diff --git a/integrations/overview.mdx b/integrations/overview.mdx index e005072..53c706a 100644 --- a/integrations/overview.mdx +++ b/integrations/overview.mdx @@ -1,7 +1,7 @@ --- -title: "Integrations: coding agents and MCP clients" +title: "Graphify for Claude Code, Cursor, VS Code, Codex" sidebarTitle: "Overview" -description: "See which coding agents and assistants connect to Graphify's hosted MCP server, which support the open-source skill, and which get always-on context." +description: "Connect Claude Code, Cursor, VS Code, Copilot, Codex, or Gemini CLI to Graphify over MCP, or install the open-source Graphify skill." keywords: ["coding agent integrations", "hosted mcp", "graphify cli skill", "which agent to connect"] surface: "both" hideFooterPagination: true @@ -10,7 +10,9 @@ icon: "layout-grid" import OfficialMcpSource from '/snippets/official-mcp-source.mdx'; -Every agent below can use Graphify. Start with **Graphify**: it answers from repositories you have indexed, through `https://api.graphify.com/mcp`, with no local build. **Graphify CLI**, the alternative for offline or self-hosted setups, installs the open-source `graphifyy` skill and builds the graph on your machine. See [Graphify vs Graphify CLI](/platform/graphify-vs-local) to choose. +Graphify is shared codebase context for agents and the people who work with them: a code graph, a wiki, memory, and pull request reviews. Connect [Claude Code](/integrations/claude-code), [Cursor](/integrations/cursor), [VS Code](/integrations/vscode), [Codex](/integrations/codex), and the other assistants below to the hosted MCP server, or install the Graphify CLI skill on a graph you build locally. + +**Graphify** answers from repositories you have indexed, through `https://api.graphify.com/mcp`, with no local build. **Graphify CLI** installs the open-source `graphifyy` skill and builds the graph on your machine. See [Graphify vs Graphify CLI](/platform/graphify-vs-local) to choose. @@ -61,7 +63,7 @@ You need a Graphify account. If you don't have one yet, you can create one for f
OpenAI

ChatGPT, Codex, and Dots

One OpenAI plugin. Install it once.

OpenClaw

OpenClaw

ClawHub package for the hosted server.

Vercel

Vercel

A project token, or a per-user Connect token.

-
AntigravityWindsurfCline

Other Cloud agents

Antigravity, Windsurf, Cline, Zed, and any other MCP client.

+
AntigravityWindsurfCline

Other agents

Antigravity, Windsurf, Cline, Zed, and any other MCP client.

