Swytchcode CLI - Give agents reliable access to 2,000+ APIs w/ durable state

by
Write agent logic, and skip the plumbing. Give AI agents reliable access to 2,000+ APIs with retries, idempotency, policy enforcement, and durable state.

Add a comment

Replies

Best

Nice job! Need of the hour

 thank you for your support.

Really cool! Can I use this on my projects? Like instead of me writing this protection layer swytchcpde handles that

 yes you can use this in your project, Swytchcode support popular coding agents like Claude, co-pilot,cursor,codex etc.

 would love to speak to you Lakshay and understand your use case and take feedback. Sending you a linkedin connect

skip the plumbing is the right pitch for this category. the actual agent logic is usually 20% of the work and the retry handling, rate limiting, auth management, and state persistence is the other 80% that nobody wants to rebuild for every new integration. 2000 APIs is a coverage claim worth verifying but the reliability primitives are the real produc

 rightly said. I would really love to hear your feedback about the product.
Please give it a try and reach me out if you face any issue

The durable state part feels like the real differentiator here. A lot of agent API integrations work in demos, but get messy once auth, retries, partial failures, and long-running workflows show up.

Curious how you think about permission boundaries: is the agent scoped per workflow, per connected API, or per user session?

 That's a great question. Today, the boundaries are set for only a project-wide scope. But we are already working on workflow/method level granularity. It'll come soon

 That makes sense. Workflow/method-level granularity sounds like the right direction for production use. Curious if you’ll also support read-only vs write permissions per method.

 Good suggestion. We'll look into this

Congratulations!!

 thankyou so much Thami

 thanks a lot Thami

congratulations on the launch

really interesting take on the execution layer being the missing piece for agents.

curious to know: at what scale or stage do teams usually start feeling this pain? is it after a certain number of agent runs, APIs, or production workflows?

 teams start feeling the pain when
1. something breaks in production and customers complain
2. AI starts hallucinating and you have no control over what calls are made to your API services
3. there is an API update or a security update and you lose track of the notifications
4. AI starts calling services without your consent

And a lot of other use cases

The emphasis on idempotency and durable state is massive. In marketing automation, the absolute last thing you want is a glitch causing an agent to double-trigger an email sequence or webhook to a customer. How does Swytchcode handle those retry loops cleanly under the hood?

 thanks for your thoughts, Andika. Today, a manifest file manages Swytchcode's retries and idempotencies. While executing, the CLI ensures all the rules in the manifest are properly followed and never missed. The custom retries and idempotencies are set by the user.

For a community launch workflow, I’d test an agent that collects Discord feedback, opens GitHub issues, and sends follow-up emails without redoing auth plumbing. The .swytchcode folder as a project boundary makes sense, but I wonder about handoff between local dev and production. When deploying from a CLI-built agent, does Swytchcode provide a hosted runtime, or is it expected to ship inside our own worker/server?

 thank you for the support and asking this, swytchcode gets shipped inside your worker/container.

That boundary is helpful: the runtime stays in our infra, while Swytchcode owns the integration layer. For production, I’d probably look next at how the .swytchcode config gets promoted between staging and prod without leaking credentials into the repo.

 absolutely. Please feel free to try it out and share with us your feedback. I would absolutely love to hear back from you. Happy to connect on or

The execution-layer framing is right. The failure I'd worry about most is the call that succeeds but does the wrong thing. Schema validation and idempotency catch malformed and duplicate requests, but a well-formed request that pauses the wrong campaign or refunds the wrong order still goes through clean. I run approval-gated writes on ad accounts for exactly this reason, so I'd want a dry-run mode and a confirmation gate on anything destructive or money-moving, scoped by risk level rather than only per method. Does the manifest let you flag certain actions as require-approval before they execute?

 hmm, that's a great question. We are coming up with custom policies to handle that.

Would love to know what you are building. Let me connect with you on your X.

This is a strong framing: the agent is not the hard part, reliable execution is. In B2B workflows, policy enforcement often needs business context, not just API/schema context.

 rightly said, Soumyaa. Please give it a try and we would love to hear your feedback