Using Obsidian as long-term memory to cut Claude Code token waste
s can use an as instead of loading large amounts of old every time. The workflow narrows information from an index, to a map of related notes, to the specific note that matters for the current task.
A local SQLite FTS5 helps find the right notes quickly, while old log files are archived automatically so the workspace does not keep growing with stale material. A CLAUDE.md protocol tells the agent how to look up information and what to bring into context.
The goal is to reduce token use while still giving the agent enough relevant memory to improve accuracy and debugging. The setup is packaged as a reusable template for other projects.
Key points
- Obsidian is used as for s.
- The agent moves from an index, to a note map, to specific notes instead of reading everything.
- SQLite FTS5 search helps retrieve relevant information from local notes.
- Old logs are archived automatically to avoid unnecessary context growth.
- CLAUDE.md defines the rules for how the agent finds and uses memory.