## Graphify CLI @@ -90,6 +92,20 @@ The installer adds platform-specific files and may install hooks or instructions The [local MCP server](/open-source/mcp-server) exposes a graph that already exists on your machine as MCP tools. Use it with the skill or on its own. +## FAQ + +### Does Graphify work with Claude Code, Cursor, or VS Code? + +Yes. See [Claude Code](/integrations/claude-code), [Cursor](/integrations/cursor), and [VS Code and GitHub Copilot](/integrations/vscode). The table above lists every assistant on this page, including Codex, Gemini CLI, JetBrains, ChatGPT, OpenClaw, and Hermes. + +### Do I need Graphify CLI if I use hosted Graphify? + +No. Hosted Graphify is enough when you connect your agent over MCP and have an indexed repository. Use Graphify CLI when you want an offline or on-machine graph. + +### What is always-on context? + +It is what `graphify install` writes so the agent checks the graph before reading source, without being asked. Hooks never grant the agent new permissions. + ## Beyond coding agents diff --git a/integrations/vscode.mdx b/integrations/vscode.mdx index fa8d40b..3d99484 100644 --- a/integrations/vscode.mdx +++ b/integrations/vscode.mdx @@ -1,7 +1,7 @@ --- -title: "Graphify for VS Code and GitHub Copilot" +title: "Connect Graphify to VS Code and GitHub Copilot" sidebarTitle: "VS Code and GitHub Copilot" -description: "Connect VS Code and GitHub Copilot to Graphify's hosted MCP server with OAuth, or install the open-source Graphify skill and query a graph on your machine." +description: "Install the Graphify MCP extension for VS Code, or add https://api.graphify.com/mcp. You can also run the open-source Graphify skill on a local graph." keywords: ["vs code mcp", "github copilot", "graphify mcp extension", "vs code marketplace"] surface: "both" hideFooterPagination: true @@ -13,6 +13,10 @@ import HostedOrLocal from '/snippets/hosted-or-local.mdx'; + +This page is for VS Code and GitHub Copilot. Install the [Graphify MCP](https://marketplace.visualstudio.com/items?itemName=graphify-labs.graphify-mcp) extension for Copilot Chat, or use the Graphify CLI tab for Copilot CLI and a local graph. If you use Cursor, see [Graphify for Cursor](/integrations/cursor). + + @@ -26,7 +30,7 @@ One click: install the official **Graphify MCP** extension by Graphify Labs from ## Before you start -- VS Code 1.102 or later. +- VS Code 1.102 or later. If Graphify is not in **MCP: List Servers**, see [Troubleshooting](#troubleshooting). - An agent chat model available in VS Code. The extension does not include one. - A Graphify account. If you don't have one yet, you can create one for free while connecting. The Free plan needs no card. See [Plans and pricing](/platform/support/pricing). - At least one repository with the status **Indexed**. Connect a repository and wait for that status. See [Repositories and builds](/platform/repositories). diff --git a/llms.txt b/llms.txt index d9a3502..100b26f 100644 --- a/llms.txt +++ b/llms.txt @@ -93,8 +93,8 @@ Use for errors, rate limits, pricing, security, or moving from Graphify CLI to h Use only when the user wants open-source Graphify on their machine: install graphifyy, build a graph, or serve it over MCP. - [Graphify CLI: open-source code knowledge graph](https://docs.graphify.com/open-source/overview.md): Open-source Graphify, the graphifyy package, builds a deterministic code knowledge graph on your machine with no vector store or hosted service. -- [Quickstart: map a repository with the skill](https://docs.graphify.com/open-source/quickstart.md): Install the graphifyy package, add the Graphify skill to your coding agent, and build a knowledge graph of your repository with one command. -- [Install Graphify CLI with uv or pipx](https://docs.graphify.com/open-source/installation.md): Install graphify with uv or pipx on macOS, Linux, or Windows, upgrade it, and register the Graphify skill with your coding assistant. +- [Graphify skill: install graphifyy and run /graphify .](https://docs.graphify.com/open-source/quickstart.md): Install graphifyy, run graphify install to add the Graphify skill, then type /graphify . in your coding agent to map the repository. +- [Install graphifyy (Graphify CLI) with uv or pipx](https://docs.graphify.com/open-source/installation.md): Install the official graphifyy package with uv or pipx, fix PATH if graphify is missing, and register the Graphify skill. Or use hosted Graphify. - [CLI quickstart: build and query a code graph](https://docs.graphify.com/open-source/cli-quickstart.md): Build a code knowledge graph with graphify extract, then query it with query, path, explain, and god-nodes. No agent or API key needed. - [MCP server quickstart: serve your graph](https://docs.graphify.com/open-source/mcp-server.md): Run graphify-mcp over stdio for one agent or over streamable HTTP for a team, then call query_graph and nine other graph tools from any MCP client. - [Self-host the Graphify MCP server with Docker](https://docs.graphify.com/open-source/self-host.md): Build the open-source Graphify Docker image from source and run graphify-mcp over streamable HTTP so your whole team queries one graph. @@ -144,12 +144,12 @@ Use when Graphify CLI fails to install or build a graph. Use when connecting a specific coding agent. Each page has a Graphify tab and a Graphify CLI tab. -- [Integrations: coding agents and MCP clients](https://docs.graphify.com/integrations/overview.md): See which coding agents and assistants connect to Graphify's hosted MCP server, which support the open-source skill, and which get always-on context. +- [Graphify for Claude Code, Cursor, VS Code, Codex](https://docs.graphify.com/integrations/overview.md): Connect Claude Code, Cursor, VS Code, Copilot, Codex, or Gemini CLI to Graphify over MCP, or install the open-source Graphify skill. - [Graphify for Claude](https://docs.graphify.com/integrations/claude-ai.md): Connect Graphify from the Claude connectors directory. Create your Graphify account for free while connecting, then enable the connector per chat. - [Graphify for Claude Code](https://docs.graphify.com/integrations/claude-code.md): Connect Claude Code to Graphify with your Claude account or claude mcp add. Create your Graphify account for free while connecting. - [Graphify for Cursor](https://docs.graphify.com/integrations/cursor.md): Connect Cursor to Graphify's hosted MCP server with OAuth, or install the open-source Graphify skill and query a graph built on your machine. - [Graphify for