@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…
Summary
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.
View Cached Full Text
Cached at: 05/25/26, 12:37 PM
Codex Advanced Memory Techniques: Building Cross-Project Shared Memory Using the Obsidian Knowledge Base
The basic setup is just two steps:
- Copy the prompt from Figure 1 into Codex to create a memory folder in Obsidian
- Copy the instructions from Figure 2 and add them to the custom instructions in Settings, as part of the global AGENTS.md, so that Codex can automatically precipitate valuable context into Obsidian in subsequent work
(Specific prompts and global rule instructions are in the comments; see the linked article for basic memory techniques and configuration)
- Prompt
Please create a folder named “Codex” in my Obsidian vault root directory [fill in your Obsidian vault root path] and set it as Codex’s persistent cross-project memory space.
Use the following structure:
Codex/ ├── TODO.md ├── AGENTS.md ├── people/ ├── projects/ ├── agent/ └── notes/
This memory system should follow these memory patterns:
The focus is not on saving the full chat history, but on serializing useful context into persistent Markdown files that are easy for me to browse, edit, compare, and reuse.
This Codex vault holds rolling context around my work:
- People
- Decisions
- Follow-ups
- Daily notes
- Project status
- Repetitive workflows
- Reusable ideas
- Useful background information that would otherwise be lost across conversation threads
Create Codex/AGENTS.md as the operating instructions for this vault.
In Codex/AGENTS.md, specify: When Codex learns persistent information about people, makes progress on projects, makes decisions, or processes follow-ups, it should update the relevant pages in this vault.
- Global Rule Instructions
Use my Obsidian Codex memory vault as persistent cross-project memory.
Memory vault root directory:
[your Obsidian vault path]/Codex
At the start of an important work session, quickly review:
[your Obsidian vault path]/Codex/AGENTS.md
When you learn persistent background information about people, projects, decisions, follow-ups, repetitive workflows, project status, or reusable ideas, update the corresponding Markdown files in this Codex memory vault.
The goal is not to save the chat history, but to serialize useful memories into files that I can browse, edit, compare, and reuse.
Do not dump conversation logs directly. Memory updates should be concise, specific, and verifiable.
Before ending an important work session, perform a memory wrap-up:
- Decide if there is anything worth persistently recording;
- If necessary, update the corresponding Codex memory files;
- Note which files were modified;
- Record any unresolved follow-ups in
TODO.mdoragent/open-loops.md.
Do not store keys, credentials, or sensitive private information.
- Configuration reference: Method used by Codex team members
You can try this
Codex’s Memories feature is a setting you must enable — it gives Codex proactive memory capability.
How to enable: Settings → Personalization → Memories → Enable Memories (Figure 1)
After enabling, once some time has passed, you can open the memory.md file under ~/.codex/memories/ to see the memory content Codex has added.
Figure 2 below shows my memory.md file — you can see that Codex has organized key information from the conversation history by topic, including my specific preferences, reusable knowledge, failure cases, and corresponding solutions.
Similar Articles
@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…
Introduces how to configure Obsidian as Codex's cross-project long-term memory repository, allowing Codex to persistently save important information and avoid forgetting.
@Luckyjudy666: 8 Tips to Make Codex Your Personal Assistant 1. Build a Shared Memory for Codex Core rules go in Agents.md, project background in Obsidian, repeated processes as skills, personal preferences and common questions in Memories. Otherwise, Codex is like a new colleague every time, having to explain everything from scratch...
This article shares 8 tips for using the Codex AI assistant effectively, including building shared memory, remote task execution, scheduled automation, file organization, and teaching new software operations, all aimed at improving work efficiency.
@daniel_mac8: How to setup persistent Codex memory in Obsidian 1. Copy the below prompt into Codex. The prompt instructs Codex to cre…
A guide on setting up persistent memory for Codex using Obsidian by copying a prompt and custom instructions for the AI assistant.
@Saccc_c: https://x.com/Saccc_c/status/2058396860784505295
This article introduces how to give Codex persistent memory by configuring the AGENTS.md and Memories features, thereby improving communication efficiency and operation security.
@Saccc_c: Codex's Memories feature is a setting you must enable; it gives Codex active memory. How to enable: Settings → Personalization → Memory → Enable Memory (Figure 1). After enabling and letting it run for some time, you can open memory.m...
Introduces Codex's Memories feature, which gives Codex active memory, along with instructions on how to enable it and how to view the memorized content.