The Demo OS is a single AgentOS application that exercises every feature in the Runtime section. Use it as a working reference when building your own.
git clone https://github.com/agno-agi/demo-os && cd demo-os
cp example.env .env # set OPENAI_API_KEY
docker compose up -d --build
http://localhost:8000.
What’s inside
| Type | Count | Examples |
|---|
| Agents | 14 | Helpdesk (HITL + guardrails), Approvals (compliance), Contacts (memory), Studio (multimodal), Reasoner (reasoning + fallback) |
| Teams | 4 | Pal (RAG), Dash (text-to-SQL), Research (4 team modes), Investment (7-agent committee) |
| Workflows | 5 | Morning Brief, AI Research, Content Pipeline, Repo Walkthrough, Support Triage |
Map: capability → demo
Each row points at the demo agent that exercises that capability.
| Capability | Demo agent | Page |
|---|
| Hybrid search RAG | Pal, Dash | RAG |
| MCP tool / context provider | MCP agent | MCP |
| Dependency injection | Injector | Context Providers |
| Persistent learning across sessions | Pal, Dash, Contacts, Investment | Learning |
| Knowledge base with chunking & reranking | Pal, Dash | Knowledge |
| Entity memory + user profile + session context | Contacts | Memory |
| Session state with agentic updates | Taskboard | Session State |
| HITL confirmation, user input, external execution | Helpdesk, Approvals, Feedback | Human-in-the-Loop |
| Multi-agent text-to-SQL with dual schema | Dash team | Text-to-SQL |
| Multi-agent investment committee with Gemini | Investment team | Investment |
Why a reference implementation matters
The docs explain what’s possible; Demo OS shows it running. When the docs say “you can wire pre-hooks for PII detection,” the Helpdesk agent shows the four-line config that does it. When the docs say “agents can update their own session state,” the Taskboard agent is a 30-line working example. Every page in this section links straight to the source.
Run it locally
git clone https://github.com/agno-agi/demo-os && cd demo-os
cp example.env .env # OPENAI_API_KEY required, others optional
docker compose up -d --build
# Load Dash's SaaS dataset and knowledge
docker exec -it demo-os-api python -m agents.dash.scripts.load_data
docker exec -it demo-os-api python -m agents.dash.scripts.load_knowledge
http://localhost:8000/health. Then open os.agno.com → Add OS → Local → http://localhost:8000.
Deploy it to Railway
railway login
./scripts/railway_up.sh
📷 Add screenshot: Demo OS connected to AgentOS UI showing the agent picker with all 14 agents listed.
Next
RAG → 
