Skip to main content

Documentation Index

Fetch the complete documentation index at: https://docs.chatgrid.ai/llms.txt

Use this file to discover all available pages before exploring further.

One sentence: ChatGrid is where your team’s project knowledge lives — YouTube videos, PDFs, docs, decisions — on a visual board that AI can search and answer from.

​
Get started in your IDE

Pick your tool. One config file. Done.

Claude Code

Add to .mcp.json — works instantly

Cursor

MCP config in settings — same setup

Windsurf

MCP config in settings — same setup
.mcp.json
{
  "chatgrid": {
    "command": "npx",
    "args": ["chatgrid-mcp"],
    "env": { "CHATGRID_API_KEY": "cgk_live_..." }
  }
}
Then talk to your AI naturally: 
> Create a ChatGrid board for the payments project
> Add this YouTube tutorial to the board: https://youtube.com/watch?v=...
> Upload this PDF to the board: /path/to/architecture.pdf
> Search the board for webhook verification
> What does our architecture doc say about rate limiting?

​
What can you add to a board?

Everything your team needs to remember. ChatGrid auto-processes each type.
Content typeWhat happensExample
YouTube videosThumbnail rendered, transcript extracted and vectorizedAdd this video: https://youtube.com/watch?v=abc
Websites / URLsPage scraped, content chunked and vectorizedAdd this blog post: https://vercel.com/blog/...
PDFsUploaded to storage, text extracted and vectorizedUpload this PDF: /path/to/spec.pdf
ImagesUploaded to storage, displayed on canvasUpload this diagram: /path/to/arch.png
Text / NotesDisplayed as sticky notes, vectorized for searchAdd a note: "We decided to use Stripe webhooks"
Every piece of content is automatically vectorized so AI can search and answer from it.

​
How it works

1

Create a board

One board per project. Takes 5 seconds.
2

Add knowledge

YouTube videos, PDFs, blog posts, architecture docs, decisions. Drop them in via MCP or the API. Everything is vectorized automatically.
3

AI answers from your sources

Ask questions. Get answers grounded in your actual content. Not hallucinated.

​
Why ChatGrid?

Your team’s knowledge dies in Slack threads and wikis nobody updates. Memory tools like claude-mem remember what one dev did. ChatGrid remembers what the whole team knows.
claude-memSlackWikiChatGrid
Who benefitsOne devTeam, temporarilyTeam, theoreticallyTeam, permanently
External knowledgeNoLinks that dieManual pagesYouTube, PDFs, URLs — auto-vectorized
AI can search itNoNoNoYes
VisualNoNoNoSpatial canvas

​
Quick start (API)

# 1. Create a board
curl -X POST https://api.chatgrid.ai/v1/boards \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"name": "My Project"}'

# 2. Add a YouTube video (creates a youtubeNode on the canvas)
curl -X POST https://api.chatgrid.ai/v1/boards/{boardId}/nodes \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"type": "youtube", "position": {"x": 0, "y": 0}, "data": {"url": "https://youtube.com/watch?v=abc", "label": "My Tutorial"}}'

# 3. Add a website (creates a websiteNode with auto-scraping)
curl -X POST https://api.chatgrid.ai/v1/boards/{boardId}/nodes \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"type": "url", "position": {"x": 400, "y": 0}, "data": {"url": "https://example.com/blog", "label": "Blog Post"}}'

# 4. Upload a PDF
curl -X POST https://api.chatgrid.ai/v1/boards/{boardId}/assets \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -F "file=@/path/to/document.pdf"

# 5. Search everything
curl -X POST https://api.chatgrid.ai/v1/boards/{boardId}/documents/search \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"query": "how does this work?"}'

​
Next steps

MCP Setup (2 min)

Add ChatGrid to your IDE

Use Cases

Onboarding, shared knowledge, learning

Quickstart

Build your first project board

API Reference

Full endpoint documentation