Workspaces

A place for every project.

Files, knowledge, contacts, monitors, and a publish button. Backed by a real folder on your disk — not a database you can’t open with another tool.

Project containers

A folder, with structure.

Every workspace is a folder. Every section is a subfolder. Every item is a file. You can open it in Finder, edit with another app, sync via your preferred tool, and Egg will pick up the changes.

Filesystem-backed

No proprietary database for project content. Open the folder anywhere — Finder, Explorer, terminal, another editor — and your data is there.

Visual or raw view

Toggle between the workspace UI and the raw file manager. Same data, different lens.

Sections = subfolders

Drag files into sections. Reorder by drag. Sections persist as folders on disk.

Items = files

Markdown, PDFs, images, videos, captured web pages, monitor reports, notes — whatever you drop in.

Add page from any tab

Right-click a tab or page → Add to Project. Captures URL, title, body, screenshot, capture timestamp.

Add link from anywhere

Right-click any link to add it to a project without navigating.

Knowledge engine

The agent reads your project.

Hit "Compile knowledge." The agent reads every file in the project and writes a synthesis to knowledge.md. Re-runs when you ask. Marks itself stale when monitors bring new data.

One-click compile

Run the knowledge skill from the project page. The agent reads every file, builds a synthesis, writes it back to the project as Markdown.

Staleness badge

When a monitor or new file changes the project, the knowledge view shows a "stale" badge so you know to re-run.

Project search

Keyword search across every text file in a project. Hits get inline previews with surrounding context.

Knowledge as artifact

The output is a Markdown file you can edit, version, copy, or share. Not a black-box vector store.

Monitors & automation

Set it. Forget it. Read the report.

Web monitors check URLs on a schedule, detect changes, and write reports straight into the project folder.

Interactive monitor creation

Visit a URL, point at what should be tracked, and the LLM derives the extraction logic. No JSON config.

Schedule

Set the interval — minutes, hourly, daily. Monitors run in the Gateway daemon, even when the app is closed.

Reports as files

Each detected change writes a Markdown report to project/monitors/ with the diff, timestamp, and source URL.

Notifications

Telegram, email, or system push when conditions match. Per-monitor channel routing.

Match conditions

"Notify when price drops below X." "Notify when stock changes." "Notify on any change." LLM-derived from natural language.

People

Contacts, with context.

Egg ships a CRM-grade contact system without acting like one. Every person you research becomes a profile — notes, memories, social links, work history, education, recent activity.

Profile extraction

Open any person’s page (LinkedIn, personal site, Twitter) and click Extract profile. Egg parses and saves a contact.

Notes & memories

Free-form notes and structured memories per contact. The agent surfaces them automatically when you mention the person.

Social links

LinkedIn, Twitter, GitHub, personal sites — tracked per contact and used as launch points for re-extraction.

Work & education timeline

Career and education history extracted automatically. Editable.

Tags

Flexible tagging for people and organizations. Filter contacts by tag.

Implicit, not explicit

You don’t "use" a CRM. Egg builds the contact graph as a side effect of normal browsing.

Publish

One project. One link.

Turn any project into a public canvas with a shareable URL. Edit in place. Copy the link. Unpublish when you’re done.

Dedicated Publish page

Lists every published canvas, with create-new, edit, copy-link, and unpublish actions.

Create from project or scratch

Start a canvas from an existing project or build one from a blank page.

Canvas editor

Inline rich-text editor with embedded artifacts, screenshots, and links. The same editor that backs project knowledge.

Public link

One click to copy. Anyone with the link can read. No account required to view.

Unpublish anytime

Pull the canvas off the public site without deleting it locally.

Agents that work for the project

Workspace agents.

Each workspace gets its own agent surface — specialized for discovery, research, organization, and monitoring inside that project.

Workspace agent

A dedicated agent rooted in one project. It knows the files, the contacts, the monitors, the knowledge state.

Agent cards

Skill loadouts per workspace agent. Toggle which skills apply to this project — research-only here, organize-only there.

InfiniteCanvas

The /agent route is a spatial canvas. Pin nodes (research questions, contacts, articles) and the agent walks the graph.

Add to Workspace tool

The agent itself can add files, contacts, and monitor outputs to the right project — routed by intent.

Communications

Direct messages, in the works.

P2P encrypted chat ships in the backend today. The UI is parked while we get the basics right.

Direct messages (backend)

Cloud-relay DMs over the same E2E-encrypted transport that powers sync. Phase 1 active in the daemon.

Backend only

Gmail integration

The agent has full Gmail access via Google Workspace tools. Standalone email UI is parked — for now, you read mail in Gmail and ask the agent to act.

Backend only

What’s next

Try it.

Free to download. Bring your own API key.

Download for Windows

Also available for macOS