Examples / Cookbook
Start with the complete multi-SDK implementation first, then use cookbooks for focused patterns. Full implementation page: Full-fledged support agent Then apply recipes in this order:01-quickstart-support-agent.py-> Support agent memory loop07-multi-agent-system.py-> Multi-agent shared state08-event-driven-agents.py-> Building event-driven agents09-branch-what-if.py-> Branching what-if simulations10-stateful-task-tree.py-> Stateful task trees
Framework integration examples
Complete example apps with real LLM calls showing MuBit integrated with popular agent frameworks:| Example | Framework | What it shows |
|---|---|---|
| Support Ticket Triage | CrewAI | 3-agent crew with handoffs, checkpoints, and outcome recording |
| Code Review Pipeline | LangGraph | StateGraph with conditional reviewer loop and MuBit store |
| Research Assistant | LangChain | Multi-turn conversation with cross-session memory |
| Travel Planner | Google ADK | SequentialAgent with Gemini tool calling |
| FAQ Bot | Vercel AI SDK | Middleware auto-injection with knowledge-base tool |
Failure modes and troubleshooting
| Symptom | Root cause | Fix |
|---|---|---|
| Recipes work alone but fail together | Run identity not carried between stages | Keep deterministic run IDs by role/task |
| Progression feels disconnected | Cookbook file order skipped | Follow stage order and reuse the same project folder |
Next steps
- Recheck foundations at How Mubit works.
- Use route-level references at Control HTTP reference.