Skip to main content
R

Riza

Riza offers a secure, low‑latency code execution service that runs LLM‑generated Python, JavaScript/TypeScript, Ruby, and PHP code in isolated WebAssembly sandboxes. Developers can invoke execution via a REST API or SDKs with configurable environment variables, network access, and filesystem permissions, ensuring safe, fast execution without risking production systems.

San Francisco, United StatesFounded 20247300+ followers
Updated 2 months ago

Funding

$2.7M raised to dateRaised to date based on public sources. This may differ from the amount the company actually raised and is based only on what is publicly available on the internet.

Funding rounds are not available yet.

Founders

Founder details are not available yet.

Product

Problem

LLMs can generate code but executing that code safely and quickly is difficult, especially when the code may be untrusted or require specific runtime environments. Without isolated execution, developers risk exposing production systems, secrets, and resources to malicious or buggy code.

Solution

Riza provides a secure, low‑latency code execution service that lets AI applications run generated Python, JavaScript/TypeScript, Ruby, and PHP code in isolated WebAssembly sandboxes. Each request runs in a stateless Docker container with configurable environment variables, network access, and filesystem permissions, ensuring that code cannot affect the host system or access unauthorized data. The platform offers an API‑first design with client libraries for Python, Node.js, and Go, enabling developers to invoke code execution via simple REST calls or SDK methods. Riza’s service starts executing code in under 10 ms, eliminates cold‑start overhead, and supports custom runtimes for additional packages. For organizations with strict compliance needs, Riza can be self‑hosted as a single Docker image, providing the same isolation guarantees on‑premise.

Target Audience

Primary customers are AI product teams, SaaS developers, and enterprises that need to safely run LLM‑generated code for data transformation, tool creation, or feature extension, as well as organizations requiring on‑premise execution for compliance.

Features

  • Isolated WebAssembly sandboxes with no privileged Docker mode required
  • Support for untrusted Python, JavaScript/TypeScript, Ruby, and PHP execution
  • Configurable environment variables, HTTP‑only network access, and fine‑grained filesystem permissions per request
  • Sub‑10 ms cold‑start latency and up to 15 minute execution time (depending on plan)
  • API‑first interface with REST endpoints and official SDKs for Python, Node.js, and Go
  • Custom runtimes allow inclusion of third‑party packages and dependencies
  • Optional self‑hosting via a single Docker image for on‑premise or private‑cloud deployments
  • SOC 2 Type 1 audited security posture covering confidentiality, integrity, and availability
This profile is AI-generated and may contain inaccuracies.