CodingHybridFreeActiveVerified on a mock· intermediate · ~30 min setup
Persistent Memory for Codex using Obsidian
Give Codex durable, searchable long-term memory backed by an Obsidian vault.
Run this workflow
See exactly what it produces before you build it.
Build this with your agent
One copy-paste hands Claude Code, Codex, or Cursor the full recipe, steps included, nothing to fetch.
Intended Use
Long-running coding sessions where Codex needs context from previous days, project conventions, prior decisions, accumulated knowledge.
Not for
- One-off tasks under 10 minutes
- Teams sharing a single agent
The Stack
Tested Against
codex@2026.05obsidian@1.7.xSide effects & data flow
- Network
- openai-codex-api.com
- Writes
- ~/vault/memory/
- Credentials
- CODEX_API_KEY
Data privacy
- openai ← code + memory notes (retention: per Codex policy)
Prerequisites
- Codex installed
- An Obsidian vault
- Node 20+
Steps
- 1
Create a memory vault
Make a dedicated Obsidian folder the agent reads and writes to as markdown.
mkdir -p ~/vault/memory && touch ~/vault/memory/MEMORY.md - 2
Configure Codex
Point Codex at MEMORY.md.
codex config set memory.path "~/vault/memory/MEMORY.md"
Eval, 1 fixture
Last passed: verified 1mo agobasic-write-readcontainstimeout 30s · max $0.05Expected:
vitest
Results
Context survives across sessions; ~40% fewer repeated explanations.
Did this work for you?
Our CI checks the setup runs. You tell us if the whole thing worked. Tell us straight.
Related workflows
- Self-host CodeWiki on private code: validate the config before you spend tokens
- Run GLM-5.2 for the bulk, escalate the hard turns to Opus 4.8
- codebase-memory-mcp: wire the knowledge graph, stop re-reading files
- OrcaRouter for coding: judge by passing tests, not by vibes
- Kilo Code: add an MCP tool and bind it to one mode
- Kilo Code: a mode that can only edit the files you let it
Liked this workflow?
Get new verified workflows in WebAfterAI, three issues a week (Tue, Thu, Sat).