anoop_kumar

Is it just me, or are others getting the same error? Error from provider (Console): Upstream request failed: Endpoint is unavailable.

I really like the way this is framed. I don't like the fact that AI is the one writing the novel, but honestly, who cares as long as the novel is good.

What I would really like is a fiction writing tool that helps me brainstorm and research as I'm writing specific topics. for example I would write certain things I would click on it highlight and say go do research it'll go do research on that particular line come back to me and then present me with the analysis and also how I should reframe that line I think that in my opinion is going to be super helpful I wish somebody would build a tool for that.

Would love to get some feedback

This looks great. I was thinking of using this until I saw the pricing for Team.

Seems like Anthropic heard us and reduced it down to 2. https://claude.com/pricing#team-&-enterprise

IMO, this seems like it was tasked to someone and that someone had to do a checklist to say 'yes i completed the task'. The 2-50 team member plan is great but the benefits like org spend limits, role based access, audit logs etc only remain with the enterprise tier.

I want this on my kindle! but unfortunately, the refresh rates won't permit you to build something like this even if you could.

Fantastic! I have been using HTML for all my slides but this is next level. Is there a way to export this into PPTX format?

I am confused. What is this for again? IS it for AI Agents to start discussion or humans?

Nice! Simple yet elegant. I was looking for something like this and prompting my nano banana pro to create it and it would work sometimes but not all the time.

Is this open sourceD? How do we know how the routing happens? IS there an eval?

Is Canopy wave another one like crusoe or do they just whitelabel from big cloud providers?

has anyone tried hosting this on a machine that's not a laptop like a EC2? Curious if we can get better performance than on bedrock (which does not yet support GLM 5.2)

why not just use something like smol VMs? So many VM's and I am confused on which one to use for what. I think we now need a VM orchestrator!

looks like the page is broken

Got me down a rabbit hole of trying to find the ROI of doing something like this. This is what every GM at AWS thinks about. So, a back of the napkin calculation of running at FP8 and approx 35GB. You can fit that on a g6e.xlarge @ 48GB for about $900/year at reserved capacity.

Assuming you are netting at $5.5 (post stripe fees), and maybe $100/month for API/auth box for egress, you probably need about 170 paying customers to breakeven. This is assuming light/bursty usage.

Kudos! This is a a win win for both you and customer using it as it removes the undifferentiated heavy lifting.

I am going to open source and build a tooling to help partially solve this problem for telemetry for AI coding agents.

Agree. Seems like claude is losing out on smaller startups. If the hypothesis is that there will be unicorns with 2-3 person company, then why fix at 5?

i have been looking for something like this for a while now! Thank you!

Interesting. Good use case especially for portability to cloud.

just happened to stumble on this project. Super awesome!

I used to like Electron but most recently became a fan of Tauri. Electron is great from a UI perspective but seems like it tends to get bloated very quickly. Any suggestions on how to deal with it?

Open source? Is there a github link?

I would love to have an option where instead of just redaction; I'd love to swap it with something else when it goes to AI and then swap it back when the AI returns it. Thanks for sharing the github. I might submit a PR if I don't find that feature

What's the feedback from users who have tried this? Seems like a easy thing for agents to use but is that really necessary?

What does Artie do differently from Debezium for TOAST columns and schema drift, or is it Debezium under the hood?

Is this more effective than using mermaid?

Trying to understand this better, what does the vocabulary layer give you that just putting the graph schema in the system prompt doesn't?

Does this run on WebAssembly in the browser?