The Delegation

Design, run, and inspect Gemini multi-agent teams in a no-code 3D office.

Stars
★ 735
Last updated
7mo ago
License
NOASSERTION
Primary language
TypeScript

At a glance

How it runs
Web appCLI
Works with
Platform-specific
Cost
Free software; you pay for model usage
Setup effort
Low · running in minutes
You'll need
npmGemini API keyShell / CLINetwork access
Typical use
An educator teaching multi-agent collaboration can use a predefined team and the 3D office to make roles, handoffs, and task flow visible in a lesson.
Not a fit if
  • Teams avoiding vendor lock-in; models and multimodal generation are Gemini-only
  • Commercial projects needing the 3D assets, which are CC BY-NC 4.0 non-commercial
Maintenance
No commits for 6+ monthslast commit 2026-04-04latest release v0.2.0 (2026-04-04)+0.6 ★/day over 7 days

What does this agent do, and when should you use it?

The Delegation is a no-code 3D environment for AI enthusiasts, educators, and creative developers exploring multi-agent collaboration. It combines a shared office rendered with Three.js WebGPU and TSL with a React Flow node editor for team structures and task flows. Users can start from six predefined industry-team templates, create teams, assign Gemini models to individual roles, and inspect flows through visualizers, logs, and an agent inspector. Agent teams can generate text, images, music, and video through the Gemini API, while the interface estimates token use and costs. A hosted full experience is linked, and the repository documents local development via npm; operating the simulation requires a user-supplied Gemini API key.

A user creates multi-agent designs in the React Flow-based Team Editor or begins with predefined teams such as Creative Agency, Film Studio, and PR Agency. Individual roles can be assigned different Gemini Models, and teams generate text, image output with Nano Banana, music with Lyria 3, and video with Veo 3.1. The Team Flow Visualizer shows hierarchy and task flows, while Kanban & Action Logs and Technical Logs expose progress, raw LLM traces, tool calls, and structured agent responses. The embodied layer uses Three.js WebGPU, a NavMesh, and three-pathfinding so NPCs navigate to and claim Points of Interest including desks, seats, and computers, transitioning among walking, sitting, working, and talking. In human-in-the-loop workflows, Simulated PR Reviews let the user review proposals, provide feedback, and merge tasks.

  1. An educator teaching multi-agent collaboration can use a predefined team and the 3D office to make roles, handoffs, and task flow visible in a lesson.
  2. A creative developer designing an AI workflow can rearrange roles in Team Editor and assign Gemini models according to speed or reasoning needs.
  3. A content team experimenting with role-based generation can have an agent team produce text, Nano Banana images, Lyria 3 music, or Veo 3.1 video.
  4. An AI enthusiast who needs execution visibility can inspect an agent's mission, thoughts, history, action logs, and technical traces.
  5. A team practicing human approval in an agent workflow can use PR-style workflows and Simulated PR Reviews to review, comment on, and merge proposals.

Key setup facts

Pulled from the install and usage notes below. The project README has the current values.

Ports
3000

How do you install or deploy this agent?

Obtain a Gemini API key first: the simulation requires BYOK. Clone or fork the repository, then run these commands in the repository directory:

npm install
npm run dev

Open the local URL printed by the terminal; the documented example is usually http://localhost:3000/the-delegation. The documentation does not specify the local API-key configuration mechanism, environment-variable name, Node.js version, or a production deployment procedure, so the key must be supplied through the interface or project configuration supported by the implementation.

How do you use this agent?

Start the development server, open the local app, and provide a Gemini API key to run the simulation. Choose a predefined team or create a node-based structure in Team Editor, assign Gemini Models to roles, and run the team flow. Use Team Flow Visualizer, Agent Inspector, Kanban & Action Logs, and Technical Logs to inspect activity. When a human-in-the-loop approval occurs, use Simulated PR Reviews to review the proposal, give feedback, or merge the task.

What are this agent's strengths and limitations?

Pros
  • It combines a React Flow team editor, live flow visualization, and a Three.js WebGPU office in one environment, making multi-agent coordination tangible.
  • Per-agent Gemini model assignment is paired with token and cost estimates plus visibility into raw LLM traces, tool calls, and structured responses.
  • It supports four output types—text, Nano Banana images, Lyria 3 music, and Veo 3.1 video—rather than limiting teams to text.
  • NavMesh-based NPC movement with three-pathfinding gives task state a spatial representation through desks, seats, and computers.
Limitations
  • Its core AI provider is the Gemini API and the full experience requires a user-provided Gemini API key, so it is not provider-agnostic.
  • Local documentation does not provide API-key setup details, environment-variable names, a Node.js version, or a production deployment process.
  • The roadmap still marks the space editor, long-term team memory, deeper embodied AI, and further architecture decoupling as unfinished.
  • Repository metadata is NOASSERTION while the documentation claims MIT code and CC BY-NC 4.0 3D assets; commercial adopters need to verify the applicable license scope.

How does this agent compare with similar options?

Key facts side by side with the most closely related agents.

Agent Source review Form / cost Stars Updated Language Full support on
The Delegation This agent 45 · Major gaps Web appFree + model costs ★ 735 7mo ago TypeScript —
Paper2Poster 50 · Major gaps CLIFree + model costs ★ 4.1k 10d ago Python Codex · OpenAI API
WorldX AI World Builder 52 · Major gaps Web appFree + model costs ★ 1.6k 1mo ago TypeScript OpenAI API
ReelMimic Style-Mimicking Video Studio 56 · Major gaps — ★ 2.1k 1d ago JavaScript Codex · Claude Code

How does FollowAgents rate this agent?

