
pipelock
Open-source AI agent firewall that scans HTTP, MCP, A2A, and WebSocket traffic for exfiltration, SSRF, and prompt injection, emitting verifiable…

Open-source AI agent firewall that scans HTTP, MCP, A2A, and WebSocket traffic for exfiltration, SSRF, and prompt injection, emitting verifiable…

Krawl is a customizable, lightweight, cloud-native web deception server and anti-crawler that creates fake web applications with low-hanging…

ATHF is a framework for agentic threat hunting - building systems that can remember, learn, and act with increasing autonomy.

Self-hosted runtime control plane for AI agents. Observe or HITL approve or Block rogue tool calls before it executes: secret leaks, prompt…

a guard that blocks catastrophic agent actions

Policy engine and EDR for AI agent fleets and developer workstations. Monitors tool calls, file access, network flows, and process execution with…

A modular, skill-based autonomous Security Operations Center (SOC) agent that monitors OpenSearch/Elasticsearch data, builds RAG-based behavioral…

macOS persistence mechanism scanner with code signature verification and timeline tracking.

Read-only AI agent that queries your cloud, code, and runtime infrastructure to surface misconfigurations, leaked secrets, and privilege escalation…

Execution-Layer Security (ELS) for AI agents — policy-enforced shell with audit.

eBPF-powered Linux observability with AI incident detection. AGPL-3.0 licensed.

The Execution Security Layer for the Agentic Era. Providing deterministic "Sudo" governance and audit logs for autonomous AI agents.

Agentic AI memory with Ebbinghaus forgetting curve decay. +16pp better recall than Mem0 on LoCoMo.

Secure agents in seconds with permissions enforced at runtime.

AI 驱动的 SOC 仿真平台

AI runtime inventory: discover shadow AI, trace LLM calls

Kernel-level eBPF sandbox for securing LLM agent tool calls made through the Model Context Protocol (MCP)

Deploy self-hosted AI coding agents (OpenClaw, Claude Code, Codex) into your AWS account with CloudFormation, IAM profiles, and sandbox isolation for…