Skip to content
NEW Assistants are live — persistent AI coworkers, now in cross-host teams. Read the launch note →
The Agentic Development Environment

Every agent. Every machine.
One command center.

Run Claude Code, Codex, Gemini, and 35+ more across every machine you own — watched, steered, and approved from one end-to-end encrypted screen.

Closed beta · the local tier is free · runs on the agent subscriptions you already pay for
recorded from the real app
AES-256-GCM end-to-end 3 first-class adapters · 35+ via ACP desktop · CLI · browser · phone macOS · Windows · Linux · iOS · Android
Runs the agents you already run
Claude CodeOpenAI CodexGoogle Gemini GitHub CopilotCursorOpenCodeGrok Build
Compatibility, not a customer list. Claude Code, Codex, and Gemini ship as first-class adapters — 35+ more connect over the Agent Client Protocol.
The problem

You already run a fleet.
You just can't see it.

Claude Code in one terminal. Codex in another — that one on a box you SSH into to check. VS Code with files changing under it, and a chat app you paste code into because it can't see your repo. Four windows, zero shared state. The agent that finished an hour ago has been idle ever since. The one that needed an approval has been blocked since lunch. Nothing told you.

your setup today glueprint
← terminals, IDE, chat — none of them talkingdrag the handleevery session, every host, one screen →
Request early access
name and email — that's the whole form
ADE /eɪ·diː·iː/
agentic development environment · noun

The IDE was built for a human typing into one machine. The ADE is built for a human directing agents across all of them.

Files and tabsSessions and tiles
You type the codeYou direct the agents typing it
One machine, one seatEvery machine you own, from anywhere
Command center

Many sessions on screen.
Arranged like you mean it.

Tile sessions, terminals, editors, git worktrees, and assistants in a recursive split mosaic. Every tile carries a host, so one layout can reach across every machine you own.

  • Save named layouts, group them, pop a group out into its own OS window
  • Drag tiles between splits with edge-aware drop targeting
  • Same surface in the web portal — your cockpit follows your browser
Explore the Command Center
recorded from the real app
Sessions

Live agent runs
you can steer.

Watch every prompt, response, and tool call as it streams — from any device. Approve permissions inline and the run continues.

  • End-to-end encrypted event stream — drop offline and gap-fill catches you up
  • Inline permission approvals, with the diff
  • Resume the same session id from desktop, portal, or phone
More on sessions
recorded from the real app
Cross-host control

Type here.
It runs there.

Open a live terminal, editor, or git view on any machine you own, from any other. Keystrokes, file writes, and commit messages are AES-256-GCM encrypted before they leave your device.

  • A headless daemon — glueprint run — turns any Linux server, homelab box, or container into a first-class host
  • Managed by systemd or launchd, with a local health endpoint
  • Drop offline for a minute and the protocol backfills exactly the events you missed
Laptops sleep. Put the daemon on a box that doesn't — that's the point of the relay.
Run the headless daemon
recorded from the real app
Persistent assistants

A crew that's still there
in the morning.

Assistants keep a persona, a constitution, and a workspace on disk, with memory that survives restarts. Routines wake them on cron — nightly triage, standup prep — and if there's nothing to do, they go back to sleep without burning tokens.

  • Every fact they learn lands as a typed markdown file in a local git repo — inspectable, diffable, revertible
  • Daily journals plus long-term memory with an auto-rebuilt index
  • Claude Code sessions resume across restarts — context carries over for weeks
More on assistants
recorded from the real app
Governance

Routines run the night shift.
Governance keeps it boring.

Autonomy without guardrails is a pager incident. Glueprint enforces permission tiers, tool filters, token budgets, and quiet hours in the engine — per assistant, per team, per org.

  • Allow / Ask / Deny tiers layered org → host → team → assistant
  • Constitutions are files on disk — versioned, reviewable, diffable
  • Task flows are role-gated state machines, so an agent can't merge what a lead hasn't reviewed
  • Every action lands in the audit log
How governance works
recorded from the real app
The editor

The IDE didn't disappear.
It moved inside.

A real editor lives in the cockpit — review and fix agent output without alt-tabbing. Monaco panes with full LSP: diagnostics, go-to-definition, rename, code actions, format-on-save.

  • Node.js debugger wired end-to-end — breakpoints, call stack, stepping, launch.json
  • Task runner with problem matchers, straight from tasks.json
  • Full git suite: worktrees, 3-panel merge conflict resolver, commit graph with checkout, cherry-pick, revert
Tour the editor
recorded from the real app
Mobile · 12:42

The blocked agent
finds you.

Permission requests land on your phone with the actual diff — red lines out, green lines in. Allow, deny, or always-allow, and the session on your desk resumes.

  • Decryption happens on-device — the relay never sees the file
  • Watch live session streams from the train
  • iOS and Android, same encrypted protocol as desktop
What works on mobile
recorded from the real app
The trust boundary

We route your code.
We can't read it.

Your agents run on your machines. The relay routes sequence-numbered envelopes it cannot decrypt and stores only a wrapped key. On the free tier, nothing leaves your machine at all.

