AskOpenSource by The Arthi AI Collective

GRIDCITY

Developers, homelab users and small teams who run a few servers and databases. They can see what is unhealthy at a glance, diagnose a failed database connection with suggested fixes that are tested before being shown, and let their AI coding agent investigate their infrastructure safely, approving each command it wants to run.

View chapeee/gridcity on GitHub
GitHub stars
—
Forks
—

Project details

Repository
chapeee/gridcity
Licence
MIT
Catalog status
Available
Catalog check
2026-11-13
Required costs
None for the app. It runs locally and needs Node.js 22.12+ or Docker. The AI features use your own AI client (for example Claude Code or Cursor over MCP) or your own Codex, Gemini or Anthropic account, which may have their own costs; monitoring and management work without any AI. Optional AWS cost reports use AWS Cost Explorer, which AWS charges per request.

Repository description

GRIDCITY shows your Linux servers, databases (PostgreSQL, MySQL, SQL Server, SQLite, MongoDB), Redis and S3-compatible buckets as buildings in a 3D city, where each light maps to one real metric. From the city you can open a real SSH terminal, browse data read-only by default, see SSH attacks and exposed databases, get alerts and replay past incidents. It includes an MCP server so AI agents such as Claude Code or Cursor can ask for the root cause of an incident and propose commands, and every command waits for the user's approval before it runs.

Explore by topic

More tools in AI agents