YOUR KNOWLEDGE. EVERY WORKSPACE.

Switch your AI.
Keep your context.

The decisions you made in Claude belong in Cursor, too. Save project knowledge to Webcraw. Ask your next AI tool to pick it up.

Free to startYou choose what to save
One project. Two AI tools.Interactive example
Planning
Y

Save this project context to Webcraw.

This demo stays in this page. No account or AI connection is used.

01 / THE HANDOFF Save in one tool. Retrieve in another. Try it above.

One shared memory.
Your choice of tools.
Claude/Cursor/Claude Code
Connect through remote MCP

THE CONTEXT TAX

You already explained it.
Then you switched tools.

Architecture choices. Naming conventions. The reason you ruled something out. Useful knowledge gets stranded in conversations, right when you need it somewhere else.

STARTING OVER
Claude · Monday

“Let’s use PostgreSQL. Here’s why…”

Cursor · Tuesday

“A little context before we start…”

The same explanation. Another conversation.

CARRYING IT FORWARD
Atlas / project contextSHARED

PostgreSQL for persistence.
UTC for timestamps.
Review before deployment.

Save from ClaudeRead in Cursor

One place for the knowledge you choose to keep.

A SMALL HABIT. A BETTER HANDOFF.

Save. Switch. Pick up.

Open the quickstart
01

Connect your tools

Add Webcraw through MCP. Authorize each AI tool for the same workspace.

Claude + Cursor → Webcraw
02

Save what matters

Ask your AI to store a decision, preference, or brief. Check the saved result.

“Save our Atlas project context.”
03

Ask for it elsewhere

Start in your next tool. Read the project context before continuing the work.

“Read Atlas from Webcraw.”

Explicit by design: you ask to save, retrieve, and update. Your full conversations stay where they are.

MORE THAN A CHAT TO REMEMBER

Keep what moves
the project forward.

Small, useful pieces of knowledge.
Ready for the next conversation.

DECISIONS

The what. And the why.

Keep architecture choices and constraints close to the work, including the reasoning behind them.

Database: PostgreSQLReason: relational reportingConstraint: no schema changes this sprint
PREFERENCES

Your way of working.

Carry writing style, naming conventions, and review expectations from one assistant to another.

Use descriptive variable namesExplain the tradeoffsKeep customer-facing copy concise
HANDOFFS

A place to pick up.

Save the state of the work so your next session starts with the open questions and next steps.

Done: signup implementationOpen: email provider choiceNext: verify mobile signup

FROM THE DEMO TO YOUR DESK

Make your first handoff.

Connection steps, exact prompts,
and a result you can verify.

START WITH SHARED CONTEXT

Try the whole handoff.
On the free plan.

Save, retrieve, and update knowledge.
Upgrade when you need more capacity.

Free

START HERE

$0/ month

Make your first handoff. Keep a project’s context across tools.

Start with shared context
  • Shared context through MCP
  • Up to 500 knowledge nodes
  • 150 MCP requests per 5 hours
  • 10 reusable scripts
  • Basic AI model · 15 messages per 5 hours
  • Community support

Pro

$5/ month

More room for your knowledge, with tools for recurring work.

Create an account
  • Shared context through MCP
  • Higher knowledge & script limits
  • 1,000 MCP requests per 5 hours
  • Scheduled tasks
  • Advanced AI model
  • Priority sandbox execution & email support

Enterprise

Let’s talk

Deployment and controls shaped around your organization.

Discuss your requirements
  • Self-hosted deployment
  • Custom access controls
  • Encryption key management
  • Audit compliance & SLA options
  • Software customizations
  • Licensed access to source code

Your AI client may have its own subscription or connector requirements. Webcraw plans cover the Webcraw service.

A FEW GOOD QUESTIONS

Know what
you’re connecting.

Need a hand with setup?

Talk to the builder
Does Webcraw automatically sync my conversations?

No. You ask your connected AI tool to save selected knowledge to Webcraw and to retrieve it when needed. Full chat histories are not imported, and a new conversation does not automatically load your saved context.

What should I save?

Start with a small project brief: important decisions, constraints, working preferences, and next steps. Give it a clear project name. Ask your AI to update the existing brief as decisions change.

How does another tool find my context?

Connect both tools to the same Webcraw account and workspace. Ask the second tool to read the project by name. Webcraw’s overview tool helps your AI discover saved knowledge. The quickstart includes exact prompts and troubleshooting.

Where is the knowledge stored?

Knowledge saved through the hosted service is stored in your Webcraw workspace. Connected clients can read or change it through MCP within their authorized permissions. Review the knowledge you want to make available before saving it.

Can I try shared context on the free plan?

Yes. The free plan includes shared context through MCP, up to 500 knowledge nodes, and 150 MCP requests per five hours. The Claude-to-Cursor tutorial fits within these limits and does not need scheduled tasks.

What happens when a decision changes?

Ask your AI to read and update the existing project knowledge, preserving unrelated details. In the other tool, ask for a fresh read. A conversation may still contain an older copy until you retrieve the updated version.

ALSO IN WEBCRAWShared knowledge is the starting point.

Code & scripts

Run Python and JavaScript in cloud sandboxes and keep reusable scripts alongside project knowledge.

Scheduled work

Use Pro to schedule recurring tasks and put saved scripts to work.

Interactive apps

Build dashboards and forms for MCP clients that support embedded apps.

TAKE YOUR KNOWLEDGE WITH YOU

Your next conversation
can start further along.

One project brief. Two connected tools.
Try your first real handoff.