Open-source security guard that runs AI-generated and untrusted code in Firecracker micro-VMs with capability tokens and a full audit trail.
Autonomous AI agents are writing and executing code, but running it on your host server is a massive security risk. Vela (powered by the Aegis runtime) solves this. It’s a policy-driven execution guard that uses Firecracker micro-VMs and HMAC capability tokens to safely run untrusted code. Get structured results, fine-grained filesystem/network restrictions, and a full JSONL audit trail. Open-source, MIT licensed, and built for LangChain/LlamaIndex.
Source: Product Hunt
Every verified price, limit, and model change we have tracked for VELA.
One email when VELA changes price or limits. No account, no spam.