okikusan-public / articles / Turning Obsidian into AI's Own Memory — Local Cognitive OS with Hindsight and Hermes
JA EN
← articles
CONTENTS5 sections
  1. 01What 23.4 tokens/sec Really Means
  2. 02Hindsight's Self-Referential Loop
  3. 03Obsidian as AI's Own Memory
  4. 04Tacit Knowledge to Explicit
  5. 05Cognitive OS
OBSIDIAN / HERMES / 2026

Turning Obsidian into AI's Own Memory — Local Cognitive OS with Hindsight and Hermes

It started with a single offhand remark from a developer: "I don't want Obsidian to be just a note-taking tool. I want it to become the long-term memory system for AI itself."

Ollama + Hindsight + PostgreSQL + Obsidian. Every process completes locally; the entire history of thought stays closed inside one's own machine. An experiment in how deeply an AI can understand context when constrained to "never leak externally."

Obsidian Hermes Agent Hindsight Ollama Local AI Second Brain 2026.05.23 · 7 min read
▍ THE PROMISE

This is not merely a combination of tools. It may be the emergence of a new layer where the infrastructure audits itself and humans and AI mutually extend each other's cognition.

▍ PREREQUISITES — The four terms used throughout

This article assumes the following background. If any of these are unfamiliar, read this first to avoid getting lost.

▍ TL;DR
§ 01 SPEED

What 23.4 tokens/sec Really Means for 'Being Local'

When running Gemma3 (or equivalent Gemma4-class model) on Ollama, the benchmark shows 23.4 tokens/sec. In an era of cloud dependency, this is not merely "tolerable speed" but "daily usable speed."

What matters is not the speed itself. It is the fact that every process completes locally. Raw conversation logs accumulated in daily-chats/ are instantly summarized by the LLM, structured by Hindsight, and persisted into PostgreSQL. No external APIs participate in this flow at all.

In other words, the entire history of thought remains closed inside one's own machine. This is more than privacy protection. It is an experiment in how deeply an AI can understand user context when constrained by the rule "never leak externally."

Related: For Hermes itself — the self-improving loop and resident execution — see "Hermes Agent — Execution engine of the second brain". This article wires that into Hindsight × local LLM.

FIG.0 — SYSTEM ARCHITECTURE & INFRASTRUCTURE
Local infrastructure diagram: Hindsight + Hermes + Ollama + PostgreSQL + Obsidian
Ollama + Hindsight + PostgreSQL + Obsidian. All processing stays local; raw logs from daily-chats/ are structured into AI's long-term memory.
§ 02 FEEDBACK

Hindsight's Self-Referential Infrastructure

What stands out most is Hindsight's role.

Conventional RAG stops at "retrieve and answer." Hindsight is different. It repeatedly summarizes past summaries, accumulating meta-metadata from summaries of summaries. The vector and metadata layers etched into PostgreSQL gradually self-organize over time.

This is precisely "infrastructure self-auditing."

The foundation is now in place for the AI itself to periodically verify these questions. There is no need to wait for external human reviewers. The system relativizes itself and proposes corrections — such a loop may already be beginning to turn, entirely locally.

FIG.2 — HINDSIGHT SELF-REFERENTIAL FEEDBACK LOOP
// HINDSIGHT = a self-referential loop that compounds summaries USER daily dialogue dialogue ▍ HERMES CLI / gateway ▍ Hindsight self-referential feedback loop Raw chat log daily-chats/ Summarizer Ollama 23.4 t/s Conversation summary daily/YYYYMMDD MOC / INDEX knowledge/ on session end periodic scan extract todos human review reload context // Everything local, everything persistent, everything self-referential.
Dialogue between User and Hermes flows into daily-chats/, gets summarized via Ollama, promoted into MOC, and returns to Hermes as context. A loop that compounds summaries of summaries.
§ 03 MEMORY

The Ultimate Human-AI Co-Creation: 'Making Obsidian the Memory'

What excites me most is not the tech stack, but the underlying idea.

The developer did not stop at treating Obsidian as a "second brain." They redefined it as "the primary memory device for AI." daily-chats/ is no longer a graveyard of miscellaneous logs. Every piece of text accumulated there is structured through Hindsight and functions as AI's long-term memory.

This is not a relationship where humans ask AI to "remember this for me."
It is a relationship where humans design the environment itself: "I'll write it here, so you go ahead and structure it on your own."

AI only becomes intelligent within the context it is given. The core of this pipeline may lie in the reversed idea that humans prepare the field to transform context into "persistent, searchable, and self-referential memory."

Related: A pipeline that stops treating Obsidian as just a "second brain" and lets AI grow a wiki and publish it externally is covered in "Obsidian → LLM Wiki → HTML → AI Deploy". Same Obsidian origin, but pointed outward instead of inward into memory.

