Skald – open-source context layer API that runs in your VPC
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…
What it does
In the maker’s words, at launch
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 but bring 6 API keys to get started”. Our customers have used Skald to quickly build features for their own users, as well as for internal tooling. The self-hosted MIT version is completely fully-featured, so much so that it’s what we run on our Cloud offering today. We do also have an enterprise license for larger customers that runs on their infra and has a few enterprise-focused features on top of the MIT version. Keen to hear your feedback and I’ll be around to answer questions! GitHub: https://github.com/skaldlabs/skald
Does the same job
all alternatives →
More ai this month
the category →
I trained a 125M-parameter transformer to autocomplete piano performances in real time (~108 notes/sec on an iPhone 15). The idea is basically GitHub Copilot or Tabnine, except instead of prompting it with code, you prompt it by playing a few notes on a MIDI piano. The model then continues what you played, entirely on-device. The app is free if anyone wants to try it. Happy to answer questions about the model, training, Core ML, or the many things that didn't work.
AI · 17d ago · simedw.com
Astute▲585Automate your B2B brand going viral, with new media creators
AI · 18d ago · company-app.joinastute.com
Hey HN, Henry from Cactus here! We previously released Cactus Needle, a 14MB agentic LLM for tool call, device use, and structured extraction for phones, wearables, smart homes, small robots and microcontrollers. We got really great feedback here, and have now incorporated the suggestions to release Needle 2. The whole model is a single 14MB binary that runs a full session in 28MB of RAM; 45m parameters at 2bit compression. Needle hits 500 tokens/sec decode speed on a Raspberry Pi 5, sits between 400-1,500 tokens/sec on VR devices like Meta Quest 3S and Apple Vision Pro, and ranges…
AI · 26d ago · cactuscompute.com
Launched alongside, December 2025
the whole month →- GP
Life & fun · Dec 2025 · dosaygo-studio.github.io
- JG
Hi everyone! My name's Luke and I made the original Jmail here alongside Riley Walz. We had a ton of friends collaborate on building out more of the app suite last night in lieue of DOJ's "Epstein files" release. Please AMA!
Life & fun · Dec 2025 · jmail.world
PlanEat AI▲733AI turns your health goals into a 7-day menu & grocery list
AI · Dec 2025 · planeatai.com
- 2G
Community, All the HN belong to you. This is an archive of hacker news that fits in your browser. When I made HN Made of Primes I realized I could probably do this offline sqlite/wasm thing with the whole GBs of archive. The whole dataset. So I tried it, and this is it. Have Hacker News on your device. Go to this repo (https://github.com/DOSAYGO-STUDIO/HackerBook): you can download it. Big Query -> ETL -> npx serve docs - that's it. 20 years of HN arguments and beauty, can be yours forever. So they'll never die. Ever. It's the unkillable static archive of HN and it's…
Dev tools · Dec 2025 · hackerbook.dosaygo.com
