rguldener

Author here, the build happens together with building your app. Once built, the code executes deterministically at runtime.

The news here is the AI reading the API docs, assembling requests, and iterating on them until it works as expected.

This sounds simple, but is time consuming and error prone for humans to do.

Nango | Staff backend engineer | Remote | Full time | $120-200k + equity

Nango (YC W23) is an open-source developer infrastructure for product integrations.

We power the integrations of Replit, Semgrep, Motion, Vapi, Exa, and hundreds of other AI companies.

Small but highly experienced team, hard technical challenges (scale + infra devtool running untrusted user code), tons of ownership, direct customer contact, growing very fast.

We are looking for a Staff engineer who can touch every part of the stack and is passionate about dev infrastructure.

Website: https://nango.dev Jobs: https://nango.dev/careers

Nango is an open-source alternative: https://nango.dev

Especially if you use pipedream for integrations in your agent or product.

(I’m one of the founders)

Nango | Staff backend engineer | Remote | Full time | $120-200k + equity

Nango (YC W23) is an open source product: Developer infrastructure for product integrations.

We power the integrations of Semgrep, Motion, Vapi, Exa, and hundreds of other B2B software.

Small but highly experienced team, hard technical challenges (scale + infra devtool running untrusted user code), tons of ownership, direct customer contact, growing very fast.

We are looking for a Staff engineer that can touch every part of stack and is passionate about dev infrastructure.

Website: https://nango.dev Jobs: https://nango.dev/careers

It varies a lot. Which is why we always recommend to start with the feature requirements/user problem and work backwards from there.

Examples: - Low latency to show X last emails a person had with a specific email address

- Enriching data from the emails/calendar with other data from your product (E.g. mapping email recipients to contacts)

- Knowing when a calendar event has changed (sometimes also possible with webhooks)

- Detecting deletes (maybe also possible with webhooks, not sure for gmail/calendar)

Founder of https://www.nango.dev here.

A lot of teams use us for their Gmail & Google calendar integrations.

If you want to run complex queries across large parts of the data, syncing + indexing on your side will be necessary. Limits on filters, pagination & rate limits make it infeasible to search across most of a user's inbox without tens of seconds to minutes of latency.

But before you sync all the data, I would test if your users actually need to run such queries.

Both Gmail & Google Calendar have a query endpoint that searches across many fields. I would start with a simple tool for your agent to run queries on that, and expand from there if necessary.

Both Nango and Composio could do this for you.

With Nango, you would also get syncs on the same platform, if it turns out you need them.

Hope this helps!

Thanks for the flag, should be fixed!

Nango | Staff backend engineer | Remote | Full time | $120-200k + equity

Nango (YC W23) is an open source product: Developer infrastructure for product integrations. We power the integrations of Semgrep, Motion, Vapi, Exa, and hundreds of other B2B software.

Small but highly experienced team, hard technical challenges (scale + infra devtool running untrusted user code), tons of ownership, direct customer contact, growing very fast.

We are looking for a Staff engineer that can touch every part of stack and is passionate about dev infrastructure.

Website: https://nango.dev Jobs: https://nango.dev/careers

Open source tools for engineers to build integrations in their products: https://nango.dev

We offer volume discounts on all metrics.

Email me on robin @ <domain> and happy to find a solution for your use case

Agree, one MCP server per API doesn’t scale.

With something like https://nango.dev you can get a single server that covers 400+ APIs.

Also handles auth, observability and offers other interfaces for direct tool calling.

(Full disclosure, I’m the founder)

You could use Nango for the OAuth flow and then pass the user’s token to the MCP server: https://nango.dev/auth

Free for OAuth with 400+ APIs & can be self-hosted

(I am one of the founders)

Nango | Remote | Hiring fullstack engineers & Entrepreneuer in Residence

Nango is an open-source platform for product integrations with 300+ APIs.

B2B SaaS use us to connect their product with all the other SaaS their customers use. Learn more here: https://www.nango.dev

We are a late-seed stage, YC-backed startup and fully remote (US & EU).

Hiring for fullstack engineering roles (EST timezone) and an entrepreneur in residence (also EST based).

More details: https://www.nango.dev/jobs

A year ago we implemented OAuth for 100 popular APIs.

Our experience was exactly like OP describes: https://www.nango.dev/blog/why-is-oauth-still-hard

I agree. Integrations can be incredibly cumbersome if you have to learn each API from scratch.

There are also more flexible solutions like https://www.nango.dev

It handles the API-specific complexities (auth, retries, webhooks, per-customer config, pre-built templates) but allows you to implement the exact use case + data model you need.

It's open source/source available.

(disclaimer: I am a founder)

I heard good things about Infisical (open source, end to end encryption of secrets): https://infisical.com/

Very cool! I love how you build on the need for each step one by one.

We implemented (O)Auth for 250+ APIs with Nango and wrote about our experience here: https://www.nango.dev/blog/why-is-oauth-still-hard