Codex + GPT-6 Astra: Persistent Notes to Keep Context Across Windows
Melvin Vivas · X post · 2026-09-05 · Open on X
Topics: Prompt & Context Engineering, AI Agents, Tool Use & MCP, AI Dev Tools & Productivity · Level: intermediate
Summary
The creator shares a quoted announcement that Astra brings a new way for Codex to keep and retrieve context when the context window fills up. Instead of repeatedly squashing the history into one summary, Astra keeps notes across context windows so details that build up over a session aren't lost. This is a useful pattern for anyone managing context in long-running coding agents.
Key points
- When a context window fills, the usual approach is to compress the history into a single summary, and details are lost each time.
- With Astra, Codex keeps notes across context windows, so accumulated details survive without being repeatedly re-summarized.
- Takeaway for context engineering: long agent sessions benefit from external, persistent notes (a form of memory) rather than only rolling summaries.
- The post only quotes the announcement and points to a follow-up post. No setup steps are given.
Resources mentioned
- OpenAI Codex · tool · openai.com · paid · recommended by both Bashiri Smith & Melvin Vivas
OpenAI's coding agent. In the diagram it writes code, fixes review findings and drives the build loop. The creator also used it to make this video.
Also in: Developers moving from ChatGPT/Codex to Claude (Melvin Vivas on X · notes), Creator Opinion: Codex Is Still the Best at Computer Use (Melvin Vivas on X · notes), OpenAI Codex Ambassador applications are open (Melvin Vivas on X · notes), GPT-Live-1.1: Multilingual Voice Update for ChatGPT and Codex (Melvin Vivas on X · notes) and 264 more - GPT-6 Astra · tool · openai.com · paid
The model announced in the quoted launch post, pitched as the developer's most capable model for work, coding, science and cybersecurity, and able to operate a computer.
Also in: Glimpse: A Visual Reasoning Model That Uses a Visual Scratch Space (Melvin Vivas on X · notes), Is AI Getting Cheaper? How to Measure LLM Cost Per Task and Per Intelligence Level (Melvin Vivas on X · notes), GitHub Copilot Adds Intelligent Local Model Routing (Project HydraFusion) (Melvin Vivas on X · notes), Comparing Opus 5.5, GPT-6 Astra and Grok 4.7 on OpenRouter (Melvin Vivas on X · notes) and 55 more
Try this
- Read the creator's follow-up post for the actual Codex context-preservation tips.
More in Prompt & Context Engineering
- How to Prompt GPT-6 Astra in Codex: Simpler Instructions, Leaner AGENTS.md
- OpenAI Guide: Rethinking Skills and Prompts for GPT-6 Astra
- Codex Losing Task Context After Compaction
- MiniMax H3 Official Video Prompt Writing Guide
- Context Management in Coding Agents: /compact vs /clear vs /handoff
- Better Frontend UI from GLM 5.2 with a Design Skill in Claude Code