Skip to main content

Documentation Index

Fetch the complete documentation index at: https://docs.edgespark.dev/llms.txt

Use this file to discover all available pages before exploring further.

Gemini CLI is a first-class supported agent for EdgeSpark. The EdgeSpark Gemini workflow uses GEMINI.md as the project instructions file together with the dedicated Gemini CLI extension.
1

Install the EdgeSpark CLI

npm install -g @edgespark/cli
edgespark login
This installs the CLI globally and authenticates your account. Your credentials are stored locally and reused for all subsequent commands.
2

Install the EdgeSpark Gemini CLI extension

gemini extensions install https://github.com/edgesparkhq/gemini-extensions
This is the current public Gemini CLI onboarding flow exposed by EdgeSpark.
3

Initialize your project

Pass --agent gemini to generate GEMINI.md:
edgespark init my-app --agent gemini
cd my-app
The scaffold writes GEMINI.md at the project root so Gemini CLI sessions have a dedicated EdgeSpark instructions file.
4

Start an EdgeSpark task

In Gemini CLI, use the EdgeSpark task-entry command:
/edgespark:building-edgespark-apps

​
Extending GEMINI.md

Add project-specific rules below the generated content: 
<!-- Generated content above — do not edit -->

## Project-specific rules

- The `posts` table is soft-deleted — always filter `WHERE deleted_at IS NULL`
- Route `/api/admin/*` requires `user.role === 'admin'` checked after platform auth
Gemini follows these additions with the same priority as the generated content. See AGENTS.md reference for the full format.

​
See also

AGENTS.md reference

Full reference for the agent instructions file — what it contains and how to extend it.

Declarative workflow

How Gemini CLI pulls schema and writes code against generated types.

Deploy and test loop

The full autonomous deploy and test workflow for any agent.

Supported agents

All supported AI agents and their setup pages.
Last modified on April 9, 2026