the platform
Self-Hosted AI Agent Orchestration: A Full Tour
Clone the repo, bring the stack up, install a model, then build, run, and trace an agent — the full tour.
Walkthrough · 6:41
How to Deploy TheYgent to Kubernetes
What This Video Covers
Deploying TheYgent to Kubernetes — Minikube on a laptop in the video, any cluster in practice. Clone the repository and review the manifests under deploy/k8s; resources, volume sizes, and replicas are yours to change.
One make target builds the images, loads them into the cluster, applies the manifests, and waits for the rollout: the interface, control plane, inference plane, and durable worker deployments, plus Postgres as a StatefulSet. After port-forwarding, the first visit creates the admin account, and the planes report healthy. make k8s-down removes everything again.
Try It Yourself
More Walkthroughs
retrieval
Give Your LLM a Memory: RAG with File Upload and Web Crawl
Upload a PDF, crawl a docs site, and wire both into an agent as retrieval tools — no code.
voice
Voice In, Voice Out: A No-Code AI Agent Pipeline
Speech-to-text, a model, and text-to-speech wired on the canvas — a spoken conversation with an agent you built.
hybrid
Run Local and Remote AI Models in One Agent
A local model triages and handles the easy work; the hard question goes to a hosted API — one graph, each branch calling its own model.