ironcurtain
★ 614
vs
platform
★ 15
ironcurtain vs platform
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.; platform: SidClaw intercepts AI agent tool calls, checks them against defined policies, and holds risky actions for human review. It prevents agents from executing unauthorized or high-risk operations, ensuring secure and compliant AI deployments.
01
TL;DR
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.
platformSecurity & Safety · ★ 15
Customer Support Agent (Financial Services): Governing email sending and other sensitive operations by AI agents in financial customer support.
02
Side-by-Side Comparison
Field
ironcurtainplatformCategory
Security & Safety
Security & Safety
Stars
★ 614
★ 15
License
Apache-2.0
Apache-2.0
Install Command
npm install -g @provos/ironcurtain
git clone https://github.com/sidclawhq/platform && cd platform/packages/sidclaw-demo && node cli.mjs
Updated
2d ago
4d ago
Open Source
Yes
Yes
Tags
AI Agents, Security, Runtime
AI Agent Governance, Tool Call Control, Security
03
Features
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.
platform01Policy engine: allow / approval_required / deny with priority ordering and classification hierarchy.
02Approval workflow: context-rich cards with agent reasoning, risk classification, and separation of duties.
03Audit trails: correlated traces with integrity hash chains (tamper-proof).
04Fast setup: `npx create-sidclaw-app` scaffolds a working governed agent in seconds.
05Framework-agnostic: Compatible with LangChain, OpenAI, Claude Agent SDK, and many more, or plain functions.
04
Use Cases
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.
platform↳Customer Support Agent (Financial Services): Governing email sending and other sensitive operations by AI agents in financial customer support.
↳Infrastructure Automation (DevOps): Enforcing human approval for high-risk deployments or scaling operations performed by AI agents in DevOps.
↳Clinical Decision Support (Healthcare): Allowing physicians to review and approve AI assistant recommendations for lab orders, while blocking restricted actions like medication prescribing.
FAQ
FAQ
What is the difference between ironcurtain and platform?
Both ironcurtain and platform are in the Security & Safety category. ironcurtain has 614 stars, while platform has 15 stars.
Which is better, ironcurtain or platform?
The best choice depends on your use case. Choose 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., and platform if Customer Support Agent (Financial Services): Governing email sending and other sensitive operations by AI agents in financial customer support..
Is ironcurtain free or open source?
Yes, ironcurtain is open source on GitHub (Apache-2.0).
Is platform free or open source?
Yes, platform 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.
→