One prompt.
Full control.
A native desktop app that turns a detailed project brief into a coordinated fleet of AI agents — with a live task graph so you see everything and miss nothing.
Works with OpenAI, Anthropic, Ollama, LM Studio, or any OpenAI-compatible endpoint. Bring the AI you already pay for.
You decide how much you're involved.
Configurable involvement levels let you choose your operating mode. From hands-on to fully autonomous.
Direct every step
Full manual control. Review every output, guide every decision, steer the work exactly where you want it to go.
Get pulled in at checkpoints
Agents work autonomously until they hit a blocker or checkpoint. The Decision Queue surfaces what needs your attention. Everything else runs.
Set the brief, check in when you want
Approve the plan and let the fleet execute. Continuation rules keep agents moving. Operate like a CEO of your projects, not a babysitter.
What it does
Not monitoring what happened.
Orchestrating what happens next.
Other tools watch your agents. The Construct coordinates them — plans the work, dispatches the briefs, manages dependencies, surfaces decisions, and keeps the project moving forward.
Orchestration
The differentiator.
Describe what you need. The system drafts a plan: which agents, what order, what dependencies. You approve before execution. You stay in control without doing the coordination manually.
The Terminal
See everything. Miss nothing.
Three zoom levels of visibility into your projects. The Task Graph shows a live directed dependency flow — gold glow on the lead node, green as tasks complete, lane-colored pulses on active work. Minimap, zoom, pan, lane filters. Click any node to see details and jump into the agent's conversation. Zoom out to Project View for a card grid across all your projects. Zoom out further to System View — your full agent fleet, provider health, and global stats. Mission control for everything you're running. Auto-refreshes every five seconds. The graph is alive.
Decision Queue
You will get pulled in. But only when it matters.
Agents work autonomously using configurable continuation rules — keyword detection, turn counting, involvement levels. The machine runs until it can't. When an agent hits BLOCKED or reaches a CHECKPOINT, a Decision Queue card appears. It tells you what's needed and why. You make the call, work resumes. No notification spam. No "here's what I'm going to do next" updates. Just the decisions that actually need a human. Get notified on mobile when you're away from the desk. Step in, decide, step out.
Context Meter + Wrap and Transfer
The context crash killer.
Every thread shows token usage in real time. You can see exactly how close you are to the edge — before the AI starts forgetting. When you're running hot, the Wrap and Transfer protocol packages your full session state — decisions made, work completed, open items, carry-forward context — and moves it losslessly into a new thread. No starting over. No "as I mentioned earlier." No lost momentum. This is the feature that saves projects other tools let die.
Project Intelligence
Ask your project a question.
The Architect sees everything your agents have found across every thread. Ask "what did the content team find about venue options?" and get a synthesized answer — not a link to a thread, an actual answer with context from across the entire project. For orchestrated projects, The Architect knows the plan, the task graph, and all agent findings. For manual projects, Morpheus provides cross-thread intelligence and pattern recognition. Every message gets fresh context — assembled in real time from your actual project data. A Context Inspector shows you exactly which threads were analyzed and how the token budget was allocated. Full transparency.
Autonomous Continuation
The machine runs until it can't.
When an agent hits a blocker or reaches a checkpoint, the Decision Queue surfaces a card. You make the call. Work continues. You will get pulled in — but only when it matters. What it promises: one prompt and you're in control.
5-Lane Framework
Structure that keeps agents coherent.
SYSTEM, BUILD, CONTENT, DESIGN, and OPS — with Operator, Tank, Link, Mouse, and Trinity as the default lineup. Every message lands in the right lane with the right project header.
Personality System
Make it yours.
A four-level personality slider: Off (corporate clean), Lite (a little warmth), Medium (the sweet spot), and There Is No Spoon (full Matrix flavor). 450+ UI strings that change based on your setting — from status messages to agent dispatch preambles to toast notifications. It's a small thing. But it makes the app feel like yours, not like another generic SaaS dashboard.
