wirken
★ 192
vs
ironcurtain
★ 614
wirken vs ironcurtain
wirken: Wirken is an enterprise gateway that securely connects your team's messaging channels to autonomous AI agents. It prioritizes security, offering sandboxed execution, audit logging, and credential isolation to control agent actions and protect sensitive data.; ironcurtain: IronCurtain provides a secure runtime for autonomous AI agents, enforcing security policies derived from human-readable constitutions to prevent issues like prompt injection. It ensures agents operate within defined boundaries through mechanisms like V8 isolates and a policy engine that mediates all tool calls.
01
TL;DR
wirkenSecurity & Safety · ★ 192
Securely deploying AI agents in enterprise environments with compliance needs.
ironcurtainSecurity & Safety · ★ 614
Securely Automating Development Tasks: Allowing AI agents to manage files and execute Git operations like cloning and pushing changes within defined security boundaries.
02
Side-by-Side Comparison
Field
wirkenironcurtainCategory
Security & Safety
Security & Safety
Stars
★ 192
★ 614
License
MIT
Apache-2.0
Install Command
curl -fsSL https://raw.githubusercontent.com/gebruder/wirken/main/install.sh | sh && wirken setup && wirken run
npm install -g @provos/ironcurtain
Updated
1d ago
2d ago
Open Source
Yes
Yes
Tags
AI Agents, Enterprise Gateway, Security
AI Agents, Security, Runtime
03
Features
wirken01Enterprise gateway for autonomous agents, acting as a secure switchboard.
02Sandboxed execution for shell commands in ephemeral containers (Docker/gVisor).
03Tamper-evident, hash-chained audit log for every agent action.
04Out-of-process credential isolation; tokens and keys never reach the LLM.
05Capability-attenuated multi-agent delegation with operator-set limits.
ironcurtain01Constitution-driven Security Policy: Define security intent in plain English, which is then compiled into deterministic and enforceable rules.
02Semantic Interposition & Runtime Enforcement: All agent interactions and tool calls are routed through a policy engine that allows, denies, or escalates based on policy.
03Untrusted Agent Model: Assumes the LLM may be compromised (e.g., by prompt injection or drift), enforcing security at the boundary regardless of the model's behavior.
04Multi-mode Operation: Supports both an internal LLM agent running in a V8 sandbox (Code Mode) and external agents running in Docker containers (Docker Agent Mode).
05Built-in Capabilities: Ships with pre-configured MCP servers for filesystem, Git, web fetching, and GitHub operations, all governed by policy.
04
Use Cases
wirken↳Securely deploying AI agents in enterprise environments with compliance needs.
↳Integrating AI agents with existing team messaging platforms like Slack and Teams.
↳Auditing and monitoring autonomous agent activities for security and accountability.
↳Running untrusted or external agents with controlled access to internal resources.
↳Automating routine tasks using scheduled, headless agents with security controls.
ironcurtain↳Securely Automating Development Tasks: Allowing AI agents to manage files and execute Git operations like cloning and pushing changes within defined security boundaries.
↳Autonomous Code Management and Bug Fixing: Utilizing agents to fix failing tests or perform code modifications in a project workspace with robust policy enforcement.
↳Controlled API Interactions: Enabling agents to interact with web services (e.g., web search, GitHub APIs) with granular policy control over each specific API call.
↳Managing AI Agent Security in Complex Environments: Running external AI agents (e.g., Claude Code, Goose) securely within a Docker container, with IronCurtain mediating every tool call through its policy engine.
↳Remote Agent Control and Escalation Handling: Interacting with and approving agent actions via end-to-end encrypted messaging platforms like Signal.
FAQ
FAQ
What is the difference between wirken and ironcurtain?
Both wirken and ironcurtain are in the Security & Safety category. wirken has 192 stars, while ironcurtain has 614 stars.
Which is better, wirken or ironcurtain?
The best choice depends on your use case. Choose wirken if Securely deploying AI agents in enterprise environments with compliance needs., and ironcurtain if Securely Automating Development Tasks: Allowing AI agents to manage files and execute Git operations like cloning and pushing changes within defined security boundaries..
Is wirken free or open source?
Yes, wirken is open source on GitHub (MIT).
Is ironcurtain free or open source?
Yes, ironcurtain is open source on GitHub (Apache-2.0).
Cloud Infrastructure
AdDeploy on DigitalOcean
Host your MCP servers, Docker containers, and AI agents with $200 free credit over 60 days.
→