Hey Kyle and congrats to the launch! Riza looks great!
Looks like we're building in the same space. I'm Vasek, co-founder of E2B [0]. We recently launched our Code Interpreter SDK [1].
We think safe code execution for AI generated code has a big future potential. I'd love to chat some time if you're up to it! Maybe there's a way we could join forces and build something great.
[0] https://e2b.dev/
really interesting direction! my company, assembled, builds software for customer support teams. i could imagine being on either end of this. on the one hand, we've built applications to run in the curated zendesk/salesforce sandbox. on the other hand, we get tons of requests to incorporate custom workflows or metrics natively in our application.
Will its security ever be defeated?
Been using Riza for the past few months at our startup for executing code generated by GPT4.
We use it for local dev, running model eval (when changing prompts), in CI and production work loads.
- It's the easiest to setup. It took us just a few minutes to execute our first function call.
- Multiple languages support - we use both JS and Python for code generated by LLM , Riza works great with both out of the box.
- No cold start - this is important because latency matters in our product.
- No infra management - even if we use AWS lambda or similar serverless product we felt like we still needed to a bunch of setup to make sure its fast + secure.
Congrats on launching!