Codex](https://docs.graphify.com/integrations/codex.md): Connect Codex to Graphify's MCP server with OAuth, or install the open-source Graphify skill. Create your Graphify account for free while connecting. -- [Graphify for VS Code and GitHub Copilot](https://docs.graphify.com/integrations/vscode.md): Connect VS Code and GitHub Copilot to Graphify's hosted MCP server with OAuth, or install the open-source Graphify skill and query a graph on your machine. +- [Connect Graphify to VS Code and GitHub Copilot](https://docs.graphify.com/integrations/vscode.md): Install the Graphify MCP extension for VS Code, or add https://api.graphify.com/mcp. You can also run the open-source Graphify skill on a local graph. - [Graphify for Gemini CLI](https://docs.graphify.com/integrations/gemini-cli.md): Connect Gemini CLI to Graphify's hosted MCP server with OAuth, or install the open-source Graphify skill and query a graph built on your machine. - [Graphify MCP for JetBrains](https://docs.graphify.com/integrations/jetbrains.md): Install the Graphify MCP plugin to connect JetBrains AI Assistant to your indexed repositories through hosted Graphify's MCP server. No API key to paste. diff --git a/open-source/installation.mdx b/open-source/installation.mdx index 9baf32f..f553826 100644 --- a/open-source/installation.mdx +++ b/open-source/installation.mdx @@ -1,7 +1,7 @@ --- -title: "Install Graphify CLI with uv or pipx" +title: "Install graphifyy (Graphify CLI) with uv or pipx" sidebarTitle: "Installation" -description: "Install graphify with uv or pipx on macOS, Linux, or Windows, upgrade it, and register the Graphify skill with your coding assistant." +description: "Install the official graphifyy package with uv or pipx, fix PATH if graphify is missing, and register the Graphify skill. Or use hosted Graphify." keywords: ["install graphifyy", "uv tool install", "pipx", "graphify install skill"] surface: "local" hideFooterPagination: true @@ -11,7 +11,7 @@ icon: "download" import TryCloudCard from '/snippets/try-cloud-card.mdx'; -Don't want to install anything? Graphify, the hosted product at app.graphify.com, indexes your GitHub repositories in the browser. We run it for you, so there's nothing to deploy. Start with the [Cloud quickstart](/platform/quickstart). +Don't want to install anything? Start with the [Graphify quickstart](/platform/quickstart). Graphify indexes your GitHub repositories in the browser and hosts the graph for you, so there's nothing to deploy. ## Prerequisites @@ -73,6 +73,8 @@ The macOS command is Homebrew. The Linux and Windows commands are uv's own insta The official PyPI package is `graphifyy`. Other similarly named packages are not the Graphify Labs package. +The package is `graphifyy`. The command you run is `graphify`. If your shell cannot find `graphify` after install, see [Command not found](#command-not-found). + ## Register the skill ```bash @@ -82,8 +84,6 @@ graphify install --platform codex The first command detects an assistant. The second targets one explicitly. Run the specific command for each assistant you use. -The package on PyPI is `graphifyy`. The command you run is `graphify`. - Open the assistant in a repository and send `/graphify .`. That message builds the graph for the folder. Follow [Your first knowledge graph](/open-source/quickstart) to read the output and ask a question. Use `--project` when you want the registration committed with a repository: @@ -122,11 +122,13 @@ Re-run registration for the assistants you use so their skill files match the pa ## Command not found +If `graphify` is not on your `PATH` after `uv tool install graphifyy`, run: + ```bash uv tool update-shell ``` -Then open a new terminal. With pipx, run `pipx ensurepath`. If an MCP client cannot find Graphify, use an absolute executable path in its configuration. +Then open a new terminal. With pipx, run `pipx ensurepath`. If an MCP client cannot find Graphify, use an absolute executable path in its configuration. More install failures are in [Troubleshooting](/open-source/troubleshooting). ## Remove a registration diff --git a/open-source/quickstart.mdx b/open-source/quickstart.mdx index 68fa2b8..278237f 100644 --- a/open-source/quickstart.mdx +++ b/open-source/quickstart.mdx @@ -1,18 +1,18 @@ --- -title: "Quickstart: map a repository with the skill" -sidebarTitle: "Quickstart (skill)" -description: "Install the graphifyy package, add the Graphify skill to your coding agent, and build a knowledge graph of your repository with one command." -keywords: ["graphify quickstart", "claude code skill", "graphifyy install", "code knowledge graph"] +title: "Graphify skill: install graphifyy and run /graphify ." +sidebarTitle: "Skill quickstart" +description: "Install graphifyy, run graphify install to add the Graphify skill, then type /graphify . in your coding agent to map the repository." +keywords: ["graphify skill", "graphify quickstart", "claude code skill", "graphifyy install", "code knowledge graph"] surface: "local" icon: "zap" --- import TryCloudCard from '/snippets/try-cloud-card.mdx'; -The fastest way to use open-source Graphify is as a skill inside your coding agent. You install it once, type `/graphify .`, and the agent builds the graph and reads `GRAPH_REPORT.md` before it answers questions about your code. +The Graphify skill lets your coding agent build and query a local knowledge graph of the repository. You install `graphifyy` once, type `/graphify .`, and the agent builds the graph and reads `GRAPH_REPORT.md` before it answers questions about your code. -**Use the skill when** you work in Claude Code, Codex, Cursor, Gemini CLI, or another agent that supports skills, and you want the agent to drive extraction for you. If you only want terminal commands, follow the [CLI quickstart](/open-source/cli-quickstart). +**Use this skill quickstart** to install `graphifyy` and run `/graphify .` in your coding agent. For a graph, wiki, memory, and pull request reviews hosted for you, start with the [Graphify quickstart](/platform/quickstart). If you only want terminal commands, follow the [CLI quickstart](/open-source/cli-quickstart). ## Before you start @@ -48,7 +48,7 @@ The fastest way to use open-source Graphify is as a skill inside your coding age - The package is `graphifyy` (two y's). It installs the `graphify` and `graphify-mcp` commands. + The package is `graphifyy` (two y's). It installs the `graphify` and `graphify-mcp` commands. If your shell cannot find `graphify`, see [Command not found](/open-source/installation#command-not-found). ```bash