> ## 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.

# Amp and EdgeSpark

> Set up Amp (by Sourcegraph) to work with EdgeSpark — install the CLI, generate AGENTS.md, and give Amp the context it needs to build on EdgeSpark.

Use `AGENTS.md` as the project instructions file for Amp. The `AGENTS.md` file generated by `edgespark init` gives Amp the EdgeSpark-specific context for path-based auth, database schema workflow, and CLI commands.

<Steps>
  <Step title="Install the EdgeSpark CLI">
    ```bash theme={null}
    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.
  </Step>

  <Step title="Install EdgeSpark skills and docs MCP">
    Use the generic EdgeSpark skills package for OpenCode, Amp, Devin, Aider, Windsurf, Cline, Continue, Antigravity, Kiro, and every other AI coding agent that does not have a dedicated EdgeSpark plugin or extension:

    ```bash theme={null}
    npx skills add edgesparkhq/agent-skills
    ```

    If your agent supports remote MCP helpers, add the EdgeSpark docs MCP server:

    ```bash theme={null}
    npx add-mcp https://mcp.edgespark.dev/docs
    ```
  </Step>

  <Step title="Initialize your project">
    ```bash theme={null}
    edgespark init my-app --agent amp
    cd my-app
    ```

    Keep `AGENTS.md` in the repo as the primary EdgeSpark instructions file for Amp.
  </Step>
</Steps>

## See also

<Columns cols={2}>
  <Card title="Supported agents" icon="robot" href="/agents/supported-agents">
    Claude Code, Gemini CLI, OpenAI Codex, GitHub Copilot, Cursor, OpenCode, Amp, Devin, Aider, Windsurf, Cline, Continue, Antigravity, Kiro, and all other AI agents.
  </Card>

  <Card title="AGENTS.md reference" icon="file-lines" href="/agents/agents-md">
    What the agent instructions file contains and how to extend it with project-specific rules.
  </Card>

  <Card title="Declarative workflow" icon="database" href="/agents/declarative-workflow">
    Pull schema, write code against generated types, and validate deploys safely.
  </Card>

  <Card title="Deploy and test loop" icon="rotate" href="/agents/deploy-and-test">
    The full autonomous deploy and test workflow any agent follows.
  </Card>
</Columns>