21K-star open-source course teaches harness engineering with 14 lectures and 8 hands-on projects
techNmak · x · 2026-10-28
A 21K+ star GitHub course, "Learn Harness Engineering," teaches how to build reliable AI coding agents from scratch. It offers 14 lectures, 8 hands-on projects, and 8 progressive phases under an MIT license, translated into 15 languages.
Its approach: instead of just teaching concepts, it gradually builds the engineering environment around an AI agent using one real application throughout, synthesizing OpenAI and Anthropic's harness engineering practices. Topics include agent instructions and repo structure, context management and persistent memory, multi-session continuity and task handoffs, task planning and scope control, testing and observability, automated coding loops with maker-checker workflows, and graph orchestration with parallel execution and rollback. Includes reusable templates and a harness-creator skill.
More from coding & agent
- VibeVideoBench: multimodal agents coding videos often fail on time management — Muxi Diao · 2026-10-28
- Dev builds open-source Excalidraw MCP after AI-generated diagrams kept overlapping text and arrows — pikahikmag · 2026-10-28
- DeepSeek vs Haiku pricing debunk: accounting for peak rates and token use, 1017 is 2-2.5x cheaper — teortaxesTex · 2026-10-28
- Viral screenshot shows an agent spawning 32 parallel workspaces in ~30 seconds — cephaloform · 2026-10-28
- Grok Bot 0.78.1 hides unreleased per-bot logins with manager-only team sharing — faraz0x · 2026-10-28
- Uber Built a Legal Redlining Agent for Its Lawyers—Here's What It Learned — AxSaucedo · 2026-10-28