MAB (Plan)
SAB1 (Research)
SAB2 (Strategy)
SAB3 (Content)

Campaign Mode

Platform: All
🧠
Hello! I'm NeuroDesk's Main Agent Brain. Tell me about your marketing goal and I'll orchestrate a team of specialized agents to create a comprehensive campaign for you.
MAB Just now
Activity Stream 00:00:00
Just now
🧠 MAB: System initialized
🔍
Hello! I'm SAB1, the Market Research Analyst. Ask me to research competitors, audience insights, market trends, or any data you need for your marketing campaign.
SAB1 Just now
Agent Info
SAB1
Market Research Analyst
Idle
Provider
Ollama
Model
llama3:8b
Tools
serper_search, website_scraper
📊
Hello! I'm SAB2, the Marketing Strategy Specialist. I'll create a comprehensive 30-day content strategy based on the research findings.
SAB2 Just now
Agent Info
SAB2
Strategy Specialist
Idle
Provider
Ollama
Model
llama3:8b
✍️
Hello! I'm SAB3, the Senior Copywriter. I'll create ready-to-publish marketing content based on the research and strategy.
SAB3 Just now
Agent Info
SAB3
Senior Copywriter
Idle
Provider
Ollama
Model
llama3:8b

Settings

Configure agents, pre-instructions, and API keys

System Configuration
Global Engine Settings
Demo Mode Active

When enabled, agents will use real LLM inference and live tools instead of mock demo data.

MAB - Main Agent Brain
Orchestrator & Manager
Active
SAB1 - Research Analyst
Market Research
Idle
SAB2 - Strategy Specialist
Content Strategy
Idle
SAB3 - Content Writer
Copywriting
Idle

Tool Registry

Name Status Assigned to Actions
serper_search Installed SAB1
website_scraper Not Installed SAB1, SAB2

Performance Dashboard

Real-time AMD GPU inference metrics and benchmark comparison.

Total Requests
0
All-time requests
Avg Tokens/sec
0
Throughput metric
AMD Requests
0
GPU-accelerated
Avg Latency
0 ms
Response time

Latency Over Time

Benchmark Results

Provider Model Latency (ms) TPS GPU
No benchmark data yet. Click "Run Benchmark" to start.

Performance Summary

Last Updated Never
Demo Mode Enabled

About NeuroDesk AMD

Powered by AMD Developer Cloud.

🚀 Powered by AMD MI300X

NeuroDesk leverages AMD Developer Cloud with MI300X GPUs for high-performance LLM inference.

AMD Cloud (vLLM)

Open-source models served on AMD GPUs via vLLM

Recommended

Hugging Face Compatible

Deploy as Hugging Face Space with public-safe mode

ROCm Ready

Optimized for ROCm stack on AMD GPUs

Supported Model Endpoints

  • Qwen2.5 Instruct - Qwen/Qwen2.5-7B-Instruct
  • Llama 3.1 Instruct - meta-llama/Llama-3.1-8B-Instruct
  • Mistral Instruct - mistralai/Mistral-7B-Instruct
  • DeepSeek Instruct - deepseek-ai/DeepSeek-V2.5

Getting Started

  1. Sign up for AMD Developer Cloud
  2. Create a VM with AMD MI300X
  3. Install vLLM or SGLang for OpenAI-compatible endpoint
  4. Configure your model endpoint and API key in Settings

Session History

View and resume your past campaigns.