Search
llm-cage
Pasindu
Cage: run local-LLM components in a network-isolated OS process, hardware access intact, with a friction-free call interface back to the rest of your app. Placeholder release reserving the name while the project is designed.
...more@newgenesis/vision
newgenesis
Professional bot and AI detection library with behavioral analysis, fingerprinting, and adaptive challenges
@approov/react-native-approov
ivo.liondov
Approov Mobile App Protection for ReactNative
ai-agent-shield
esoteric1entity
Defensive overlay for AI agents — 8-layer architecture with harness-agnostic adapters; ships 6 of 8 layers (1 skill_vetting, 2 sanitize, 3 structured_output, 4 bash_guard+write_guard, 6 audit, 7 config) plus adapters for Claude Code (PreToolUse) and OpenClaw (before_tool_call)
...moreai-metadata-cleaner
kukyasin
A command-line tool to remove EXIF data and metadata from AI-generated images and videos
mcpjail
The flight recorder & firewall for MCP tool calls.
@trustsig/client
trustsig-ou
Vanilla JavaScript client for TrustSig bot protection. Handles dynamic script injection and token retrieval.
@oneminutelogs/next
oneminutestack
A Lightweight npm package for working with one minute logs. Set up your logging pipeline within one minute.
simplify-captcha
krishna.paul
A modern React CAPTCHA component library with advanced human verification
authograph
goblinlordx
Authorization solution for use with GraphQL
securedact-mcp
Local-first privacy MCP server for sensitive AI workflows
aquaman-plugin
tech4242
Credential isolation plugin for OpenClaw
archmind
sid7vish
Catches conflicting AI-generated auth logic before it ships.
Agent Core
pushkqr
Dynamic AI Agent Framework - Create, orchestrate, and manage AI agents with YAML configs, MCP tool integration, and linear workflow execution using AutoGen and Google Gemini.
...morenext-safe
trezy
<div align="center"> <h1><code>next-safe</code></h1> </div>
ts-rate-limiter
chrisbreuer
High-performance, flexible rate limiting for TypeScript and Bun
crucible-ai
Red-teaming framework for AI applications — LLMs, agents, RAG, MCP servers
@unkn0wnartist/h1-poc-test
unkn0wnartist
PoC package for demonstrating supply-chain vulnerability in GitHub Actions via Dependabot
io.github.nickjlucker/greynoise
MCP server for GreyNoise API - Check if IPs are internet background noise or targeted attacks
envaultx
What your LLM sees, stays safe.