Milk Infrastructure – AI that builds, deploys, manages infra
I've been working on a platform that uses LLMs to build maintain and manage k8s clusters on any cloud. The system writes infra as code to your Github repos and automatically containerizes and scales any services (public or private). The goal is to give your average engineer a vercel-like deployment experience for any service in any language at minimal cost. We have humans involved at the moment auditing LLM outputs and keeping an eye on clusters. We are looking for folks who may be thinking about their first infra/devops hire. Just connect your github and your cloud provider. The system…
Milk Infrastructure – AI that builds, deploys, manages infra launched on June 27, 2024 with 6 votes, #1,458 of 4,672 launches that month and more than 50% of that year's launches. The site was still online in September 2026, 2 years on.
What it does
Point the official OpenAI SDK at Milk Parlor. Milk Man processes completed requests and responses from object storage.
Your app gets its answer. Milk puts the saved traffic to work. Keep the official OpenAI SDK and your existing calls. Change the URL and key. Sends your model calls and returns the answers. Saves eligible request–response pairs in the background. Give it a goal. It runs commands, starts cloud models, measures results, and saves what it learns. Parlor handles the request. Milk Man works on what comes after. The saved file fills the dashboard. Open it to see what changed. Example milestones · set with MILK_SUMMARY_THRESHOLDS . One exchange is a request and its response. Save each eligible request and answer under your account's unique ID. Related exchanges stay grouped as one task. Count new…from milkinfrastructure.com
In the maker’s words, at launch
I've been working on a platform that uses LLMs to build maintain and manage k8s clusters on any cloud. The system writes infra as code to your Github repos and automatically containerizes and scales any services (public or private). The goal is to give your average engineer a vercel-like deployment experience for any…
Does a similar job
all alternatives →
Infrabase2025 · infrabase.co · ▲142We too at first thought that letting an LLM manage your AWS account must be a bad idea. What could possibly go wrong?? However we couldn’t resist building it, and when we did, we were surprised how much it can do even in plain vanilla form, which currently is just the ai-sdk frontend with some aws sdk code generation (inspared by aws-mcp). We all but stopped using the AWS console internally and switched to Infrabase - a lot of the time it’s much faster to prompt than to click around in AWS console, especially for things that involve multiple steps, IAM roles, etc. So we started to think of…
TensorZero2025 · github.com · ▲307Hi HN! We're Gabriel & Viraj, and we're excited to open source TensorZero. To be a little cheeky, TensorZero is an open-source platform that helps LLM applications graduate from API wrappers into defensible AI products. 1. Integrate our model gateway 2. Send metrics or feedback 3. Unlock compounding improvements in quality, cost, and latency It enables a data & learning flywheel for LLMs by unifying: • Inference: one API for all LLMs, with <1ms P99 overhead • Observability: inference & feedback → your database • Optimization: better prompts, models, inference strategies • Experimentation:…
Open-source real time data framework for LLM applications2024 · getindexify.ai · ▲92Hey HN, I am the founder of Tensorlake. Prototyping LLM applications have become a lot easier, building decision making LLM applications that work on constantly updating data is still very challenging in production settings. The systems engineering problems that we have seen people face are - 1. Reliably process ingested content in real time if the application is sensitive to freshness of information. 2. Being able to bring in any kind of model, and run different parts of the pipeline on GPUs and CPUs. 3. Fault Tolerance to ingestion spike, compute infrastructure failure. 4. Scaling compute,…
More ai this month
the category →
Paintings by AI models: programs run through a simulation of oil paint.
AI · 22d ago · stillwet.art
FastRouter.ai▲364Route requests to the right LLM for cost, latency & quality
AI · 23d ago · fastrouter.ai
Source: Show HN post ↗ · launch text quoted in part
Launched alongside, June 2024
the whole month →
La Growth Machine▲1,216Create personalized, multi-channel conversations at scale
AI · 2024 · lagrowthmachine.com
PyjamaHR▲1,132Hiring on autopilot. The AI applicant tracking system (ATS).
Work · 2024 · pyjamahr.com