github-backup/research/hermes-obsidian-second-brain-recommendation-2026-05-27.md

Edit Back to List

Hermes Agent + Obsidian Second Brain for Easier

Research Dossier and Implementation Recommendation

Prepared: 2026-05-27, Europe/London
Subject: Hermes Agent as an AI operating layer for Easier Agency, Easier Now, and future business workflows
Scope: public-source research and inactive deployment preparation only

Executive Recommendation

Use Hermes Agent as an orchestrating assistant, not as the authoritative store of business memory. Build the durable second brain as an Obsidian-compatible Markdown vault with immutable evidence, compiled knowledge pages, provenance, confidence and sensitivity labels. Let Hermes read and maintain the compiled layer through its official llm-wiki skill. Add hybrid local search through QMD after a retrieval benchmark confirms it improves recall on real Easier questions.

Host Hermes beside the existing n8n GCE workload only inside a separately contained, non-public runtime with its own data and vault volumes. Initially:

  1. No messaging gateway.
  2. No API published to the internet or private network.
  3. No n8n, Notion, CRM, ad-platform or email MCP integration.
  4. No autonomous curator, cron jobs, or automatic mass ingestion.
  5. No secrets in the prepared configuration.

This keeps the system useful to inspect and activate later while avoiding the early-stage failure mode of putting a self-modifying agent directly in the middle of customer relationships, fulfilment or money-moving operations.

The practical target is not "AI runs everything" on day one. It is a progressive operating memory that first helps Anthony recall, synthesise and decide; then drafts and routes work for approval; and only eventually executes bounded, reversible operations with logs and budgets.

What Was and Was Not Accessed

Reviewed

Access Notes

Infrastructure Limitation

The existing GCE instance could not be altered from this environment:

An inactive, auditable setup package is therefore staged in deployment/. It can be transferred and executed once the correct SSH user/key or Cloud access is provided.

Hermes Agent in May 2026

Verified Current State

As observed on 2026-05-27, the official GitHub "latest release" page identifies Hermes Agent v0.14.0 with tag v2026.5.16, released on 2026-05-16. Hermes is an MIT-licensed, open-source agent built by Nous Research.

The official documentation describes:

Capability Relevant detail Design implication
Runtime Linux/macOS/WSL2; native Windows beta; Docker supported GCE Linux container is a sensible home
Entry points CLI, messaging gateway, API server, library and batch paths Start with CLI-only inspection; do not expose gateway/API
Agent tools 70+ built-in tools and MCP extension support Tool permission design matters before integrations
Terminal isolation Local, Docker, SSH and cloud sandbox backends Use container isolation even on an owned VM
Core memory MEMORY.md 2,200 chars and USER.md 1,375 chars Useful routing context, too small to be the second brain
Session recall SQLite/FTS5 conversation search Useful operational history, not structured business truth
Skills Files in ~/.hermes/skills/, including progressive disclosure Good place for controlled workflows
Context files .hermes.md, AGENTS.md, CLAUDE.md; global SOUL.md Vault governance can be loaded explicitly
MCP Catalog entries reviewed by Nous and disabled by default Keep every connector off until reviewed
Security Filtered MCP environment, credential redaction, URL/SSRF controls Helpful baseline, not a substitute for business controls
Docker Persistent host data mounted at /opt/data Clean separation from the existing n8n deployment

Notable v0.14.0 Items

The official release notes describe improved distribution and installation, native Windows beta, a PyPI distribution, provider/OAuth work, stronger dangerous-command protections, tool error sanitisation, and new integrations. They also add or revise Notion-related optional skill support. None of that is a reason to connect sensitive systems before permissions and audit policies are chosen.

Where Hermes Fits Well

Hermes is a strong candidate for:

Where Hermes Alone Is Insufficient

Hermes' built-in memory is explicitly bounded and curated. It should not be asked to hold:

These belong in the vault and, as the system matures, appropriate operational systems of record. Hermes should retrieve and assist with them subject to policy.

Karpathy Pattern: Compile Knowledge, Do Not Just Chat With Files

Andrej Karpathy's April 2026 LLM Wiki gist presents an "idea file" for a personal knowledge base maintained by an LLM. Its important idea is a division between raw material and an interlinked, evolving wiki that the model maintains. It is attractive for an owner/operator because the artifacts remain plain Markdown and human-inspectable in Obsidian.

