secure-Vector/securevector-ai-threat-monitorSecurity & Observability for AI Agents — audit every tool call, enforce allow/block policies, catch prompt injection and data leaks. Local-first; works with Claude Code, Codex, Copilot CLI, OpenClaw, LangChain, and all major LLM APIs.
Python · JavaScript★ 14Sep 9, 2026
adamsjack711-ux/pkgxrayPre-install security for AI agents, npm packages, and MCP servers. Zero-dep local static analysis; normal scans never execute package code.
JavaScript★ 11↓ 486/moSep 10, 2026
bookedsolidtech/reaZero-trust governance layer for Claude Code. Policy-enforced MCP gateway with autonomy controls, middleware chain, audit log, HALT kill-switch, and prompt-injection defense.
TypeScript · Shell★ 0↓ 642/moSep 14, 2026
Packagist73Goodhealth index
fissible/verdictA Laravel security boundary for AI-triggered application actions. It bounds what an agent may do — authority, duplication, rate, approval — not what it was trying to do.
PHP★ 2↓ 802/moOct 21, 2026
sunglasses-dev/sunglassesOpen source input firewall for AI agents, beta. A local scanner checks text, code, PDFs, images, QR codes, audio and video with 1,583 patterns across 117 categories and reports findings and incomplete scans. A Claude Code hook blocks secret material in tool calls and the paths and hosts your policy lists before tools run.
Python★ 10↓ 1,856/moOct 19, 2026
PyPI · npm73Goodhealth index
vaquarkhan/MCP-BastionMCP-Bastion: The Zero-Infrastructure Runtime Middleware ,Enterprise-Grade Security Middleware for the Model Context Protocol (MCP)
Python★ 5↓ 3,959/moSep 18, 2026
Python★ 1↓ 2,471/moSep 15, 2026
HeadyZhang/agent-auditStatic security scanner for LLM agents — prompt injection, MCP config auditing, taint analysis. 51 rules mapped to OWASP Agentic Top 10 (2026). Works with LangChain, CrewAI, AutoGen.
Python★ 230↓ 3,609/moSep 18, 2026
goklab/guardvibeSecurity infrastructure your AI can't be — deterministic, daily CVE intel past your model's training cutoff, whole-repo-aware, author-independent, and shift-left: secure_prompt secures the prompt before code generation. The security MCP for vibe coding: 450 rules, 39 tools, CLI + doctor for Next.js, Supabase, Clerk, Stripe, Prisma, Hono & MCP.
TypeScript★ 5↓ 1,719/moSep 10, 2026
npm · crates.io71Goodhealth index
Rust · JavaScript★ 0↓ 11K/moSep 9, 2026
vishnu-77/seccheckerStatic security scanner for AI agents, MCP tools, and LLM applications. Detects OWASP LLM Top 10 risks, unsafe tool use, prompt injection paths, secrets, and AI infrastructure misconfigurations. Zero runtime dependencies.
Python★ 2Sep 12, 2026
tiagosilva07/zyrax-guardAudit your AI agent configs before you run them — prompt injection, rogue MCP servers, credential-exfil. Plus dependency vetting.
Go★ 2Oct 20, 2026
directive-run/directiveConstraint-driven runtime for TypeScript. Declare requirements, let the runtime resolve them.
TypeScript★ 4↓ 20K/moSep 8, 2026
hawonb711-tech/nexusLocal-first trust layer for AI coding agents: structural prompt-injection and action guards, secret scanning, semantic memory, code review, and 17 MCP tools. No model API required.
TypeScript★ 0↓ 154/moSep 21, 2026
TypeScript★ 0↓ 3,388/moSep 11, 2026
npm · PyPI65Goodhealth index
stylusnexus/agent-armorOpen-source agent security framework. Detects and defends against AI Agent Traps — content injection, embedded jailbreaks, RAG poisoning, data exfiltration, and more. Based on the DeepMind Agent Traps taxonomy.
TypeScript · Python★ 4↓ 1,659/moSep 18, 2026
subodhkc/ai-appsecEvidence-backed AppSec for AI applications and agents. Powered by HAIEC.
TypeScript★ 4↓ 19.4K/moSep 20, 2026
PyPI63Moderatehealth index
batrapulkit/squidbrakeBrakes for your AI agents: every tool call is checked against your rules, held for human approval when risky, and recorded in a tamper-evident audit trail. Works with Claude Code and any MCP app.
Python · HTML★ 14↓ 2,655/moOct 9, 2026
npm63Moderatehealth index
calllint/calllintPre-flight risk linting for MCP and agent tools — check the blast radius before your agent runs them.
TypeScript · HTML★ 2↓ 859/moSep 15, 2026
crates.io63Moderatehealth index
kahramanemir/VallumSecurity boundary CLI proxy between AI coding agents and your shell — redacts secrets, neutralizes prompt injection, wraps untrusted terminal output, and audits every command. Single Rust binary.
Rust★ 5↓ 159/moSep 6, 2026
PyPI63Moderatehealth index
zrk222/code-factoryEvidence-first audits for AI-generated code: prove tests can fail, catch security and release gaps, and ship reviewable receipts across VS Code, JetBrains, CI, MCP, and App Store workflows.
Python · TypeScript★ 6↓ 4,653/moSep 10, 2026
npm62Moderatehealth index
Synapsor/Synapsor-RunnerLet AI agents query and update Postgres/MySQL without raw SQL, unrestricted schema access, or database credentials in the model; writes stay reviewed.
TypeScript · JavaScript★ 3↓ 669/moOct 20, 2026
PyPI62Moderatehealth index
Python★ 13↓ 522/moSep 11, 2026
famclaw/honeybadgerSecurity scanner for AI agent skills and MCP servers. Detects secrets, CVEs, supply chain attacks, and prompt injection in SKILL.md files before they're installed. Pre-install gate for Claude Code, OpenClaw, PicoClaw, NanoBot, FamClaw, and CI/CD pipelines. Single Go binary, MIT licensed.
Go★ 3Sep 9, 2026
npm62Moderatehealth index
TypeScript★ 100↓ 223K/moSep 14, 2026
npm62Moderatehealth index
subodhkc/llmverify-npmAI model health monitor for LLM apps – runtime checks for drift, hallucination risk, latency, and JSON/format quality on any OpenAI, Anthropic, or local client.
TypeScript · JavaScript★ 18↓ 23.2K/moSep 20, 2026
PyPI62Moderatehealth index
Python★ 9↓ 3,182/moSep 15, 2026
npm · PyPI60Moderatehealth index
CogNEXUSlabs/cognexus-toolsCogNEXUS Labs builds the infrastructure that makes autonomous AI accountable to the enterprise. Our product, Artzain is the model-agnostic Agent Control Plane for autonomous systems. Here's the SDK
Python · TypeScript★ 1↓ 2,494/moSep 18, 2026
PyPI60Moderatehealth index
Python★ 0Sep 12, 2026
PyPI59Moderatehealth index
gawk-dev/mcpgawkOne gateway in front of every MCP server your agents can reach. A server that changes after you approved it is caught, the call is blocked before it runs, and nothing leaves your machine.
Python · HTML★ 0↓ 3,703/moSep 26, 2026