@gengdaJ: Genius! Use external Obsidian to permanently preserve Codex's important memories, so Codex won't forget key tasks! I have organized the content you need to send to your Codex into a super prompt: (Remember to specify the Vault path) Please help me configure Obsidian as Codex's cross-project…

X AI KOLs Timeline Tools

Summary

Introduces how to configure Obsidian as Codex's cross-project long-term memory repository, allowing Codex to persistently save important information and avoid forgetting.

Genius! Use external Obsidian to permanently preserve Codex's important memories, so Codex won't forget key tasks! I have organized the content you need to send to your Codex into a super prompt: (Remember to specify the Vault path) Please help me configure Obsidian as Codex's cross-project long-term memory repository. My Obsidian Vault path is: <your Obsidian Vault path> Please create a folder in this vault called: Codex记忆 (Codex Memories) The target structure is as follows: Codex记忆/ ├── AGENTS.md ├── TODO.md ├── agent/ │ └── open-loops.md ├── 项目/ (Projects) ├── 人物/ (People) ├── 工作流/ (Workflows) ├── 决策/ (Decisions) └── 素材/ (Materials) Please complete the following: 1. Create the above directories and base Markdown files. 2. Write the Codex memory usage rules in `Codex记忆/AGENTS.md`. 3. Append an "Obsidian Codex Memory" rule to Codex's global AGENTS.md or custom instructions, so that Codex will know this directory is the long-term memory repository in the future. 4. Do not modify any content in the global AGENTS.md unrelated to Obsidian Codex memory. 5. Do not save any sensitive information such as Cookies, Tokens, API Keys, passwords, verification codes, ID numbers, bank cards, or private contact details. 6. Do not write full chat logs into the memory repository; only save information that is long-term valid and will be used repeatedly in the future. 7. After completion, verify that the files are successfully created, and tell me which files were created and which global configuration file was modified. Please write the following rules into `Codex记忆/AGENTS.md`: # Codex Memory Usage Rules This folder is Codex's cross-project long-term memory repository. It resides inside the Obsidian vault. All content should be readable, editable, searchable, and diff-able Markdown. ## When to Read Before starting more important or longer-duration tasks, quickly browse this file and check the relevant directories based on the task type: - Project-related: `项目/` (Projects) - People, collaborators, user personas: `人物/` (People) - Reusable processes, commands, checklists: `工作流/` (Workflows) - Important choices, trade-offs, reasons: `决策/` (Decisions) - Reusable materials, templates, expressions: `素材/` (Materials) - Cross-project unclosed items: `TODO.md` and `agent/open-loops.md` ## When to Write Only write information that is long-term valid and will be used repeatedly in the future. Prioritize saving the following: - User's long-term preferences, clear boundaries, repeatedly emphasized work styles - Project stable paths, key commands, environment differences, release processes - Verified fault causes, fixes, troubleshooting sequences - Important decisions and their reasons - Cross-project to-dos, pending issues - Reusable article structures, script flows, research templates, prompts ## Do Not Write - Do not save full chat logs, running logs, temporary emotions, one-time intermediate processes - Do not save Cookies, Tokens, API Keys, passwords, verification codes, ID numbers, bank cards, private contact details - Do not copy third-party platform configurations, account credentials, or sensitive values from logs into here - Do not write low-value summaries just to "look like you have memory" ## How to Write - Prefer updating existing notes; create new ones only when no suitable note exists - Write only small, checkable Markdown sections each time - Use clear titles, dates, source tasks, and scope of applicability - Separate facts from inferences; avoid solidifying guesses as rules - If you find old memory is outdated, do not delete it directly; first mark it as "outdated" and explain why ## Closing Rules Before finishing an important task, perform a memory closeout: - Determine if there is any long-term valuable content that needs to be written - If so, update the corresponding file - Write unclosed items into `TODO.md` or `agent/open-loops.md` - In the final reply, briefly describe which memory files were changed Please append the following to Codex's global AGENTS.md or custom instructions: ## Obsidian Codex Memory Use this directory as the cross-project long-term memory repository: `<your Obsidian Vault path>/Codex记忆` Before starting more important or longer-duration tasks, quickly browse: `<your Obsidian Vault path>/Codex记忆/AGENTS.md` When you learn information that is long-term valid and will be used repeatedly in the future, update the relevant Markdown files in `<your Obsidian Vault path>/Codex记忆`. Focus on saving: project stable paths, key commands, user long-term preferences, clear boundaries, verified troubleshooting conclusions, important decisions, reusable workflows, cross-project unclosed items. Do not save full chat logs, do not write running logs, do not treat temporary processes as memories. Do not save Cookies, Tokens, API Keys, passwords, verification codes, ID numbers, bank cards, private contact details, and do not copy third-party platform configurations or sensitive values from logs into Obsidian memories. Writing rules: prefer updating existing notes; create new ones only when no suitable note exists. Write only small, checkable Markdown sections each time. Separate facts from inferences. When discovering old memory is outdated, do not delete it directly; first mark it as "outdated" and explain why. Before finishing an important task, do a memory closeout: judge whether any long-term valuable content needs to be written; if so, update the corresponding file; write unclosed items into `<your Obsidian Vault path>/Codex记忆/TODO.md` or `<your Obsidian Vault path>/Codex记忆/agent/open-loops.md`; in the final reply, briefly describe which memory files were changed.
Original Article
View Cached Full Text

