Build it with the people who’ll use it.
Engineers, PMs, and analysts work in one shared Builder Chat. Point at the preview, leave a comment, and turn feedback into a change.
How it works
Build together. With your own keys and security.
A walkthrough of Grafty, from the first prompt to an app the whole company can find: building together, using your own models, publishing to the catalog and keeping cost under control.
Collaboration
One prompt. The whole team.
Product, R&D and Finance work in the same Builder Chat. Everyone sees the plan, the build and each other's changes, and the agent builds one app instead of four.
- One shared thread per app: prompts, plan, build, test, all visible to the team
- Team notes: talk to teammates in the same thread; the AI doesn't read them
- Auto / Balanced model mode, governed by IT
Live preview
Point at it. Comment. Ship it.
Not everyone writes prompts. Click any element in the live preview to reference it in chat, or pin a comment on it, like Figma, but on a running app. Send to Builder turns the comment into a change, immediately.
- Select any element and reference it in a prompt
- Pinned comments with replies, Open/Resolved, team-only visibility
- Desktop, tablet and mobile previews, and every revision kept
Your keys, your data
You signed an enterprise AI agreement. Your app builder should use it.
On cloud AI builders, your prompts and code go through their servers under their model contract. Grafty runs inside your network and calls your models with your keys: your OpenAI or Anthropic enterprise agreement, your Azure or Bedrock endpoint, or a model running on your own hardware. We never see your data.
- Your OpenAI and Anthropic enterprise agreements: the preferred setup
- Azure and Bedrock-style enterprise endpoints, or fully local models
- Air-gapped licence available: no outbound connection at all
App catalog
Your company already built that. Now you can find it.
Every app published in Grafty lands in one searchable catalog. Search before you build, open what exists, and join its build chat instead of starting a duplicate. Permissions decide who sees what: open apps are visible to everyone, restricted ones only to the people they're shared with.
- Search, filter (All / Can edit / Public) and sort every published app
- Restricted apps stay invisible to everyone else
- IT finally sees every internal app that's running
Cost control
Every app has a price tag. IT sets the limits.
Grafty shows what every app costs, across everyone who worked on it, down to input, output and cached tokens. IT decides which models are approved, which are manual only and which are blocked, and sets a maximum price Auto will never exceed. The biggest saving isn't a cheaper model. It's building once instead of four times.
- Live spend per app, all contributors combined
- Models: Approved, Manual only or Blocked
- Auto limits: maximum input and output price per 1M tokens
- Budgets per user, project and team, enforced before the call
- 0% markup: you pay providers directly
0%
Markup on model usage
3
Budget scopes: user · project · team
100%
Limits enforced before the API call
Example scenario.
Example scenario
Estimate model spend on your own keys
Move the sliders to match your team. Your model provider bills you directly at its own prices, and Grafty adds no markup.
Estimated model spend per month
$433
≈ $17.33 per person, paid to your provider. Set budgets per user, project and team.
Illustrative only. Real cost depends on your models, prompts and provider prices. A change can be a new app or an edit to one.
MCP server
Build from any agent. Ship on your own network.
Your developers already live in Codex, Claude Code and Cursor. Grafty includes an MCP server, so any MCP client can work with your Grafty instance directly: pick up a teammate's comment, fix it, reply on the thread and publish, without leaving the editor. Sign-in follows the MCP authorization spec (2025-11-25).
- Read and reply to team comments, with the element each comment points at
- Create apps and request changes, then wait on or cancel the build
- Find apps, read their files and history, and use Team chat
- Check GitHub sync status and resync
- Preview first, then publish: Grafty returns a preview and a confirmation code, and nothing goes live until the agent sends that code back
Works with
- Codex
- Claude Code
- Claude custom connectors
- Gemini CLI
- VS Code
- Cursor
- Devin
- Pi
- any MCP client
From “we need a tool” to “here it is”
Start with a real problem.
Build something useful.
01
Describe the work.
Start with what your team needs to do. Bring the context, the requirements, and the people who know the process.
“Build a shared inventory dashboard. Highlight low stock and let us filter by region.”
02
Make it yours, together.
Review a running preview, point at what needs changing, and work with teammates in the same conversation.
03
Put it to work.
Publish on your own infrastructure. Give your team a tool they can find and use, then keep improving it.
Inside the Grafty builderShared chat + live preview
Useful for the team. Built for the company.
Build together.
Keep it in your company’s hands.
Visit the trust center Your own keys and security.
Use your own model endpoints and keys, and deploy Grafty on your infrastructure. Your team controls the environment.
Give good tools a home.
Publish to a searchable app catalog. Teammates can find what already exists, use it, or join the conversation to make it better.
Keep a clear view of the cost.
See model spend per app and set budgets by user, project, and team. You pay your model providers directly, with no Grafty token markup.