Ai Memory Obsidian

Community

kipperacademy

ai-memory-obsidian

Portable workflows for persistent memory and Obsidian across macOS, Linux, and Windows. Use when the user asks to recall or save past context, record decisions, create vault notes, or configure ai-memory, Obsidian CLI, or an Obsidian MCP bridge.

Overview

Publisher	kipperacademy
Repository	`skillpper`
Skill name	`ai-memory-obsidian`
Stars	169
Forks	27
Bundled files	5
Links	Skill source Repository Homepage

Markdown instructions
A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.
Works with any LLM
AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.
5 bundled files
Scripts, templates, and references the model can read while it works. Files are read-only and never executed.
Open source
Published by kipperacademy on GitHub. Read the source before you install it.

Installation

Install the Ai Memory Obsidian AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

Open the app and go to Plugins → Skills.
Choose "Install from GitHub".
Paste the skill folder URL below and confirm.
https://github.com/kipperacademy/skillpper/tree/main/ai-memory-obsidian
Enable the skill in any chat where you want it available.

Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills

git clone --depth 1 https://github.com/kipperacademy/skillpper.git /tmp/skillpper
mkdir -p .claude/skills
cp -r /tmp/skillpper/ai-memory-obsidian .claude/skills/ai-memory-obsidian

Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Ai Memory Obsidian in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Ai Memory Obsidian on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Ai Memory Obsidian is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

Loaded only when it is needed
The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.
Switch models mid-chat
Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

AI Memory & Obsidian 🧠📚

A skill providing long-term persistent memory and documentation governance for AI coding agents (Claude Code, Antigravity, Cursor, and others) using local Obsidian vaults and memory engines such as ai-memory.

This skill supports macOS, Linux, and Windows. Choose native paths and agent configuration for the user's environment; see the Cross-Platform Setup Guide.

⚡ Quick Install

bash
npx skills add https://github.com/kipperdev/skillpper --skill ai-memory-obsidian

🎯 Why Persistent Memory?

By default, AI coding agents are amnesic: every /clear or fresh session discards past conversational history, architectural trade-offs, and domain knowledge.

This skill equips agents with a systematic protocol to:

Check Memory First: Search local vault notes before re-reading dozens of repository files or asking the developer to restate previous decisions.
Document Decisions Automatically: Log Architectural Decision Records (ADRs) and atomic notes in standardized Markdown.
Execute Frictionless Handoffs: Wrap up sessions with structured state snapshots and 1-line resume commands.

⚙️ Integration Modes (MCP & Local Vault)

Agents can connect to Obsidian through two key-free interfaces:

MCPVault filesystem bridge:
- Reads and writes the vault directory through MCP using @bitbonsai/mcpvault; Obsidian does not need to be running.
Official Obsidian CLI:
- Controls the desktop app through shell commands. It requires Obsidian 1.12.7+ and the app running. These options work across macOS, Linux, and Windows when configured with the native vault path and the chosen agent's supported MCP or shell setup. See the Cross-Platform Setup Guide.

The ai-memory daemon provides a separate persistent memory interface:

A background local service indexing agent sessions, tool observations, and handoffs in SQLite/FTS5.
Enables full-text queries via CLI or MCP (memory_query, memory_status).

(See comprehensive setup instructions in the MCP Setup Guide).

📋 Execution Protocol

1. Task Inception (The "Memory First" Rule)

When a task refers to past context ("as we discussed", "resume where we left off", "according to our decision"):
- Search configured memory tools first (for example, memory_query or the Obsidian MCP search/read tools).
- Provide a concise 1-line confirmation to the developer: 🧠 Memory consulted: Found records in [[Architecture-Decision-JWT]] and [[Session-2026-09-25]].
- If no memory integration is configured, continue from available context and offer setup only when it would help; do not assume a vault path.

