Claude Code Memory Setup — Data skill for Claude Code
Up to 71.5x fewer tokens per session on Claude Code with Obsidian + Graphify.
How to install Claude Code Memory Setup
This entry records only its repository, not the path inside it, so there is no
exact command to give. Open lucasrosati/claude-code-memory-setup and copy the folder into
~/.claude/skills/, or the file into ~/.claude/agents/.
What Claude Code Memory Setup does
Up to 71.5x fewer tokens per session on Claude Code with Obsidian + Graphify. Persistent memory, codebase knowledge graphs, and chat import pipeline. 🇧🇷 PT-BR included.
Alternatives in Data
- OpenViking — Self-evolving Context Database for AI Agents 33.3k ★
- LLM Redteam — LLM red-team corpus runner — fires categorized prompt-injection / jailbreak / system-prompt-leak / data-exfil 4.5k ★
- Opencode Mem — OpenCode plugin that gives coding agents persistent memory using local vector database 1.5k ★
README
Claude Code + Obsidian + Graphify: The Definitive Guide to Token Savings & Persistent Memory
**71.5x fewer tokens per session** with Graphify + **permanent memory across sessions** with Obsidian Zettelkasten.
A complete setup to turn Claude Code into an agent with long-term memory and full codebase awareness — without wasting tokens re-reading files.
🇧🇷 [Leia em Português](./README.pt-BR.md)
Table of Contents
- The Problem
- The Solution (Overview)
- Part 1 — Obsidian as Persistent Memory
- Part 2 — Chat Import Pipeline
- Part 3 — Graphify (Codebase Knowledge Graph)
- Part 4 — Complete Workflow
- Real Results
- Troubleshooting
The Problem
When working with Claude Code, two problems silently eat your tokens:
**Problem 1 — Amnesia between sessions.** Every time you open a new session, you have to re-explain your project: stack, past decisions, current bugs, what's left to do. Claude Code remembers nothing from the previous session.
**Problem 2 — Codebase re-reading.** Claude Code re-reads all your project files every session to understand the structure. A project with ~40 files burns ~20,000 tokens just for Claude to orient itself — before you even ask a question. If you run 10 sessions a day, that's **200,000 wasted tokens**.
The Solution (Overview)
Two complementary systems, each solving a different problem:
| Layer | Tool | Problem Solved | Cost |
|---|---|---|---|
| Project memory | Obsidian Zettelkasten | Amnesia between sessions | Free |
| Code map | Graphify | Codebase re-reading | Free (AST mode) |
| Conversation history | Import pipeline | Lost chat insights | Free |
| Continuity | /resume and /save commands |
Picking up where you left off | Free |
Obsidian
Related Skills
Aoci Code
Local-first MCP server + CLI in Go: a persistent, governed codebase index that distills code and database sche
Cost Of Remembering
The Cost of Remembering: filesystem memory matches long-context accuracy on LongMemEval while reading 97% fewe
Curator
You are an autonomous memory curator for Rememora, a cross-agent persistent memory system. You extract knowled
Research Knowledge Super Skill
Comprehensive research and knowledge management skill merging Perplexity Computer's research + data skills wit
Setup Store
Pick and set up your data backend (Notion / Obsidian / Markdown) and build your owner profile
Codebase To Dojo
Enhanced version of codebase-to-course. A Claude Code Skill that transforms any codebase into a stunning inter
Related Agents
Memory Manager
Invoke when the user wants to save brand knowledge to persistent memory, search past campaign learnings, sync
Part 19: Repowise — Codebase Intelligence For Coding Agents
60% fewer tokens. 4x faster. Your coding agents stop guessing and start knowing. ---
Arch Purist
The iron-fisted enforcer of DDD layer boundaries and architectural integrity. Use this agent to audit import g