See it in action
Screenshots
Task Graph
Live dependency flow. Gold lead node, green completions, lane-colored active work.
Orchestration
You see the plan before anything runs. Approve, modify, or reject.
System View
Mission control for everything you're running.
5-Lane Sidebar
Every thread lands in the right lane. No tab juggling. No lost context.
Mobile Access
Check on running work from your phone. Decision Queue on the go.
How it works
From idea to structured execution in one session.
Desi runs a custom balloonscape business in Portland. She wanted to expand into a new concept — a Balloon Bar where customers build their own arrangements online, choose from DIY to full-service tiers, and get everything shipped or ready for pickup.
That's not a one-line prompt. That's a real business brief — pricing strategy, competitive positioning, brand extension questions, website platform decisions, fulfillment workflows, inventory tracking, and a launch plan.
The Construct's Architect parsed that brief into a dependency graph: seven tasks across five lanes. Research feeding into branding feeding into website design, with event planning and operations running in parallel.
Tank pulled double duty on pricing and website architecture. Trinity handled the business model and the 90-day launch playbook.
Link mapped the competitive landscape. Mouse built the visual merchandising system.
Desi watched the Terminal task graph light up as work moved through the pipeline.
Her reaction wasn't "cool tech." It was "wait — that's actually getting done?"
Within one session: synthesized venue research, brand direction, website structure, three-tier pricing model, and a launch timeline. Not finished. Structured. Ready for her to make decisions and push forward.
Pricing
Start free. Stay in control.
14-day free trial with full access. No credit card required. After your trial, you keep read-only access to your data — nothing is deleted. Export available anytime.
Founding Member
Same full access as Operator, permanently discounted. A thank-you to the people who believed early.
Operator
Everything in The Construct.
or $180/year (save 21%)
- ✓ Unlimited agents and sessions
- ✓ All 5 lanes: SYSTEM, BUILD, CONTENT, DESIGN, OPS
- ✓ Terminal: Task Graph, Project View, System View
- ✓ Orchestration with Architect plan generation
- ✓ Decision Queue
- ✓ Project Intelligence (Architect + Morpheus)
- ✓ Context Meter + Wrap and Transfer
- ✓ Skill System
- ✓ Personality System (4 levels)
- ✓ Mobile access via Tailscale
- ✓ Push notifications
- ✓ Gateway-agnostic (any OpenAI-compatible provider)
- ✓ Local data, AES-256 encryption
Nebuchadnezzar
For teams running shared agent fleets.
- ✓ Everything in Operator
- ✓ Shared agent configurations
- ✓ Team visibility and admin controls
- ✓ Centralized billing
FAQ
Questions before you jump in.
No. The Construct works with any OpenAI-compatible endpoint — OpenAI, Anthropic, Ollama, LM Studio, OpenClaw, or direct API keys. You bring whatever AI you already use. Claude models can also route through the Claude CLI if you have a Claude Max subscription.
Your data stays. You keep read-only access to your projects, threads, and history — nothing is deleted. You just can't run new agent sessions until you subscribe. Export is available anytime.
No. The Construct is a native desktop app. Your data lives in a local SQLite database on your machine. API keys are encrypted with AES-256. Nothing leaves your computer.
Yes. No contracts. Cancel from your account and you keep access through the end of your billing period.
Most AI dashboards monitor what already happened — they show logs, token usage, conversation history. The Construct orchestrates what happens next. It generates plans, dispatches agents to parallel threads, manages dependencies, surfaces decisions, and provides project-level intelligence across all your work. It's a control layer, not a viewing layer.
Reach out. We're happy to work something out for students and active open-source contributors.
Join the build.
Your AI is waiting for a manager.
You've got the models. You've got the ideas. You just need the orchestration layer that turns them into parallel execution with full visibility and control.
No spam. Just launch updates, early access, and the occasional field note from the build.