FollowAgents source review · FARS-2.1
Major gaps
45/ 100 5-point scale 2.3 / 5
Trust 13/29
Reliability 3/14
Adaptability 9/18
Convention 9/18
Effectiveness 7/13
Verifiability 4/8
Why each dimension lost points
Trust13 / 29 · 2.2/5

The README says users bring their own Gemini API key and describes human-in-the-loop approvals, an auto-approve option, and cost and token tracking. This supports some user control and visibility into external effects. Deductions: the packet does not explain key storage, request data flows, permission scope, rollback, or dependency security practices. Attribution is clear, but it does not verify publisher identity.

Reliability3 / 14 · 1.1/5

The README, package.json, and workflows align on the app name, version, and Vite build path. Deductions: workflows use npm install, while the packet provides no lockfile or dependency availability safeguards; it also shows no runtime error handling or failure messages.

Adaptability9 / 18 · 2.5/5

The README names AI enthusiasts, educators, and creative developers as audiences, and describes team templates, model selection, workflows, and local use. Deductions: it does not clearly bound simulated versus real agent capabilities or explain when the product is or is not suitable.

Convention9 / 18 · 2.5/5

The repository provides a structured README, installation steps, feature descriptions, a roadmap, and separate licensing terms for code and 3D assets; names and version are consistent in the packet. Deductions: there is no FAQ, limitations are sparse, version history is limited to a v0.2.0 overview, and attribution does not provide a continuing maintenance or update path.

Effectiveness7 / 13 · 2.7/5

The described node editor, preset teams, multimodal outputs, visible status, and logs suggest an interactive way to present multi-agent workflows in a 3D setting. Deductions: there are no sample outputs, usage results, or cost analysis to establish incremental value or whether benefits justify API costs.

Verifiability4 / 8 · 2.5/5

The README makes concrete feature and stack claims, while package.json and workflows support the app version, dependency types, and build/deploy path. Deductions: major feature claims lack code or example corroboration in this packet; product features are distinguished from roadmap items, but generation behavior and tracking accuracy are not independently substantiated.

Risks and how to mitigate them
  • Before use, determine where the Gemini API key is stored, what data is sent, and how to revoke or remove the key.
  • The README describes cost and token tracking, but the packet does not show its estimation method; actual API charges may differ from displayed values.
  • Code and 3D assets have different license terms; check each scope separately before commercial use.
Evidence confidence: Low Reviewed Nov 08, 2026 Reviewed revision 16c97c43d1c3
See the full review method →
Maintain this project? Add the FARS badge to your README

The badge shows the current review score and verdict and links back to this page. It refreshes about once an hour after a re-review.

FARS

[![FARS review](https://followagents.com/badge/the-delegation.svg)](https://followagents.com/en/agents/the-delegation)
<a href="https://followagents.com/en/agents/the-delegation"><img src="https://followagents.com/badge/the-delegation.svg" alt="FARS review"></a>

Recent releases

Latest entries from the project's GitHub Releases. Notes are quoted from upstream as written, not rewritten or tested by FollowAgents.

  1. v0.2.0
    Release notes excerpt
    Release v0.2.0 Features - Team Editor (React Flow): Design and visualize custom multi-agent collaboration patterns using a node-based interface. - Predefined Agentic Sets: 6 new industry-specific templates including Creative Agency, Nano Banana Lab (Visuals), Lyria Factory (Music), and Veo Studio (Video). - Multimodal Generation: Direct support for high-quality content generation: - Images with Nano Banana. - Music with Lyria 3. - Video with Veo 3.1 (720p/16:9). …
    View on GitHub ↗
  2. v0.1.0
    Release notes excerpt
    Release v0.1.0 Features - Agency Orchestration: Intelligent task management and coordination between multiple AI agents. - 3D Scene Manager: Dynamic handling of characters, props, and environment state using Three.js. - Character Controller: Realistic movement, pathfinding, and state machine-based animations. - LLM Integration: Support for Gemini via a unified factory pattern. - Interactive UI: Real-time project overview, kanban board, and agent task monitoring. …
    View on GitHub ↗

FAQ

Do I need a key or paid service to run it?
The full experience requires BYOK and specifically a Gemini API key. It displays token consumption and estimated costs, but no pricing is documented.
Can it use OpenAI or Anthropic models?
No such path is documented. The supplied material identifies the Gemini API as the core LLM provider and does not describe OpenAI or Anthropic adapters.
Can I run it locally?
Yes. The documented local workflow is npm install followed by npm run dev after cloning or forking the repository. Gemini API calls still require network access and your own key.
Are outputs automatically approved?
The project includes an Auto-approve output option and PR-style human-in-the-loop workflows. Users can review proposals, provide feedback, and merge tasks in Simulated PR Reviews.
Which port does The Delegation use?
The install notes on this page use port 3000 (for example http://localhost:3000). If the project lets you change the port, its README explains how.
Is The Delegation open source?
The source code is public on GitHub (arturitu/the-delegation), but the repository does not declare a recognised licence, so the rights to reuse or modify it are unclear. Ask the author or check the README before building on it.
Is The Delegation safe to use?
FollowAgents' FARS review (Nov 08, 2026) scored The Delegation 13/29 on trust and safety. None of the eight safety controls the review checks for was missing outright.
Is The Delegation still maintained?
The GitHub repository has had no commits since 2026-04-04, more than six months ago. That can mean the project is finished or abandoned; check its issues before relying on it. The latest release is v0.2.0 (2026-04-04).
Who makes The Delegation?
The Delegation is published on GitHub by the account arturitu. FollowAgents has not verified which person or company is behind that account.
What is The Delegation's official website?
The project's GitHub repository lists https://arturitu.github.io/the-delegation/ as its website. That link is set by the repository owner; the source code itself is on GitHub (arturitu/the-delegation).
Was this page helpful?
View on GitHub ↗ Install ↓

Related concepts