AI Shipping Labs opens code for 10 workshops on agents, vLLM, and vector search
Al_Grigor · x · 2026-07-27
The author published the code for 10 AI Shipping Labs workshops, with each workshop including a working project, setup instructions, and session notes.
The public materials cover:
- end-to-end agent deployment with FastAPI, SSE, Docker, and a chat UI
- AWS Lambda deployment for a streaming FAQ agent
- an investment coach bot built on SEC EDGAR data
- serving open-source models with vLLM on rented GPUs
- vector search with SQLite, ONNX embeddings, Turso, and libSQL
- Cloudflare AI architecture comparisons using Workers, Workers AI, and Vectorize
- a Vercel FAQ agent that evolves through multiple storage and backend options
- cost-saving with Batch API and Flex processing
- an AI CV pipeline using YAML and headless Chrome
- a voice coach built with ElevenLabs
The repo is meant to be public and the detailed notes/recordings are available via paid plans.
More from coding & agent
- OMK open-sources a provider-neutral control plane for coding agents — DMAE1133 · 2026-07-27
- A vibe-coded Trevor Noah books page was rebuilt in Three.js with pure math — xiaohu · 2026-07-27
- A 435-paper survey says LLM agents still underbuild rollback, audit, and recovery — rohanpaul_ai · 2026-07-27
- A finance agent can read accounts through MCP, but payments are still manual — 3lonStarl1nk · 2026-07-27
- Observer builds local agents that watch your screen, mic, and camera for alerts — alex_verem · 2026-07-27
- Loops vs. graphs for agents: when to let the model choose the path — alex_verem · 2026-07-27