Glueprint relay diagram Four host daemons on the left send encrypted events to the central Glueprint relay, which streams them to four user clients on the right. MULTIPLE HOSTS Always connected MULTIPLE USERS Connect from anywhere Desktop App Local machine ONLINE Daemon (Local) Linux server · launchd ONLINE Daemon in Docker Container · k8s pod ONLINE Daemon (Cloud VM) AWS · GCP · Azure ONLINE Glueprint Orchestration & Relay End-to-end encrypted Access control & governance High availability & global scale User (Browser) Laptop · desktop VIEWING 4 HOSTS User (iPad) Tablet VIEWING 2 HOSTS User (Mobile) iOS · Android VIEWING 3 HOSTS AI Assistant Agentic mode · MCP VIEWING 1 HOST
Events & streams · forward flow Approvals & control · return flow
AES-256-GCM per message PBKDF2-SHA256 · 600,000 iterations AES-KW wrapped DEK key zeroed on disconnect gap-fill on reconnect
Read the security architecture →
Receipts

No testimonials yet.
Receipts instead.

We're early, so there's no logo wall on this page and no invented numbers. What there is: claims you can check.

R.01 · Native core

Rust, not Chromium. One native binary per platform — the engine is the same crate on desktop and headless.

R.02 · No tracking cookies

Zero cookies on this site. Analytics are anonymized, first-party, cookieless. Open devtools and count them.

R.03 · Live version

v1.0.0
fetched from the release feed by this page.

R.04 · Open formats

YAML, JSONL, markdown in ~/.glueprint. No export button needed — it's already your data.

R.05 · Encryption spec

AES-256-GCM · PBKDF2 600k · AES-KW. The exact key lifecycle is published. Read it →

R.06 · Signed updates

Ed25519 signatures on every release artifact, verified before install.

Where it sits

Not another coding agent.
The layer that runs all of them.

Cursor and Copilot are agents — Glueprint runs agents. The honest comparison is with your current orchestration layer: a row of terminal tabs and a tmux session you forgot about.

Capability
Glueprint
Raw CLIs + tmux
Cursor · Copilot
Claude Code, Codex, Gemini side by side
unified tiles
~ by hand
one vendor
Every session on every machine, one screen
live
ssh per box
Approvals on your phone, with the diff
iOS · Android
Assistants with on-disk, git-versioned memory
markdown + git
per-session
Budgets, quiet hours, role-gated task flows
engine-enforced
E2E-encrypted remote access
AES-256-GCM
~ your VPN

Glueprint launches the same CLIs you already use, with your existing config and subscriptions. The terminal is the engine — this is the cockpit.

Pricing

Free where it's local.
Paid where it's relayed.

The desktop app is in every plan, and Free includes status-only portal and mobile views. The full relay on paid plans adds live sessions, remote control, and headless CLI-daemon hosts. Your agents run on their own subscriptions or keys — no markup, no resold tokens. Downgrades never delete anything.

Free

$0
Local-only, forever. No card, no trial clock.
  • 1 host · 1 seat
  • All agents, tiles, IDE, git
  • Assistants with memory
  • Portal & mobile: status only
  • Community support
Request access
Most popular

Pro

$24/mo
Pay when it follows you out the door.
  • 2 hosts included · +$8 each, up to 10
  • Full cloud relay, E2E encrypted
  • Phone + browser control
  • 3 assistant teams
  • Email support
Request access

Team

$59/mo
10 people, a host each ≈ $239/mo — about $24 a head.
  • 4 hosts · +$10 each, up to 50
  • 2 seats · +$15 each, up to 10
  • 10 assistant teams
  • Org governance + audit logs
  • Priority support
Request access

Enterprise

$399/mo
For orgs that phrase questions as security reviews.
  • 20 hosts · 10 seats included
  • Unlimited hosts +$12 · seats +$20
  • 50 assistant teams
  • SSO / SAML + SCIM
  • Dedicated support
Request access
You pay when you want your agents reachable from anywhere.
CANCEL ANYTIME · DOWNGRADES BLOCK NEW CREATION, NEVER DELETE
Blunt questions

Asked plainly.
Answered the same way.

Does my code go to your servers?

No. Agents run on your machines. The relay forwards AES-256-GCM-encrypted envelopes and stores a wrapped key it cannot open. On the free tier the relay carries status updates only — session content never leaves your machine.

I already run Claude Code in a terminal.

Keep running it. Glueprint spawns the same CLI with your existing config and subscription — and adds what the terminal can't: tiling across hosts, approvals on your phone, schedules, memory.

Do agents keep working when my laptop closes?

On a laptop, they sleep when it does. Put the daemon on a server, a homelab box, or a container and the answer is yes — that's the point of the relay.

What's the lock-in?

Plain files. Config and sessions are YAML and JSONL in ~/.glueprint, memory is markdown in a git repo, and your projects stay ordinary git repos. Uninstall, and your workflow is exactly as it was.

Which agents work?

Claude Code, OpenAI Codex, and Google Gemini are first-class adapters. 35+ more — Amp, Cline, goose, OpenCode, Qwen Code — connect through the Agent Client Protocol.

Do I need a team?

No. It's useful solo on day one — one host, local, free. Shared boards, governance, and SSO are there when you grow into them.

Why a waitlist?

Glueprint is in closed beta. Invites go out in waves, and referrals move you up the list. Already hold a code? Register at portal.glueprint.ai.

What does free actually mean?

One host, one seat, forever — the full app locally, plus status-only views in the portal and on your phone. You pay when you want to watch and control your agents live from other machines.

Closed beta · invites rolling out

Your fleet is already flying.
Take the seat.

Request early access and we'll send an invite as the beta opens up. When it lands: install, point it at the agents you already run, and watch the board light up.

The local tier is free · no credit card · hello@glueprint.ai