Serverless async back ends for compute-heavy operations
Hi HN, we’re Jessie and Eric. We’ve been baking away at Cakework (https://www.cakework.com/), which is a way to build async backends without needing to manage cloud infrastructure. Cakework is for operations that take time or more compute, like file processing, report generation, or machine learning. Devs write backends as Python functions and deploy them with our CLI. They use our client SDKs to make requests, get status, and get processing results. Each request runs with its own CPU and memory parameters in its own microVM, with no timeouts. Devs can query for failures and…
What it does
In the maker’s words, at launch
Hi HN, we’re Jessie and Eric. We’ve been baking away at Cakework (https://www.cakework.com/), which is a way to build async backends without needing to manage cloud infrastructure. Cakework is for operations that take time or more compute, like file processing, report generation, or machine learning. Devs write backends as Python functions and deploy them with our CLI. They use our client SDKs to make requests, get status, and get processing results. Each request runs with its own CPU and memory parameters in its own microVM, with no timeouts. Devs can query for failures and view logs, inputs, and outputs for each request. Under the covers, we package and deploy code as Docker containers. We queue each request on a NATs cluster, and spin up a Fly Machine (https://fly.io/docs/machines/) to process it. Cakework is open source (https://github.com/usecakework/cakework) if you want to dig in! We started exploring Cakework because we liked the idea of serverless for compute-heavy operations, but in practice found that an application made up of wiring together queues, Lambdas, storage, and step functions made iteration really slow. We also didn’t like having to switch away from Lambda when operations ran longer than fifteen minutes. If you want to give it a whirl, you can follow the quickstart on our website (https://www.cakework.com/), or check out the docs (https://docs.cakework.com/gettingstarted). We’re super excited to share an early build and get everyone’s thoughts, thanks for checking it out!
Does the same job
all alternatives →
- ADA distributed workflow engine written in Go2023 · github.com · ▲9
I'd like to share a project I've been working on for the past few months. It's a distributed workflow engine written entirely in Go. Some highlights: * Tasks are executed in a Docker container * Can run stand-alone or distributed * Highly extensible * Able to enforce limits (CPU/RAM) per task * Web UI Would love the get your feedback on it, and find out if this could be useful.
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
