Canvas Chat

LLM providers

API keys for chat and completion. Stored locally and sent directly to providers.

OpenAI API Key

Anthropic API Key

Google AI API Key

Groq API Key

GitHub Models PAT PAT with models:read scope. Create token

OpenRouter API Key Use openrouter/ models (e.g. openrouter/anthropic/claude-3.5-sonnet). Get API key

GitHub Copilot authentication Not authenticated

Uses device flow and stores tokens in this browser. Models look like github_copilot/gpt-4.

Search

Used for /search and research. If not set, DuckDuckGo is used.

Exa API key (web search) Get API key

Custom models

Add LiteLLM-compatible models for self-hosted or proxy endpoints.

Model ID * Format: provider/model-name (e.g. openai/my-model, ollama_chat/llama3.1) or openrouter/provider/model-name for OpenRouter (e.g. openrouter/minimax/minimax-m2.5)

Display Name Optional. Defaults to model ID if not specified.

Context Window

Base URL

LLM proxy

Configure a custom base URL to use your own LLM proxy (e.g., LiteLLM proxy, OpenRouter).

Base URL (optional) Leave empty to use default provider endpoints. Supports OpenAI-compatible APIs.

Keyboard shortcuts

Override default shortcuts. Click a row and press the new key, or use "Change" then press a key. Use "Reset to default" per row to restore.

Canvas

Pan and zoom (Ctrl+scroll or trackpad pinch).

Zoom sensitivity Lower = smaller steps per scroll; higher = larger steps. Middle (50) is default.

Features

Configure feature behavior.

Flashcard grading strictness Controls how strictly the AI grades your flashcard answers

Plugins

Credentials and options for installed plugins.

Getting Started

Type a message and press Enter to start a conversation
Click on a node to select it, then type to reply
Ctrl/Cmd + click to select multiple nodes
Drag the canvas to pan, scroll to zoom
Double-click empty space to fit all nodes in view

Keyboard Shortcuts

Customize in Settings → Shortcuts.

Slash Commands

`/note` text or URL	Create a note (supports PDF URLs)
`/search` query	Search the web with Exa AI
`/research` topic	Deep research with multiple sources
`/matrix` context	Create a comparison matrix
`/committee` question	Consult multiple LLMs and synthesize
`/factcheck` claims	Verify claims with web search
`/code`	Create Python code node (select CSV first)

Tips

Branching: Select text in a node to create a branch from that specific point
Semantic zoom: Zoom out to see node summaries instead of full content
Collapse nodes: Click the − button or press - to hide a node's children and reduce clutter
Context: The context budget bar shows how much of the model's context window is used
Tags: Use the 🏷️ button to organize nodes with colored tags
Stop generation: Click "⏹ Stop" on an AI response to stop and optionally continue later
PDF import: Click 📎 to upload a PDF, or drag & drop onto the canvas

Python Code

Preview

Canvas Chat

Tags

Settings

LLM providers

Search

Custom models

LLM proxy

Keyboard shortcuts

Canvas

Features

Plugins

GitHub Copilot Authentication

Sessions

Help

Getting Started

Keyboard Shortcuts

Slash Commands

Tips

Edit Content

Edit Title

Edit Code

Add Poll Option

Reset Poll Votes