REA (Reverse Engineer Anything) is an MCP server that connects coding agents such as Claude Code and Codex to reverse-engineering tools like Ghidra, IDA and JADX. It had 1,500 stars on October 4 and 275,000 on October 16. Reading its GitHub Discussions and Hacker News threads, the work people actually reported was mostly about software they already had: printing from a PC to a printer that only worked with a phone app, restoring old games, auditing their own services. What REA adds to earlier MCP servers is less an analysis engine than a record that attaches evidence and limitations to every conclusion. I read the repository and ran it against an Electron app I wrote and two npm packages, which surfaced what to know about output size and feature-trace accuracy. The showcases and an FPS-game decompilation project show that whether a result is right is decided by a separate check against the original. The post closes with the clean-room debate, an order for using it on your own project, and what package authors should move to the server and treat as their moat.

Most of the open source PRs I opened in the past were documentation translations. Reading an unfamiliar codebase, fixing a bug, and getting it through maintainer review felt out of reach in the few hours I had after work. Between April and October this year I opened 18 PRs across 10 repositories with Claude Code, and 3 of them were merged in opik, penpot, and haystack. Using my own PR history, this post covers how those three got through review, what the 10 closed PRs taught me about repository rules, and an order of steps for anyone who wants to make a first contribution with an agent.

Lauren Tan, a former Cursor engineer now building Grok Bot at SpaceXAI, says she merged 1,000 PRs to production in July and 2,462 in August. The story spread as 'she doesn't look at the code', but she answered that she reads what her agents land after the fact and turns what she finds into lints and structure. The job pre-merge human review used to do is split across three mechanisms: evidence from running the real app, a verdict from an agent that did not write the code, and a codebase where rules fail CI. I read the transcripts of two talks, her posts on X, and the code and 90-commit history of pstack, her open plugin, to see how each mechanism is built, and reproduced the patch-id rule that ties a verdict to a patch. After covering token usage and the numbers nobody has audited, the last section lays out the order in which a team on a normal budget could adopt this.

How do you engineer an LLM agent harness for a domain where wrong answers are expensive? Using Korea's ISMS-P (102 controls) as the vehicle, Claude Code reviews and audits through a domain-experts → interviewer → auditor pipeline. 10 reusable harness patterns + honest limits.

Public domain novel characters as AI agents. RAG + cognitive engine over the original text -- talk to Sherlock Holmes.

A native macOS meeting notes app. Real-time recording, automatic transcription, and AI-powered summaries -- all processed locally with on-device STT and LLM.