tldraw/tldraw-offline
A desktop app for using tldraw with local files.
What it solves
It provides a private, local-first whiteboard application that works without an internet connection, removing the need for accounts or servers while allowing users to save documents as portable files.
How it works
The app uses an infinite canvas for drawing, diagramming, and adding media. It saves documents in a native .tldraw format which includes the canvas, pages, and embedded scripts. It is designed to be compatible with coding agents that can inspect the canvas, modify it, and create scripts to add new behaviors to files.
Who it’s for
Users who need a local drawing and diagramming tool for privacy-conscious work, as well as developers and AI agent users who want a visual canvas that agents can programmatically interact with.
Highlights
- Local-first operation with no accounts or servers required.
- Cross-platform support for macOS, Windows, and Linux.
- Integration with coding agents like Claude Code and Codex to automate canvas changes.
- Portable
.tldraw files that store both content and custom document scripts.
Related
- Project
jsgrrchg/NeverWriteNeverWrite is a cross‑platform, local‑first desktop app that combines a Markdown‑centric editor, knowledge‑graph navigation, and chat sessions with multiple AI agents. It lets you edit documents, run AI‑generated suggestions, and review changes before they are saved, all while keeping your vault and data on your own machine.
- Project
hAcKlyc/MyAgentsMyAgents is an open‑source, local‑first desktop workbench for creating and orchestrating AI agents. It supports multiple LLM runtimes, a task scheduler, IM channel integration, and a private device‑to‑device network (AgentNet) for multi‑computer workflows, all under an AGPL‑v3 license.
- Project
LuqP2/Image-MetaHubA local-first AI image organizer and generative media library manager that indexes local folders to search and organize generations by prompt, metadata, and visual similarity.
- Project
nexu-io/open-designOpenDesign is a desktop‑first, Apache‑2.0‑licensed workspace that lets teams use any installed LLM coding agent (Claude, Codex, DeepSeek, etc.) to generate and iterate on design artefacts—web prototypes, slide decks, dashboards, images, and motion‑graphics videos. It ships with hundreds of design‑system packages and template libraries, supports 26+ agent CLIs via a simple plug‑in system, runs locally (macOS/Windows, source‑build for Linux), and can export results as HTML, PDF, PPTX, or MP4 via the open‑source HyperFrames engine.
- Project
Devin-AXIS/iPolloWorkiPolloWork is a local‑first, Electron‑based workbench that unifies multiple AI‑agent runtimes (OpenCode, Codex, DeepSeek Harness) into one collaborative UI for teams. It lets you manage agents, plugins, tasks and editable outputs (code, docs, designs, video) from a single workspace, with optional cloud integration for identity and hosted workers. Installers are provided for macOS, Windows and Linux; the source can be built with Node 22+, pnpm and Bun. The project is released under a source‑available license that permits personal use but requires permission for larger or commercial deployments.