> ## 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.

![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.](https://mintcdn.com/graph/s-Ce0Orb66xMgIkN/images/workbench/hero.svg?fit=max\&auto=format\&n=s-Ce0Orb66xMgIkN\&q=85\&s=5e7b981b17c414bcbbc34e9631712241)

## 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/reference/tool-file/prompt) as a step (classify, extract, summarize mid-plan) and a [finish](/plans/reference/plan-file#param-finish) 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](/getting-started/models). 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](/integrating/mcp/guides/serve-over-mcp) 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](/getting-started/workbench) and run a full end-to-end test to make sure everything is running correctly.

## Where to go next

> **[Quick start](/quickstart)**
>
> Install, scaffold a project, run your first plan.

> **[Core concepts](/getting-started/concepts)**
>
> Plans, the tool catalog, the shape cache, the workbench, and what a run costs.


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.