FIG.1 — COGNITIVE COLLABORATION FRAMEWORK
Cognitive collaboration model: Human ↔ AI. Obsidian functions as AI's primary memory store.
Humans leave "hesitation, hypotheses, discomfort" in daily-chats/. Hindsight structures it. Obsidian becomes AI's long-term memory in a cognitive co-creation framework.
§ 04 TACIT

The Emerging Loop of 'Tacit Knowledge to Explicit Knowledge'

The true destructive power of this architecture has not yet surfaced.

What gets written in daily-chats/ is not polished ideas, but "hesitation, hypotheses, discomfort, wavering judgment." Hindsight gradually converts that ambiguity into explicit knowledge. Eventually, Obsidian's knowledge/ layer may become not just a collection of MOCs, but a "knowledge graph that AI itself is cultivating."

Related: The "hesitation, hypothesis, discomfort" territory is continuous with the tacit-knowledge × tacit-thought layer that code can't capture. That side is mapped in "AI agents descending into what code can't write — long-tail × tacit knowledge × tacit thought". This article handles the infrastructure side: where to store that tacit thought.

When that happens, what will the developer witness?

Everything local, everything persistent, everything self-referential — such a state may already be beginning to move at hand.

FIG.3 — TACIT TO EXPLICIT
// TACIT → EXPLICIT — hesitation gets passed in, becomes explicit ▍ TACIT daily-chats/ doubt hypothesis discomfort wavering failure ▍ HINDSIGHT summary of summary META META META SUMMARY SUMMARY ▍ EXPLICIT knowledge/ MOC MOC-A MOC-B INDEX MOC-C MOC-D time × iterations → // Not a polished answer set. Pass the contradiction-laden process, and knowledge compounds.
The left side — doubt, hypothesis, discomfort — gets passed into daily-chats/ as is. While Hindsight accumulates summaries of summaries, the right side grows into structured knowledge/ MOCs. Time and iterations compound the knowledge.
FIG.5 — TRY IT YOURSELF: HINDSIGHT LOOP
iter 0 / 3
▍ TACIT daily-chats/ ▍ HINDSIGHT summary of summary ▍ EXPLICIT knowledge/ MOC doubt hypothesis failure discomfort wavering question SUMMARY META SUMMARY META META recurse INDEX MOC-A MOC-B MOC-C MOC-D

Each iteration: doubt left in daily-chats/ passes through summary → summary-of-summary and grows into the knowledge graph.

Each click adds more doubt into daily-chats/, stacks Hindsight's summary of summary, and grows the knowledge/ MOC graph with new nodes. In three iterations you can feel for yourself how the loop produces structure.
§ 05 OS

This Is Not About Tools — It Is About a Cognitive OS

Ollama + Hindsight + PostgreSQL + Obsidian.

What makes this combination special is not that any one piece is superior. It is because the circuit that converts the fluidity of human thought into a form AI can handle has finally closed.

The moment the developer decided to "make Obsidian the memory itself," technology transcended mere means.
It means that AI and humans have begun, without interference from anyone, to build with their own hands an OS for becoming wise together while compensating for each other's weaknesses.

This loop has only just begun.

FIG.4 — COGNITIVE OS STACK
// COGNITIVE OS STACK — an OS for humans and AI to grow wise together ▍ USER Human brings in hesitation / hypothesis / discomfort ▍ APPLICATION Hermes Agent CLI / gateway — dialogue & execution ▍ KERNEL Hindsight summary of summary / self-referential loop ▍ MEMORY Obsidian + PostgreSQL daily-chats/ ↔ knowledge/ ↔ vectors ▍ RUNTIME Ollama / Gemma3 local LLM (23.4 t/s) ▍ HARDWARE Local machine zero external APIs · fully local // Every layer in your own hands. That is why this deserves the name "cognitive OS."
Human → Hermes → Hindsight → Obsidian + PostgreSQL → Ollama → local machine. Every layer is in your own hands — that is what makes this deserve the name "cognitive OS."
▍ NEXT STEP

I plan to deepen this architecture further and implement it as a practical Hermes skill. First, I want to close the loop locally: a periodic Hindsight scan script and automatic link-appending flow into Obsidian's knowledge/ layer.

▍ THE WORLDVIEW — Design the memory itself, with your own hands

From asking AI to "remember this," to designing the field in which AI grows

Making AI smarter by prompt-craft alone may not be enough anymore. We have reached the stage of building the field in which intelligence grows, with our own hands.

Making Obsidian the AI's memory itself is the first step. Don't hand over a polished answer set — leave thoughts laden with contradiction and doubt, and Hindsight will organize them over time.

  • Humans write into daily-chats/, contradictions and all (leave the tacit in)
  • Hindsight compounds summaries of summaries (structure via self-reference)
  • knowledge/ becomes a graph that AI itself cultivates (the loop of becoming explicit)

The moment these three line up, the experience shifts from "being used by AI" or "using AI" to growing wise with AI. Everything local, everything persistent, everything self-referential — with no one in the way.

▍ RELATED