Hermes has already bundled an official llm-wiki skill based on that pattern. The skill specifies a practical three-layer structure:

  1. raw/: immutable source material, such as articles, papers and transcripts.
  2. Compiled pages: entities/, concepts/, comparisons/ and queries/.
  3. Governance/navigation: SCHEMA.md, index.md and append-only log.md.

The official Hermes skill also recommends YAML frontmatter, Obsidian wikilinks, provenance markers for multi-source claims, confidence/contested flags, explicit contradiction handling, source hashing and linting for broken links, stale pages, low-confidence material and source drift.

Adoption Decision

Adopt this layout, adjusted for a commercial operator. It is substantially better than a folder of raw notes because it distinguishes evidence from interpretation and gives future agents an audit trail.

Do not accept one part uncritically: for a large or fuzzy business corpus, reading index.md and text searching files is not enough retrieval. The compiled wiki and retrieval layer are complementary.

Greg Isenberg and Internet Vin: Make the Vault a Thinking Practice

Greg Isenberg's 23 February 2026 episode with Internet Vin, How I Use Obsidian + Claude Code to Run My Life, presents the founder-facing version of this pattern: interconnected Markdown in Obsidian gives an agent context for idea generation and delegation; custom commands can extract ideas, challenge beliefs and connect concepts; and consistent human reflection keeps the knowledge current. The accessible episode outline also explicitly raises the privacy implications of agent access to a personal knowledge base.

This contributes a useful emphasis that the purely technical architecture can miss. A second brain succeeds only if capture and review fit ordinary life. For a semi-organised founder, the implementation should therefore prioritise:

Adoption Decision

Combine Isenberg/Vin's human habit and command-oriented interface with Karpathy/Hermes' compiled wiki and Fisher's retrieval improvement. Do not let the desirable "24/7 personal operating system" framing become permission for unattended client-facing action.

Rhys Fisher: What to Adopt and What to Validate

The provided author is Rhys Fisher, not "Rhy Fisher". His public work is particularly relevant because it addresses real operator workflows rather than only agent demos.

Quiet Search Problem, 5 May 2026

Fisher argues that a Markdown second brain backed only by grep fails exactly where it matters: fuzzy recall. A founder often remembers meaning ("the prospect who was an AI champion but needed budget sign-off") rather than the literal terms in a note.

His proposed remedy is QMD, Tobi Lutke's local Markdown search tool:

The companion migration repository documents Node 22+ and roughly 2 GB of disk for local models, with a staged, backup-first procedure. This is a sensible candidate for the GCE-hosted vault, subject to benchmarking and resource checks.

Hermes and Research Swarms, 20 May 2026

Fisher's later article describes a research pipeline built from composable operations: digest one paper; walk citations in broad, canonical, deep and idea-orbit modes; generate longitudinal synthesis; mine candidate theses; then adversarially search for falsification. Two implementation lessons are useful:

He also reports using retrieval at write time: before writing a candidate new memory, query existing memory; high similarity creates an evidence link rather than a duplicate, while intermediate similarity calls for merge/routing.

Adoption Decision

Adopt now in the design:

Validate before enabling:

Do not adopt yet:

Academic and Advanced Architecture Review

No single paper establishes a production-ready personal business memory standard. The literature nevertheless supports a layered design and highlights failure modes that matter for Easier.

Source Contribution Application here Caution
MemGPT, Packer et al. (2023) Virtual context management and tiered agent memory Keep tiny always-loaded identity/rules separate from searchable long-term evidence Memory management is not truth governance
Generative Agents, Park et al. (2023) Observation, reflection and planning from memory streams Periodic synthesis can surface patterns from customer and experiment notes Reflections can compound errors without citations
HippoRAG, Gutierrez et al. (2024) Knowledge-graph-inspired retrieval for multi-hop association Later evaluate entity/relationship traversal across clients, campaigns and insights Premature graph automation adds maintenance burden
Storage Is Not Memory, Adler and Zehavi (2026 preprint) Retrieval-centred design preserving verbatim events; reports strong long-context memory benchmark results Preserve raw transcripts/events and retrieve before compressing them into knowledge Results are recent preprint claims requiring independent validation
Memory as Metabolism, Miteski (2026 preprint) Companion memory governance: triage, decay, contextualise, consolidate, audit; minority-hypothesis retention Build review, staleness and dissent paths into a personal business assistant Normative/design proposal, not production proof
From BM25 to Corrective RAG (2026 preprint) Reports hybrid retrieval plus neural reranking outperforming single-stage retrieval on text/table documents; BM25 remains strong on financial data Use lexical plus semantic retrieval, especially for margin/financial language and exact entities Benchmark domain differs from Easier's own material

