* [Pipelock v3.6.0](https://github.com/luckyPipewrench/pipelock) – All-in-one security harness for AI agents offering egress control, DLP, SSRF protection, prompt-injection scanning, and workspace integrity monitoring.

* [ToolHive v0.50.0](https://github.com/stacklok/toolhive) – Simplifies secure deployment and management of Model Context Protocol servers in isolated containers.

* [Codex Security npm-v0.2.0](https://github.com/openai/codex-security) – A CLI and TypeScript SDK for finding, validating, and fixing security vulnerabilities in your code.

* [Arcjet v1.14.0](https://github.com/arcjet/arcjet-js) – SDK for implementing security features like bot detection, rate limiting, and email validation in JavaScript applications.

* [Julius v1.5.0](https://github.com/praetorian-inc/julius) – LLM service fingerprinting tool that identifies which AI server software runs on network endpoints in seconds.

* [Guardana Control v0.11.0](https://github.com/guardana/control) – Guardana Control is a local gateway that intercepts and enforces agent MCP tool calls using signed policies, approvals, and append-only evidence trails.

* [Antares v0.6.0](https://github.com/enowdev/antares) – Self-hosted AI pentest agent and assistant providing an authorized security testing workspace with files, shell, real browser control, memory, and retrieval-augmented reports.

* [Rampart v1.9.4](https://github.com/peg/rampart) – Security layer enforcing YAML policies for commands, file access, and network requests from AI coding agents.

* [Augustus v0.14.34](https://github.com/praetorian-inc/augustus) – Go-based LLM vulnerability scanner testing models for prompt injection, jailbreaks, encoding exploits, and data extraction.

* [AEGIS aegis-v0.19.2-beta](https://github.com/antropos17/Aegis) – Local-first EDR-style monitor tracking AI agent processes, file and network activity with per-agent risk scoring.