Crewship – Deploy AI agents to production in one command
Hey HN! We built Crewship (https://crewship.dev) because deploying AI agents to production is still unnecessarily painful. If you've built something with CrewAI, LangGraph, or similar frameworks, you know the drill: it works great locally, then you spend days figuring out infrastructure, scaling, monitoring, and artifact management just to get it running for real users. Crewship handles all of that. You add a crewship.toml to your project, run `crewship deploy`, and your agents are live in seconds. It's framework-agnostic — we currently support CrewAI, LangGraph, and LangGraph.js,…
In plain words
Crewship is a deployment platform for AI agents built with CrewAI, LangGraph, or LangGraph.js. It simplifies moving agents from local development to production by automating infrastructure setup, scaling, and monitoring through a single command. The platform handles real-time streaming of agent actions, automatic collection of generated artifacts, and automatic scaling for concurrent runs without requiring Docker or Kubernetes configuration.
written from the facts on this page · September 2026
From the sources
In the maker’s words, at launch
Hey HN! We built Crewship (https://crewship.dev) because deploying AI agents to production is still unnecessarily painful. If you've built something with CrewAI, LangGraph, or similar frameworks, you know the drill: it works great locally, then you spend days figuring out infrastructure, scaling, monitoring, and artifact management just to get it running for real users. Crewship handles all of that. You add a crewship.toml to your project, run `crewship deploy`, and your agents are live in seconds. It's framework-agnostic — we currently support CrewAI, LangGraph, and LangGraph.js, with more coming. What you get: - One-command deploy (no Docker/K8s config needed) - Real-time streaming of agent actions via SSE - Automatic artifact collection (every file/report your agents produce) - Auto-scaling from zero to thousands of concurrent runs - Version control with instant rollback - Secrets management We're a small team in Switzerland, and we've been using this ourselves for months. Free tier available — would love your feedback. Docs: https://docs.crewship.dev Quickstart: https://docs.crewship.dev/quickstart
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 · 27d ago · cactuscompute.com
