> ## Documentation Index
> Fetch the complete documentation index at: https://graph.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.

# Introducing Graph

> A runtime and development environment for building scalable AI-augmented workflows

The goal of graph is to provide an AI native workflow engine that not only allows for precise integration of LLM inference into your workflows, but to provide a powerful generative development experience.  You should be able to go from idea to a new LLM-powered review check in Github in minutes instead of hours.

<Frame caption="Debugging a plan in the Graph workbench">
  <img src="https://mintcdn.com/graph/VaTetSEpy4ieswMa/images/workbench/hero.svg?fit=max&auto=format&n=VaTetSEpy4ieswMa&q=85&s=9289da12e66e3c5de8b1af44f3dd3353" alt="The workbench after a completed weekly_status run: the chat agent on the left, the fully-executed step tree with exit-gate, map, and solver rows on the right, and the map's dataflow template in the detail pane." width="1044" height="720" data-path="images/workbench/hero.svg" />
</Frame>

## Why graph

* **Deterministic by default.** Steps are plain tool calls able to reference past step output. The LLM enters only where you put it: a [prompt tool](/tools/user-defined) as a step (classify, extract, summarize mid-plan) and a [finish](/plans/finish-modes) that is a written report, structured JSON, or nothing at all.
* **Any tool you can imagine.** Native MCP support and an intuitive tool framework brings every integration you could possibly need to your fingertips.
* **Repeatable and reviewable.** A plan is a file you check into a repo, review in a PR, and share with your team. Your Monday status report is the same report every Monday.
* **Composable.** Every plan joins the tool catalog as `plan__<name>`, callable like any other tool — from the CLI, from a script, or from inside another plan. And a plan's own steps draw from that same catalog: MCP tools, wrapped CLIs, saved queries, prompt tools, and other plans.
* **Bring your own models and storage.** Any MCP server; Anthropic, OpenAI, or OpenAI-compatible/local models, [assignable per role](/models/models-and-providers). A single binary with plain-file storage — or in-memory storage for ephemeral CI runs. Your data stays on your machine.

## Prototype in your favorite harness, test and verify in the workbench

Graph's [built-in MCP server](/tools/mcp-server) brings the entire development tool set and execution runtime to your coding harness of choice.  Coupled with Graph's pre-built skills, your agent will have the tools it needs to quickly iterate on every workflow task you throw at it.  Once you're happy, open the plan in the [graph workbench](workbench) and run a full end-to-end test to make sure everything is running correctly.

## Where to go next

<CardGroup cols={2}>
  <Card title="Quick start" icon="rocket" href="/quickstart">
    Install, scaffold a project, run your first plan.
  </Card>

  <Card title="Core concepts" icon="lightbulb" href="/getting-started/concepts">
    Plans, the tool catalog, the shape cache, the workbench, and what a run costs.
  </Card>
</CardGroup>


## Related topics

- [File versions](/reference/file-versions.md)
- [MCP server](/building/mcp-server.md)
- [Quick start](/quickstart.md)
- [CLI](/reference/cli.md)
- [Installation](/getting-started/installation.md)