Cached at: 05/23/26, 06:15 PM

Brilliant! Use external Obsidian to persistently store Codex’s important memories, so Codex never forgets key things!

I’ve organized what you need to send to Codex into a super prompt (remember to specify the Vault path):


Please help me configure Obsidian as Codex’s cross-project long-term memory.

My Obsidian Vault path is:
<your Obsidian Vault path>

Inside this vault, create a folder: Codex记忆

Target structure:

Codex记忆/
├── AGENTS.md
├── TODO.md
├── agent/
│   └── open-loops.md
├── 项目/
├── 人物/
├── 工作流/
├── 决策/
└── 素材/

Please complete the following:

  1. Create the above directories and base Markdown files.
  2. In Codex记忆/AGENTS.md, write the Codex memory usage rules.
  3. In Codex’s global AGENTS.md or custom instructions, append an “Obsidian Codex Memory” rule so that Codex will know this directory is its long-term memory.
  4. Do not modify any content in the global AGENTS.md that is unrelated to Obsidian Codex memory.
  5. Do not save any cookies, tokens, API keys, passwords, verification codes, ID numbers, bank cards, private contact information, or other sensitive data.
  6. Do not write entire chat logs into the memory; only save information that is long-term useful and will be referenced repeatedly.
  7. After completion, verify that the files were created successfully, and tell me which files were created and which global instruction file was modified.

Write the following rules into Codex记忆/AGENTS.md:

Codex Memory Usage Rules

This folder is Codex’s cross-project long-term memory. It sits inside an Obsidian vault, so all content should be readable, editable, searchable, and diff‑able Markdown.

When to Read

Before starting a significant or long‑running task, quickly scan this file and check the relevant subdirectory based on the task type:

  • Project-related: 项目/
  • People, collaborators, user personas: 人物/
  • Reusable workflows, commands, checklists: 工作流/
  • Important decisions, trade‑offs, rationale: 决策/
  • Reusable assets, templates, phrasing: 素材/
  • Cross‑project open items: TODO.md and agent/open-loops.md

When to Write

Write only when you learn something long‑term useful that will be referenced repeatedly. Prioritise saving:

  • User’s long‑term preferences, explicit boundaries, repeatedly emphasised work styles
  • Stable project paths, key commands, environment differences, release processes
  • Verified root causes, fixes, debugging sequences
  • Important decisions and the reasoning behind them
  • Cross‑project to‑dos and unresolved questions
  • Reusable article structures, script workflows, research templates, prompts

