The Delegation
Design, run, and inspect Gemini multi-agent teams in a no-code 3D office.
- Source repo
- arturitu/the-delegation
- Stars
- ★ 735
- Last updated
- 7mo ago
- License
- NOASSERTION
- Primary language
- TypeScript
- FA score
- 45/100 · Major gaps
At a glance
- How it runs
- Works with
- Platform-specific
- Cost
- Free software; you pay for model usage
- Setup effort
- Low · running in minutes
- You'll need
- 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
- Website
- arturitu.github.io/the-delegation ↗ set on GitHub
- Maintenance
- No commits for 6+ monthslast commit 2026-04-04latest release v0.2.0 (2026-04-04)+0.6 ★/day over 7 days
- Source review
- 45/100 · Major gaps
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.
- 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.
- A creative developer designing an AI workflow can rearrange roles in Team Editor and assign Gemini models according to speed or reasoning needs.
- 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.
- An AI enthusiast who needs execution visibility can inspect an agent's mission, thoughts, history, action logs, and technical traces.
- 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 devOpen 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?
- 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.
- 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?
Why each dimension lost points
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.
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.
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.
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.
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.
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.
- 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.
Recent releases
Latest entries from the project's GitHub Releases. Notes are quoted from upstream as written, not rewritten or tested by FollowAgents.
-
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 ↗ -
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?
Can it use OpenAI or Anthropic models?
Can I run it locally?
Are outputs automatically approved?
Which port does The Delegation use?
Is The Delegation open source?
Is The Delegation safe to use?
Is The Delegation still maintained?
Who makes The Delegation?
What is The Delegation's official website?
Thanks — we use this to improve the page.