Synthesis

The advanced approach is not choosing "wiki" versus "RAG" versus "memory". Use different mechanisms for different memory jobs:

Memory job Mechanism Example
Identity and permission rules Small reviewed context files Scope, voice, approval limits
Exact source evidence Immutable raw Markdown/assets Transcript, brief, exported report
Working business understanding Compiled Obsidian pages Customer insight, experiment, SOP
Fuzzy recall Hybrid retrieval index "Which prospect worried about margin?"
Relationships and evolving facts Typed metadata plus later graph evaluation Person-company-project links
Learning without ossification Audit, contested claims, expiry and review A failed positioning thesis retained as counterevidence

Easier Context and Business Fit

The public Easier Agency homepage positions the company as an operator-led growth partner for UK ecommerce founders: contribution margin rather than platform ROAS; coordination of fragmented marketing suppliers; live profit visibility; and reduction of the founder bottleneck. It cites experience since 2012, 200+ brands, more than GBP 10m of ad spend managed and more than GBP 25m of revenue generated.

This positioning makes a second brain valuable, but raises the stakes. It will eventually contain:

The system must therefore be commercially useful while also being source-citable, revocable, privacy-aware and cautious about automated action.

The public Easier Now route currently displays an account sign-in screen. The future product opportunity is clear conceptually: make a reviewed memory and assistant layer part of the productivity product. This should be approached through clean interfaces and permission tiers, not by coupling the product to an ungoverned personal vault.

Proposed Operating Architecture

Human and approved captures
  |  meeting notes, research, exports, eventually approved connectors
  v
raw/ immutable evidence ----------------------------------------+
  |                                                            |
  | controlled compilation with provenance                     | retrieve exact evidence
  v                                                            |
compiled Obsidian vault: entities, projects, decisions, etc.  |
  |                                                            |
  +---- QMD hybrid index (rebuildable, local) <----------------+
  |                 |
  | relevant cited context only
  v
Hermes Agent in isolated Docker container
  |  skills: llm-wiki, later approved business workflows
  |  logs/checkpoints, no broad write/actions initially
  v
Approval queue (later via n8n / Easier Now)
  |
  v
External action only after bounded authorization

Separation of Responsibilities

Component Owns Must not own initially
Obsidian vault Human-readable source and compiled knowledge API secrets or autonomous actions
QMD index Disposable retrieval accelerator Canonical facts
Hermes Query, synthesis and approved page maintenance Unreviewed sends, spend or client changes
n8n Later controlled triggers and approval routing Agent-wide credentials without per-flow policy
Easier Now Later product interface and permission UX Direct access to a founder vault by default

Vault Design for an Innovative, Semi-Organised Operator

The vault must make capture easy before it makes taxonomy clever. Start with few folders and typed pages rather than a heavy filing burden.

easier-brain/
  AGENTS.md                  # reviewed Hermes rules and permissions
  SCHEMA.md                  # metadata and maintenance rules
  index.md                   # navigational entry point
  log.md                     # append-only knowledge-maintenance log
  inbox/                     # low-friction unprocessed captures
  raw/
    meetings/
    customer-voice/
    research/
    marketing/
    product/
    operations/
    assets/
  people/                    # reviewed relationship pages
  organisations/             # client, prospect, partner, supplier pages
  projects/                  # Easier Agency, Easier Now, tools, client projects
  decisions/                 # decision record plus why and evidence
  experiments/               # hypothesis -> test -> measure -> outcome
  playbooks/                 # delivery and operational procedures
  concepts/                  # insights and frameworks
  briefs/                    # prepared outputs, not source evidence
  reviews/                   # daily/weekly/monthly synthesis and audits
  _archive/

Minimum Metadata

---
title: "Example experiment or relationship note"
type: experiment
status: draft
created: 2026-05-27
updated: 2026-05-27
entities: [easier-agency]
domains: [marketing]
sources: [raw/research/example-source.md]
sensitivity: internal
confidence: medium
review_by: 2026-06-27
contested: false
---

Use entity slugs consistently. Add client-confidential and personal-sensitive sensitivity classes before importing any non-public material. Raw source pages should additionally carry source URL/date or import origin and a body checksum.

