Video tutorials

Each video builds something concrete, shows it running, and points to the next step. The code from every tutorial is in sagewai/examples/ so you can run it locally.

Getting started

#TitleDurationWhat you build
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.
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 minBuild the same research agent in all three frameworks. Side-by-side look at cost control, fleet workers, and local inference.

Core SDK features

#TitleDurationWhat you build
4Building a Research Agent with Memory10 minAn agent that remembers facts across conversations using GraphMemory. The knowledge graph builds as the agent runs.
5RAG in 10 Minutes: PDF Q&A with Context Engine10 minIngest a PDF, ask questions about it, watch retrieval work with the @context directive. Demonstrates vector + graph hybrid search.
6Multi-Agent Workflows: Researcher, Analyst, Writer12 minA 3-agent content pipeline with SequentialAgent. Data flows between agents; execution is visible in the admin panel.
7Sagewai Directives: The Prompt Preprocessor8 min@context, @memory, @agent:name(), @wf:name(), /tool, #model. Watch how directives transform a prompt before the LLM call.
8Safety and Guardrails: PII, Hallucination, Budget Control10 minAdd PIIGuard, HallucinationGuard, and TokenBudgetGuard to an agent. See blocked responses, redacted PII, and budget enforcement in action.

Developer tools

#TitleDurationWhat you build
9VS Code Extension: Faster Agent Development6 minInstall the Sagewai VS Code extension. Directive syntax highlighting, scaffold commands (New Agent, New Workflow, Add Tool), code snippets.
10Using Sagewai from TypeScript, Go, and Rust10 minStart the harness proxy, connect from three languages using client wrappers. Same agent infrastructure, three ecosystems.
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. AI coding assistants call your custom tools.

Enterprise and production

#TitleDurationWhat you build
12Fleet Architecture: Server + Workers Explained15 minDeploy a server container, create enrollment keys, start 3 workers (CPU + GPU), submit tasks, and watch pool/label routing.
13Multi-Tenant Setup: Per-Team Isolation and Budgets10 minCreate 3 projects with different budgets and worker pools. Each team's spend, agents, and data stay isolated on the same server.
14Zero-Cost AI: Fine-Tune with Unsloth, Serve with Ollama15 minGenerate 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.
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. A PR summary bot comments on every PR; a quality gate 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. Complexity-based routing (Haiku for typos, Opus for architecture), per-team budgets, full audit trail.

Advanced

#TitleDurationWhat you build
18Durable Workflows: Temporal-like Execution in Python12 minA workflow with ApprovalGate for human-in-the-loop review. PostgreSQL-backed checkpointing, worker crash recovery, and the dead letter queue.
19Self-Learning Agents: Improve Automatically from Usage10 minEnable auto-learn on an agent, watch it store successful interaction patterns. Response quality improves as the agent accumulates runs.
20Building a Full-Stack AI App with Sagewai20 minPython backend with FastAPI + Sagewai agents, Next.js frontend, admin panel monitoring everything. End-to-end from code to production.

Recording structure

Each video follows the same format:

  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 is in the sagewai/examples/ directory of the SDK.