I built a persistent context system for Claude Code using Obsidian.
The problem I was trying to solve was Claude starting new sessions without enough context from previous work.
The setup uses an Obsidian vault for persistent memory, journal entries, unfinished tasks, commands, skills and scripts. In a new session, Claude can locate the relevant files, recover the previous context, and continue from where I left off.
Repo: [https://github.com/seestack-dev/claude-obsidian-memory/](https://github.com/seestack-dev/claude-obsidian-memory/)
I also made a full walkthrough showing the setup and a session-recovery test: [https://youtu.be/gf8Bg71121c](https://youtu.be/gf8Bg71121c)
I built this myself, would be interested to hear how others are handling persistent context.
source & further reading
dev.to — original article
I Built a Snowflake RAG Assistant That Actually Works in Production
I built a persistent context system for Claude Code using Obsidian.
Google Search Console Adds Multimodal Reporting for Image-Led Search