Awesome list for AI agent harness engineering: tools, patterns, evals, memory, MCP, permissions, observability, and orchestration.
Python agent-harnessagent-memoryagent-orchestrationai-agent-harnessai-agentsawesome-listcontext-engineeringharness-engineeringmcp
Add Mitchell Hashimoto 'My AI Adoption Journey' (coined 'harness engineering', Feb 2026) to Foundations
ai-boostec1e1b7fa130
diff --git a/README.md b/README.mdindex 8fe9aa4..1cf72bc 100644--- a/README.md+++ b/README.md@@ -63,6 +63,7 @@ This list focuses on the *harness*, not the model. Every component here exists bCanonical essays that define what harness engineering is and why it matters.+- [My AI Adoption Journey](https://mitchellh.com/writing/my-ai-adoption-journey) — The essay that coined "harness engineering" (February 2026): Mitchell Hashimoto's six-stage adoption path culminates in engineering the harness itself — every agent mistake becomes a permanent fix, whether an AGENTS.md line or a purpose-built tool, so the error class never recurs. The Ghostty numbers (commits needing correction dropping from 40% to 3% over three months of accumulated harness fixes) are the founding empirical argument that the harness, not the prompt, is the reliability surface.- [Harness Engineering](https://openai.com/index/harness-engineering/) — OpenAI's framing of harness engineering as a discipline: how to design the scaffolding that lets Codex and similar agents operate reliably in an agent-first world.- [Unrolling the Codex Agent Loop](https://openai.com/index/unrolling-the-codex-agent-loop/) — OpenAI's detailed breakdown of the Codex agent loop, exposing each harness component and where it can be improved.- [Run Long-Horizon Tasks with Codex](https://developers.openai.com/blog/run-long-horizon-tasks-with-codex/) — OpenAI's practice guide for long-horizon task planning: introduces Plan.md, Implement.md, Documentation.md as reusable harness artifacts.