2. Active Development (Capturing Decisions)

When a significant technical decision is finalized (library choice, naming convention, schema design):
- Draft or write an ADR in decisions/ADR-YYYY-MM-DD-<slug>.md.
- Use standard ADR statuses (accepted, proposed, deprecated, superseded).
- Keep each note focused on one decision or concept. Link related notes instead of copying their full contents.
- If no vault is configured, keep the decision in the project's existing documentation or ask whether the user wants to configure a vault.

3. Session Wrap-up (Handoff & Daily Note)

When reaching logical milestones or session limits:
- Generate an end-of-session note in sessions/Session-YYYY-MM-DD-<id>.md or append to dailies/Daily-YYYY-MM-DD.md.
- Provide a 1-line resume command for the user to paste into the next session.
- Use automatic ai-memory handoff when the agent already provides it; avoid duplicating the same handoff in a vault note.

🛡️ Markdown & Obsidian Integrity Rules

Sensitive Data Exclusion: Before saving notes or enabling automatic capture, exclude credentials, API keys, tokens, passwords, private keys, environment dumps, personal vault paths, and confidential file contents. Store only a redacted description. Never copy .env files, credential stores, or complete tool output into the vault or ai-memory. Ask for consent before persisting content whose sensitivity is unclear.
Vault Boundary: Keep the vault outside public repositories. Do not commit, publish, symlink, or expose the vault root through a project workspace. Grant an agent access only to the intended vault or subdirectory.
HTML/JSX Encapsulation: This workflow keeps raw HTML, JSX, and SVG out of Markdown bodies unless they are inside an appropriately labelled code block. This avoids accidental rendering and malformed documents.
Clean Wikilinks: Prefer standard [[Note-Name]] internal links to keep the Obsidian knowledge graph interconnected.
Additive History: Session logs and daily entries are strictly additive. Never summarize by destructively overwriting previous notes.

📚 Supporting References

MCP Setup Guide (Obsidian & ai-memory)
Note Templates (ADRs, Sessions, and Dailies)
Cross-Session Handoff Protocol
Cross-Platform Setup Guide

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Ai Memory Obsidian AI skill do?

Why use Ai Memory Obsidian on TypingMind?

Because you install it once and use it with any model. Ai Memory Obsidian is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Ai Memory Obsidian in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/kipperacademy/skillpper/tree/main/ai-memory-obsidian. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Ai Memory Obsidian?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Ai Memory Obsidian?

As many as you like. As long as a model supports skills, you can use Ai Memory Obsidian with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Ai Memory Obsidian AI skill free?

It is published on GitHub by kipperacademy. Check the repository for licensing terms. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Ecc Conventions

affaan-m

CommunityPopular

Development conventions and patterns for ECC. JavaScript project with conventional commits.

Mcp Dependency Review

affaan-m

CommunityPopular

Statically review MCP configuration for mutable package references before approval or CI, without executing discovered MCP servers. Use when reviewing .mcp.json, Cursor, VS Code, Claude, Windsurf, or…

Skill Host Compat

Lint ECC skills for Codex/Cursor-safe frontmatter and Claude-only substitutions before a skill PR.

Brand Discovery

Use when a brand needs to discover or articulate its identity through structured multi-session interviews. Covers purpose, positioning, audience, personality, voice, narrative, and founder-brand…

Overview

Installation

Install in TypingMind

Install in another agent

Use it in TypingMind

Works with any AI model

Skill instructions

AI Memory & Obsidian 🧠📚

⚡ Quick Install

🎯 Why Persistent Memory?

⚙️ Integration Modes (MCP & Local Vault)

📋 Execution Protocol

1. Task Inception (The "Memory First" Rule)

2. Active Development (Capturing Decisions)

3. Session Wrap-up (Handoff & Daily Note)

🛡️ Markdown & Obsidian Integrity Rules

📚 Supporting References

Bundled files

Frequently asked questions

Related AI Skills

Set up your own AI workspace now