really excited to see this release! i've been using TypeScript for several projects like https://github.com/dyad-sh/dyad which is >250k lines of TypeScript and the speed-up makes things like running typescript check as a pre-commit hook painless

thanks DanRosenwasser and team for building such an awesome tool for so many years!

i think this underscores why having coding agents being open-source is a really good thing

i used this tool when i was at google, extremely helpful in open-sourcing things from google3 to github. still, i'm glad to just directly develop on github now :)

Interesting! tbh, we don't have any runbooks and pretty minimal telemetry set up (we're a very small team :), do you have any recommendations on which telemetry service to use to get started? right now, our services run on a combination GCP Cloud Run + Vercel

Nice to see you here, Will! I’d generally recommend using open telemetry for instrumentation so that you keep the option of switching between telemetry vendors.

Re: runbooks, yeah even larger teams don’t have good ones to begin with. Relvy helps debug without runbooks as well - it might take longer to explore, but once you are happy with a particular investigation path the AI took, you can save it as a runbook for more deterministic future executions.

Really interesting project! I tried it last week and ran into same errors and today I tried it again and it worked.

I'm curious how the Clink desktop app connects to the web app. Is it sending some kind of oauth token so you can use call Claude Code, etc, on behalf of the user?

FWIW, I created an open-source project in this space https://github.com/dyad-sh/dyad/ and it's great to see people trying different approaches :)

Oh I really like your product! you're right about how it works. the desktop app sends oauth tokens to connect to the cloud infrastructure. dyad looks really cool, love the local-first approach. it's exciting to see so many different takes on this space right now. what are you focusing on with dyad these days?

thanks! we recently added MCP support so we're figuring out how to make it easier to find & add the right MCP tools for your use case :)

yes! https://www.dyad.sh/docs/guides/ai-models/local-models

Thank you!

we have an extensive system prompt to instruct the Supabase to follow RLS best practices: https://github.com/dyad-sh/dyad/blob/de2cc2b48f2c8bfa401608c...

What you're describing as the fail-open behavior is from the Supabase platform (and not specific to any app builders): https://supabase.com/docs/guides/database/postgres/row-level...

we have features like manual context management https://www.dyad.sh/docs/guides/large-apps#manual-context-ma... which lets you select files to use in your context window

Hey, could the tool do this itself? Like using code embeddings?

https://www.trynia.ai/ seems to be doing sometihing similar.

very interesting - when we ship MCP support you should be able to use nia!

How about local support? First draft is simple enough to implement: chunk => embed => store. And then one simple lookup function.

Complexity would arise once we start to go into AST's and graph traversals.

Thanks! Check out our Prompt Library feature: this way you can create reusable prompts across your apps: https://www.dyad.sh/docs/releases/0.18.0

I'm working on adding MCP support to Dyad soon! What's your favorite MCP servers? (trying to curate a list of recommended MCPs)

There is a project I’ve been playing with called claude-code-templates that keeps curated lists of things Claude code can use, one of which is MCP servers: https://github.com/davila7/claude-code-templates

neat! thanks for sharing

Context7 or Deepwiki are a must-have. They are also relatively secure, unless those sources of information become compromised in some way.