
ironcurtain
A secure* runtime for autonomous AI agents. Policy from plain-English constitutions. (*https://ironcurtain.dev)

A secure* runtime for autonomous AI agents. Policy from plain-English constitutions. (*https://ironcurtain.dev)

Lightweight, secure Linux sandboxes for untrusted processes. Runs in the browser and on the server.

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

Trained to Escalate: Forensic Analysis and Local Replication of RLHF-Induced Privilege Escalation in AI Agents (CVE-2026-65616)

An AI personal assistant with a focus on security.

Proper sandboxing for agentic coding and web browsing

Cryptographically signed, replay-verifiable evidence layer for AI agents. Governs actions in the loop, produces Ed25519-signed receipts linked into a…

Security for the modern age of AI: defend against bad AI agents and malicious npm packages

A local sandbox for your AI agents

Lightweight CLI tool that runs AI coding agents inside isolated Bubblewrap sandboxes with strict filesystem, network, and credential isolation to…

LLM-first deception framework: "The honeypot that talks back!™"

Lightweight, cross-platform process sandboxing powered by OpenAI Codex's runtime. Sandbox any command with file, network, and credential controls.

WASM sandbox with capability enforcement for AI agent code. Agents can only call explicitly provided tools with defined constraints. Sandboxed…

Docker Compose lab reproducing CVE-2026-33626 SSRF in LMDeploy's vision-language image loader. Compares vulnerable (0.12.0) and patched (0.12.3)…


Zero-trust sandbox for AI agents with kernel-level filesystem jail, transparent network proxy, and YAML-based policy engine to intercept and control…

AI-driven automated threat analysis pipeline that routes files, URLs, IPs, domains, or images through specialized security analyzers and generates…

Ultrafast CLI on Apple Silicon macOS for fast, sandboxed development and LLM agents.