NOW LET US – AI RAG SaaS Studio TP.HCM
NOW LET US
Digital Product Studio
Back to news
DEV-TOOLS...1 min read

Show HN: Coasts – Containerized Hosts for Agents

Share
NOW LET US Article – Show HN: Coasts – Containerized Hosts for Agents

Coasts is a CLI tool and local UI for running multiple isolated development environments on a single machine using containers, featuring Docker Compose support and an offline-first architecture.

Coasts (Containerized Hosts) is a CLI tool with a local observability UI for running multiple isolated instances of a full development environment on a single machine. It works out of the box with your current setup: no changes to your existing application code, just a small Coastfile at your repo root. If you already use Docker Compose, Coasts can boot from your existing docker-compose.yml; if you do not use Docker or Compose, Coasts works just as well.

Build once and run N instances with whatever volume and networking topology your project needs. Check out one coast at a time to bind canonical ports to your host, and use dynamic ports to peek into the progress of any worktree.

Coasts is agnostic to AI providers and agent harnesses. The only host requirement is Git worktrees, so you can switch tools without changing how you work and without any harness-specific environment setup.

Coasts is also offline-first with no hosted service dependency, so there is no vendor lock-in risk: even if we disappeared, your local workflow would keep running.

Install the latest public release: eval "$(curl -fsSL https://coasts.dev/install)"

Note: Coasts is currently macOS-first. Linux development works, but canonical ports below 1024 require host setup before coast checkout can bind them.

Requirements:

  • Rust (stable toolchain)
  • Docker
  • Node.js
  • socat
  • Git

Development Workflow:

  • Terminal 1: Dev daemon (coast-dev daemon start)
  • Terminal 2: Rust rebuild on save (make watch)
  • Terminal 3: Web UI with hot reload (npm run dev:coast-dev)

Project Structure includes coast-cli, coast-daemon, coast-core, coast-secrets, coast-docker, and coast-guard (React UI). Integration tests are performed using Docker-in-Docker (DinD) to ensure end-to-end reliability.

© 2026 Now Let Us. All rights reserved.

Source: Hacker News

Advertisement
Ad slot ready: 5887729102

More in this category

NOW LET US Related – GLM 5.2 Is Out

dev-tools

GLM 5.2 Is Out

Zhipu AI has officially released GLM-5.2, its most powerful open-source model to date, featuring a 1M context window and advanced long-horizon task capabilities. The release underscores Zhipu's commitment to open-source AI and global scientific collaboration amid rising technological restrictions.

NOW LET US Related – Noise infusion banned from statistical products published by Census Bureau

dev-tools

Noise infusion banned from statistical products published by Census Bureau

The U.S. Department of Commerce has banned "noise infusion" from statistical products published by the Census Bureau, a decision that could have severe consequences for both data utility and privacy protection.

NOW LET US Related – Treating pancreatic tumours may have revealed cancer's master switch

dev-tools

Treating pancreatic tumours may have revealed cancer's master switch

A promising new drug called daraxonrasib has shown breakthrough results in treating pancreatic cancer, doubling median survival times. This achievement could pave the way for an entirely new class of cancer treatments.

NOW LET US Related – Every Frame Perfect

dev-tools

Every Frame Perfect

In UI design, perfection isn't just about the start and end states, but every single transition frame in between. Polishing these micro-interactions is key to building user trust.

NOW LET US Related – Leaving Mozilla

dev-tools

Leaving Mozilla

A poignant and candid reflection from a 15-year Mozilla veteran upon their departure. The author highlights the leadership's missteps in trying to emulate tech giants and urges Mozilla to return to its core values: community and uniqueness.

NOW LET US Related – Shepherd's Dog: A Game by the Most Dangerous AI Model

dev-tools

Shepherd's Dog: A Game by the Most Dangerous AI Model

A developer tested Anthropic's latest, supposedly 'too dangerous' AI model by asking it to build a long-held game idea in a single shot. The model succeeded, generating a complete 2,319-line game after a 45-minute reasoning session.

EXPLORE TOPICS

Discover All Categories

Deep dive into the specific technology sectors that matter most to you.