Articles for people who
ship the stack
Original rewrites on React, Node.js, TypeScript and AI — practical notes from the same engineering practice behind our operator software. Article bodies are in English.
Tagged: OpenAI
OpenAI's Managed Agents API: Hosted Sandboxes vs Self-Hosted Execution
How OpenAI's managed agent harness works in public beta: hosted Linux workspaces, self-hosted exec servers, context compaction, tool search and subagents.
8 min readRunning the Same OpenAI Chat Loop Locally with Ollama
Run the same OpenAI chat loop locally with Ollama: point the OpenAI Python SDK at localhost and keep your code. No API key, no token bill, no data leaving.
4 min readUsing Codex in VS Code: Scope, Recovery Points and the Fixes for the Usual Stalls
Codex in VS Code without the usual stalls: install and sign-in, a first bounded agent task, cloud vs CLI, shared config, and fixes for WSL and approvals.
18 min readGemStuffer: How AI Agents Turned RubyGems and RubyDoc into an Attack Path
In 2026 OpenAI agents published 2,000+ gems, ran code on RubyDoc build servers and scraped UK government sites. What happened, why it counts, and how to harden builds.
7 min readAgents API, Full-Duplex Voice, SWE-2 and Copilot Auto Routing: The Week in AI Dev
OpenAI's managed Agents API and GPT-Live-1 voice layer, Cognition SWE-2 efficiency claims and Copilot Auto routing preferences, with practical notes on cost, security and evaluation.
7 min readA Mini RAG Pipeline in 90 Lines of Python: Retrieve, Augment, Generate
Build retrieval-augmented generation from scratch with embeddings, cosine similarity and a ranked list, then see where the toy version breaks at scale.
6 min readGPT-Live-1 Voice Agents: Sessions, Delegation Modes and Real Phone-Line Costs
A practical tour of OpenAI's full-duplex voice model: how a session runs, Responses versus client delegation, a worked cost estimate and the traps in the docs.
8 min readOpenAI Agents API: A Managed Codex Harness and What Teams Still Own
OpenAI's Agents API runs the Codex harness for you, with sessions, MCP tools, subagents and sandboxes. What your team still owns: verification, access, data.
7 min readCodex Plugin for Claude Code: Install, Configure, Avoid Review Loops
How to run Codex and Claude Code together: pick a host, install the official plugin, share AGENTS.md rules, use review and rescue commands, and cap the review loop.
17 min read
About these articles
Request a 24h estimate
Need the same stack in a production operator layer? Send the brief — estimate within 24 hours.