GitHub Release Tracker
All JS React Ruby Go Postgres Frontend Node

ai-security

Past 30d, sorted by best first
12 results Markdown version
08/20 8
luckyPipewrench/Pipelock v3.4.0
All-in-one security harness for AI agents offering egress control, DLP, SSRF protection, prompt-injection scanning, and workspace integrity monitoring.
Go 815☆ 200d old #golang #go #ai-agents #ai-security #dlp
08/18 8
stacklok/ToolHive v0.44.0
Simplifies secure deployment and management of Model Context Protocol servers in isolated containers.
Go 2036☆ 530d old #golang #ai #go #mcp #aicodeassistant
08/26 7
arcjet/Arcjet v1.11.0
SDK for implementing security features like bot detection, rate limiting, and email validation in JavaScript applications.
TypeScript 681☆ 1001d old #javascript #nodejs #node #typescript #react
08/20 7
adithyan-ak/AgentHound 1.1.0
Offensive security framework for AI agent infrastructure that runs recon, credential and model inventory, exploitation, and builds a Neo4j graph to analyze attack paths.
Go 274☆ 141d old #golang #go #agentic-ai #ai-agents #a2a
08/18 7
peg/Rampart v1.8.0
Security layer enforcing YAML policies for commands, file access, and network requests from AI coding agents.
08/01 7
7anX/AgentScan v1.1.0
HTTP-based scanner that discovers exposed MCP servers, A2A Agent Cards, and open LLM APIs using one command-line workflow.
Go 99☆ 47d old #golang #llm #go #agent #a2a
08/24 6
openai/Codex Security npm-v0.1.19
A CLI and TypeScript SDK for finding, validating, and fixing security vulnerabilities in your code.
08/24 6
praetorian-inc/Julius v1.4.12
LLM service fingerprinting tool that identifies which AI server software runs on network endpoints in seconds.
08/10 6
KeyValueSoftwareSystems/OPFOR v0.10.2
Adversary emulation tool that red-teams AI agents and MCP servers end to end across OWASP-style test suites with logged, judge-evaluated results.
08/05 6
praetorian-inc/Augustus v0.14.15
Go-based LLM vulnerability scanner testing models for prompt injection, jailbreaks, encoding exploits, and data extraction.
Go 280☆ 192d old #golang #go #ai-security #capability
08/23 3
antropos17/AEGIS aegis-v0.13.0-alpha
Local-first EDR-style monitor tracking AI agent processes, file and network activity with per-agent risk scoring.
08/25 2
hivementality-ai/Hivemind 2026.08.07-rc
Self-hosted multi-agent AI team platform with persistent workspaces, team chat, sandboxed tool execution, and integrated messaging channels.