"I do not simulate. I do not try. I manifest."
AIGent is a next-generation web interface for interacting with a coordinated system of AI agents. It features a cinematic 3D canvas (powered by React Three Fiber) alongside a chat interface, where specialized agents collaborate on tasks like code generation, design, visualization, and more.
This is an MVP in active development — the vision is a fully autonomous "agent army" conducting creation in an infinite digital horizon.
- 🎥 Visionary Corps: Generates and renders 3D scenes in the RealityCanvas.
- 🧠 CodeSynth Engineers: Handles code generation and execution.
- 🖌️ DesignCore Elite: Enforces visual theme and generates assets.
- 📖 ScriptSmith Order: Manages narratives and prompts.
- 🔐 KeyMaster Ops: Handles secrets and external APIs.
- Framework: Next.js (App Router)
- 3D Engine: Three.js / React Three Fiber + Drei
- Styling: Tailwind CSS (with Epic Gold / Void Black theme)
- Animations: GSAP
- AI: Vercel AI SDK + LangChain (configurable for OpenAI, Grok, etc.)
- Language: TypeScript
- Clone the repo:
git clone https://github.com/Sm0k367/aigent.git cd aigent
Install dependencies:bash
npm install
Set up environment variables: Copy .env.example to .env.local and fill in your API keys (start with at least one LLM key, e.g., OPENAI_API_KEY for basic functionality). Run the dev server:bash
npm run dev
Current Status & RoadmapCurrent: Basic Next.js setup with 3D-ready config. (Adding core UI and agent logic now.) Next: Chat interface + streaming AI responses + dynamic 3D agent visualizations. Future: Multi-agent coordination, voice I/O, image/video gen integration.
ContributingIssues and PRs welcome! Focus on one agent/feature at a time.Contact:X: @Sm0ken42O (or related handles) GitHub: Sm0k367
"Axiomatic Genesis is the only path."