Video Tutorials

Video walkthroughs for every major Sagewai feature. Follow along to go from zero to production deployment.

Getting Started

#TitleDurationWhat You'll Learn
1Sagewai in 5 Minutes: Your First AI Agent5 minInstall sagewai, create a 4-line agent with GPT-4o, add a custom tool with @tool, run it. Zero to working agent.
2Run AI Agents for Free with Ollama + Sagewai8 minInstall Ollama, pull llama3.1, create an agent with providers.ollama(). No API keys, no cloud costs, completely local.
3Sagewai vs LangChain vs CrewAI: Honest Comparison12 minSide-by-side feature comparison. Build the same research agent in all three frameworks. See what Sagewai does differently — cost control, fleet workers, local inference.

Core Features

#TitleDurationWhat You'll Learn
4Building a Research Agent with Memory10 minCreate an agent that remembers facts across conversations using GraphMemory. Watch the knowledge graph build in real-time as the agent learns.
5RAG in 10 Minutes: PDF Q&A with Context Engine10 minIngest a PDF document, ask questions about it, see retrieval in action with the @context directive. Demonstrate vector + graph hybrid search.
6Multi-Agent Workflows: Researcher, Analyst, Writer12 minBuild a 3-agent content pipeline with SequentialAgent. Watch data flow between agents and monitor execution in the admin panel.
7Sagewai Directives: The Prompt Preprocessor8 minDeep dive into @context, @memory, @agent:name(), @wf:name(), /tool, #model. See how directives transform prompts before they reach the LLM.
8Safety and Guardrails: PII, Hallucination, Budget Control10 minAdd PIIGuard, HallucinationGuard, and TokenBudgetGuard to an agent. Watch blocked responses, redacted PII, and budget enforcement in action.

Developer Tools

#TitleDurationWhat You'll Learn
9VS Code Extension: Faster Agent Development6 minInstall the Sagewai VS Code extension. Demo syntax highlighting for directives, use scaffold commands (New Agent, New Workflow, Add Tool), and code snippets in action.
10Using Sagewai from TypeScript, Go, and Rust10 minStart the harness proxy, connect from three languages using client wrappers. Same agent infrastructure, three ecosystems. See the unified API surface.
11MCP Server: Give Claude Code and Cursor Your Agent's Tools8 minCreate an MCP server with sagewai mcp serve, connect it to Claude Code and Cursor. Watch AI coding assistants use your custom tools.

Enterprise and Production

#TitleDurationWhat You'll Learn
12Fleet Architecture: Server + Workers Explained15 minFull architecture walkthrough. Deploy a server container, create enrollment keys, start 3 workers (CPU + GPU), submit tasks, and watch pool/label routing in action.
13Multi-Tenant Setup: Per-Team Isolation and Budgets10 minCreate 3 projects with different budgets and worker pools. See complete isolation — each team's spend, agents, and data fully separated on the same server.
14Zero-Cost AI: Fine-Tune with Unsloth, Serve with Ollama15 minFull pipeline: generate training data with GPT-4o, fine-tune with Unsloth (4-bit QLoRA), export to GGUF, serve via Ollama, harness auto-discovers it. $0/token inference forever.
15Production Kubernetes Deployment12 minDeploy Sagewai fleet on K8s: server Deployment, GPU worker DaemonSet with NVIDIA tolerations, HPA for CPU workers. Terraform and Pulumi templates. Monitoring with Grafana.
16CI/CD Agents: PR Summaries and Eval Quality Gates10 minAdd run-agent and run-evals GitHub Actions to a real repo. Demo a PR summary bot that comments on every PR and a quality gate that fails CI when agent performance drops.
17The LLM Harness: Proxy, Route, and Budget All AI Calls10 minPoint Claude Code and Cursor at the harness proxy. See complexity-based routing (Haiku for typos, Opus for architecture), per-team budgets, and the full audit trail.

Advanced

#TitleDurationWhat You'll Learn
18Durable Workflows: Temporal-like Execution in Python12 minBuild a workflow with ApprovalGate for human-in-the-loop review. Show PostgreSQL-backed checkpointing, worker crash recovery, and the dead letter queue.
19Self-Learning Agents: Improve Automatically from Usage10 minEnable auto-learn on an agent, show it storing successful interaction patterns over time. Demonstrate measurably improved responses as the agent learns from its conversations.
20Building a Full-Stack AI App with Sagewai20 minEnd-to-end: Python backend with FastAPI + Sagewai agents, Next.js frontend consuming the API, admin panel monitoring everything. The complete developer experience from code to production.

Recording Notes

Each video follows this structure:

  1. What we're building (30 seconds) — show the end result first
  2. Prerequisites (30 seconds) — what you need installed
  3. Live coding (main content) — build it step by step
  4. Run and demo (1-2 minutes) — show it working
  5. What's next (15 seconds) — link to the next video

All code from these videos is available in the sagewai/examples/ directory of the SDK.