What NOT to Write

  • Do not save full chat logs, day‑to‑day logs, temporary emotions, or one‑off intermediate steps
  • Do not save cookies, tokens, API keys, passwords, verification codes, ID numbers, bank cards, private contact information
  • Do not copy third‑party platform configurations, account credentials, or sensitive values from logs into this folder
  • Do not write low‑value summaries just to “look like you have memory”

How to Write

  • Prefer updating existing notes; create new notes only when no suitable one exists
  • Write short, reviewable Markdown snippets each time
  • Use clear headings, dates, source task, and scope
  • Separate facts from inferences — avoid solidifying guesses as rules
  • If old memory becomes outdated, do not delete it directly; first mark it as “outdated” and explain why

Close‑out Rule

Before ending an important task, perform a memory close-out:

  • Determine whether any content with long‑term value needs to be recorded
  • If so, update the corresponding file
  • Unresolved items go into TODO.md or agent/open-loops.md
  • In the final reply, briefly state which memory files were changed

Append the following content to Codex’s global AGENTS.md or custom instructions:

Obsidian Codex Memory

Use this directory as a cross‑project long‑term memory:

<your Obsidian Vault path>/Codex记忆

Before starting a significant or long‑running task, quickly browse:

<your Obsidian Vault path>/Codex记忆/AGENTS.md

When you learn something long‑term useful that will be referenced repeatedly, update the relevant Markdown files inside <your Obsidian Vault path>/Codex记忆. Focus on saving: stable project paths, key commands, user’s long‑term preferences, explicit boundaries, verified debugging conclusions, important decisions, reusable workflows, and cross‑project open items.

Do not save full chat logs, day‑to‑day logs, one‑off intermediate steps, or treat temporary processes as memories. Do not save cookies, tokens, API keys, passwords, verification codes, ID numbers, bank cards, private contact information, or copy third‑party platform configurations or sensitive values from logs into Obsidian memory.

Writing rules: Prefer updating existing notes; create new notes only when no suitable one exists. Write short, reviewable Markdown snippets each time. Separate facts from inferences. If old memory becomes outdated, do not delete it directly; first mark it as “outdated” and explain why.

Before ending an important task, perform a memory close-out: determine whether any content with long‑term value needs to be recorded; if so, update the corresponding file; unresolved items go into <your Obsidian Vault path>/Codex记忆/TODO.md or <your Obsidian Vault path>/Codex记忆/agent/open-loops.md; in the final reply, briefly state which memory files were changed.

Dan McAteer (@daniel_mac8):
How to setup persistent Codex memory in Obsidian

  1. Copy the below prompt into Codex. The prompt instructs Codex to create the memory folders in Obsidian

  2. Copy the below custom instructions. They instruct Codex to use Obsidian Codex memory to save memories

That’s it!

Similar Articles

@Saccc_c: Codex Advanced Memory Techniques: Building Cross-Project Shared Memory with Obsidian Knowledge Base Basic configuration is two steps: 1. Copy the prompt from Figure 1 to Codex, letting it create a memory folder in Obsidian 2. Copy the instructions from Figure 2 and add them to the custom instructions in settings, as part of the global AGENTS.md…

X AI KOLs Following

Introduces how to use the Obsidian knowledge base to build cross-project shared memory for Codex, automatically depositing valuable context by copying prompts and global instructions.

@yanhua1010: For most people, Obsidian eventually becomes a beautifully organized filing cabinet. It stores a lot, but very little is actually used. This is because it is designed primarily for "input": clipping, organizing, tagging, and folders. However, a truly useful knowledge base should proactively push insights back to you every day. I created an auto-growing Obsidian knowledge base Demo: …

X AI KOLs Timeline

The author shares an automated Obsidian knowledge base Demo that, by integrating with Claude, delivers daily briefings and facilitates knowledge compounding, transforming passive storage into active insight.