IronClaw is the secure, open-source alternative to OpenClaw that runs in encrypted enclaves on NEAR AI Cloud. AI agents that actually do things, but your secrets never touch the LLM.

IronClaw offers simple setup and built-in security for OpenClaw's personal AI assistant—powered by NEAR AI Cloud or run locally.
Launch your own IronClaw instance on NEAR AI Cloud. It boots inside a Trusted Execution Environment — encrypted from the start, no setup required.
Add API keys, tokens, and passwords to the encrypted vault. IronClaw injects them only where you've allowed — the AI never sees the raw values.
Browse, research, code, automate. Same capabilities as OpenClaw — except now a prompt injection can't steal your credentials.
IronClaw Instance
NEAR AI Cloud · TEE Ready
IronClaw is powered by NEAR AI's cryptographically secure infrastructure, which ensures your credentials never leave the vault.
Your credentials are invisible to the AI. API keys, tokens, and passwords are encrypted at rest and injected into requests at the host boundary — only for endpoints you've approved.
A compromised skill can't touch anything else. Every tool runs in its own Wasm container with capability-based permissions, allowlisted endpoints, and strict resource limits.
Not even the cloud provider can see your data. Your instance runs inside a Trusted Execution Environment on NEAR AI Cloud — encrypted in memory, from boot to shutdown.
Credential exfiltration gets caught before it leaves. All outbound traffic is scanned in real-time. Anything that looks like a secret heading out the door is blocked automatically.
Entire classes of exploits don't exist here. No garbage collector, no buffer overflows, no use-after-free. Memory safety is enforced at compile time, not at runtime.
You control exactly where data goes. Tools can only reach endpoints you've pre-approved. No silent phone-home, no data exfil to unknown servers.
OpenClaw unlocks the agentic future but it also risks exposing your secrets. Credentials can be exposed through prompt injections. Malicious skills exist to steal passwords. If you're running OpenClaw by itself with anything sensitive, there are significant risks.
Prompt injection can dump your secrets.
A single crafted prompt can trick the LLM into revealing every API key and password you've given it. Telling it "don't share" doesn't help.
Hundreds of malicious skills found on ClawHub
Researchers found hundreds of community skills designed to quietly exfiltrate credentials. You won't spot them in a code review.
30,000+ instances exposed to the internet.
Tens of thousands of OpenClaw instances are publicly reachable. Attackers are already weaponizing them.
IronClaw's security model doesn't rely on telling the AI "please don't leak this." Your credentials live in a Trusted Execution Environment that provides hardware-enforced security. Your credentials are injected at the network boundary—only for endpoints you've pre-approved.
Every tool runs in its own WebAssembly sandbox with no filesystem access and no outbound connections beyond your allowlist. The entire runtime is Rust — no garbage collector, no buffer overflows, no use-after-free.
Credentials at rest · Encrypted
Choose a NEAR AI deployment based on your performance requirements and preferred agent. You get NEAR security no matter what.
Spin up to 5 agents in a Trusted Execution Environment with up to 130M tokens per month — no cloud setup, no infrastructure. Just a simple frontend and you're live.
Starter
Activate 1 agent instance in our secure environment, and use NEAR AI Inference to power your agent
Basic
Everything you need to get started, plus credits to get up and running quickly with up to 2 agent instances
Pro+
Activate up to 5 agent instances in our environment, plus advanced features and more tokens for high usage
Open source. One-click deploy on NEAR AI Cloud. Your secrets never leave the encrypted vault.