Search
redact-env
franky47
Redact values of critical environment variables in a string
@fractalcode/fractal-claw
haltandcatchwater
Fractal Code — Constitutional programming framework for safe AI agent execution
superred-target-chatbot
Chatbot target for the superred red-teaming framework: wraps any LLM via litellm
@trustlists/mcp
trustlists
trustlists MCP server: find public vendor trust centers, browse listed frameworks, and map project dependencies.
gitprint
gitprint
Code Provenance Intelligence — verify who really wrote your code. Stylometric author fingerprinting via git mining + pretrained code embeddings.
...moreio.github.Agnuxo1/enigmagent-mcp
Agnuxo1
Local AES-256-GCM vault for AI agents. Secrets stay local, LLMs never see real API keys.
@klars/guardrail
klars-ai
A firewall for AI agent tool calls. Wrap any MCP server in one command and block dangerous actions before they execute.
agent-loop-runtime
Mind Loops Lab
Portable, local-first self-check runtime for humans, agents, and agentic apps.
@sapience-ai-corporation/openclaw-middleware-suite
syed_ali
Sapience AI's 6-in-1 middleware suite for OpenClaw. These middlewares sit between your agent and and the systems it can affect — intercepting every turn and every tool call, enforcing Human-in-the-Loop gates, redacting PII, blocking prompt injection, rout
...morecreate-gef
king241
Générateur interactif de projets respectant le Guardian Engineering Framework
cc-sandboxer
ngocquang
Run claude --dangerously-skip-permissions safely inside a Docker sandbox
Claude Skills Governance Risk And Compliance
Sushegaad
Claude Skills for Governance, Risk, and Compliance frameworks. Expert-level compliance guidance for ISO 27001, SOC 2, FedRAMP, GDPR, and HIPAA. Skills scored 99% ± 4% in Evals.
...morets-prime-gen
chrisbreuer
A prime number library.
agentshield-guard
Official Python SDK for AgentShield — prompt injection detection for LLM applications.
react-export-excel
rdcalle
A tool to export dataset from react to excel format.
GatewayStack
davidcrowe
User-scoped AI governance and control plane for agentic systems. Modular identity, policy, rate limits, routing, and audit layers for LLM and tool calls.
...morenode-encryption
bjarneo
This package will simplify the process of encrypting and decrypting data for your application providing robust AES-256-GCM encryption and decryption utilities for protecting sensitive data.
...morechaosify-kubernetes
nahaap
Deterministic CLI for Kubernetes Continuous Control Verification
gitleakguard
podut
One-command Git secret protection — blocks commits with exposed credentials
wallettriage-mcp
wallettriage-mcp
WalletTriage MCP server — real-time wallet risk check for AI agents, paid per query via x402 (USDC on Base).