OpenClaw + Obsidian gives you super powers

From the creator

OpenClaw's memory is 100x better when you combine it with Obsidian. Here's how to do it. FULL OpenClaw/Obsidian bootcamp in the Vibe Coding Academy coming up: https://vibecodingacademy.dev Sign up for my free newsletter: https://www.alexfinn.ai/subscribe Follow my X: https://x.com/AlexFinn My $300k/yr AI app: https://www.creatorbuddy.io/ Prompt: I want to build an Obsidian memory system into OpenClaw. Here's how it will work: There are 4 layers, from smallest/always-present to largest/on-demand: LAYER 1: BUILT-IN MEMORY (~2,200 chars) ---------------------------------------- - Injected into every single prompt automatically - Tiny — just compact facts and pointers - Things like "Alex's name", "SSH into DGX with ssh spark", "vault is at X path" - Think of it as sticky notes on my monitor — always visible LAYER 2: AGENTS.md + SOUL.md ----------------------------- - Also injected every single prompt automatically - My operating instructions, personality, and hard rules - Includes the mandatory logging rules we just tightened - This is my "how to behave" layer LAYER 3: OBSIDIAN VAULT (the big one) -------------------------------------- - Location: iCloud Obsidian vault, shared with OpenClaw - NOT auto-injected — I read it on session start and during work - Three folders: Agent-Shared/ — both agents read/write user-profile.md — who you are, preferences, corrections project-state.md — all projects and their status decisions-log.md — shared decision history Agent-Hermes/ — my private workspace working-context.md — what I'm actively doing right now mistakes.md — things I've gotten wrong daily/ — daily logs (one file per day) Agent-OpenClaw/ — OpenClaw's space (I don't touch it) - I READ on: session start, after compaction, when I need details - I WRITE on: task start, every 3-5 tool calls, task completion, corrections LAYER 4: SESSION SEARCH ------------------------ - Searchable archive of every past conversation - I don't write to it — it's automatic - I query it when you reference past work or I need cross-session context - Last resort recall — "what did we do about X last week?" THE FLOW ======== New session starts | v Read vault (user-profile, project-state, working-context, today's log) | v Work on tasks — checkpoint to vault every 3-5 tool calls | v Task done — append to daily log, update working-context | v Compaction hits? — todo list survives, re-read vault after | v Session ends — flush everything to daily log Timestamps: 0:00 Intro 0:21 What the memory system is 2:32 How OpenClaw memory works 7:40 How to set it up 9:38 Personal knowledge wiki

Choose to Build with AI
Matched to AI Agents

AI Maker Residence 3

The third AI workshop taught by our legendary teacher, Nick Sarafa. This is a full-day hands-on training workshop for purposeful co-creation with AI using Claude Code. Imagine having access to hundreds of billions of dollars of computing power and knowing exactly how to make it work for you through the power of super intelligence.

◆ Fri 09 Oct 2026 ◆ KOKO Cafe, London ◆ With Nick Sarafa
AI Maker Residence 3
Live event
AI Maker Residence 3
Fri 09 Oct 2026

More like this

Running one yourself?

List your AI event,
wherever it is.

A meetup, a workshop, a hackathon, a conference. Any city, or online. Tell us about it and it lands in front of people already learning this stuff.