skald

> "- It was easier to find a link to where you worked at than your repo (https://github.com/skaldlabs/skald?tab=readme-ov-file), you should have linked it visibly" Genuinely curious, can I ask why this is relevant to point out? This seems like just a general blog post, about raising money for a startup and personal reflections on it. Why would a link to a github repo be an important part of that?

Some feedback from me (not a likely user though): - It was easier to find a link to where you worked at than your repo (https://github.com/skaldlabs/skald?tab=readme-ov-file), you should have linked it visibly - I had no idea what / why I should use it so I looked at the demo video and it didn't seem to solve any particular use case for any particular problem, it was more a ,,config'' video instead of a demo video - From reading the (quite interesting) article it seemed like you are focusing on pivoting instead of iteration speed. Have you tried for example to just query an LLM to build the whole project that you have done? How much time would be to vibe code it? I know that HN is mostly against vibe coding, but if the project could have been created in 1-3 days and you took 3 month, that's a bigger issue than growth itself. In that case

Hey HN! We built an open source context layer to power AI agents and apps even in air-gapped infra setups. TL;DR: Use our API (or one of the 6 SDKs) to push context into the Skald platform, and get semantic search and AI chat out of the box. We’ve seen companies spend months building a context layer system internally, only for it to have subpar performance and require active maintenance. Skald gives you the plumbing to get started really fast when building context-aware agents and AI apps (customers have gone to prod in a day with us) but is still highly extensible and configurable to fit individual needs. Our core is entirely MIT-licensed and you can even run it with a fully self-hosted stack (document parsing, chunking, vector search, LLM, etc) in your VPC. We think solutions in this space must be open source, and not just “open source