Knowledge Page Rules

  1. raw/ is append-only and is never silently rewritten by an agent.
  2. Claims on compiled pages cite raw evidence or are labelled inference.
  3. Relationship pages distinguish direct statements, observed facts and agent hypotheses.
  4. Decisions include owner, date, status, rationale and reversal condition.
  5. Experiments preserve failed hypotheses, not only wins.
  6. Any page that affects a client communication, money, privacy or fulfilment needs human review before downstream action.
  7. Automated maintenance produces a report and proposed diff, never an invisible rewrite.

Retrieval and Memory Policy

Retrieval Stack

Phase 1 should compare:

Build a set of 30-50 judged questions after the first real sources are present:

Measure whether the correct evidence appears in top 5 results, whether the answer cites it, latency, and whether sensitive cross-domain leakage occurs.

Write-Time Retrieval

Before an agent proposes a new compiled page or a strong new claim:

  1. Search for existing related pages and raw evidence.
  2. If nearly duplicate, link evidence to the existing page.
  3. If updating an existing belief, preserve old evidence and mark the change.
  4. If contradictory, retain both claims and route for review.
  5. Write a log entry describing the proposal or approved update.

This adopts Fisher's write-time retrieval insight while making the threshold a reviewed policy rather than an opaque automatic action.

Hermes Built-In Memory

Use USER.md and MEMORY.md only for compact routing context such as:

Do not place customer facts, commercial detail or relationship histories into Hermes prompt-injected memory unless intentionally reviewed.

Use Cases and Automation Boundaries

Domain Useful first capability Later controlled automation Never unattended at first
Marketing Retrieve proof, create cited creative/research briefs Draft experiments and content variants Publish ads or alter spend
Sales Pre-call brief from approved notes Draft follow-up for approval Send messages or alter CRM state
Relationships Surface commitments and context Reminder queue Infer sensitive traits or contact people
Fulfilment Retrieve SOP and prior lessons Draft checklists/status summaries Deliver client work as final
Operations Weekly bottleneck/decision digest n8n approval routes Change live workflows or credentials
R&D Paper/product research corpus and thesis tracking Bounded overnight reading runs Ship code/product changes
Easier Now Requirements and learning vault Read-only assistant prototype Connect personal/client vaults directly

Deployment Recommendation for the n8n project VM

Preferred Topology

Inert Preparation Performed Locally

The deployment pack:

What Remains for an Approved Activation Session

  1. Obtain the correct GCE connection method and inventory OS, Docker, disk, memory, current n8n containers, backups and firewall.
  2. Transfer or reproduce the reviewed deployment pack.
  3. Run only the host preparation script and review its audit record.
  4. Choose vault sync/backup method and data classification policy.
  5. Choose provider credentials locally; do not place secrets in chat or vault.
  6. Start Hermes interactively without channels and test on synthetic/public notes.
  7. Benchmark retrieval before enabling QMD for real private knowledge.
  8. Add one read-only source or approval workflow at a time.

Phase 0: Prepared, Not Running

Current goal. Stage pinned software, inactive config, vault schema and security choices. No credentials or business data.

Exit gate: authenticated VM access and infrastructure inventory.

Phase 1: Personal Research Vault

Use public research and self-written notes only. Run Hermes interactively, enable the official llm-wiki skill, compare native retrieval with QMD, and perform weekly human-reviewed lint/audit.

Exit gate: retrieval quality test passes and all generated claims are cited.

Phase 2: Internal Business Memory

Bring in approved non-client-sensitive Easier strategy, product research and operating notes. Begin an approval queue for drafted decisions and tasks.

Exit gate: backup, sensitivity rules and correction workflow have been tested.

Phase 3: Confidential Material

Only then import selected customer/prospect/meeting material under retention, access and deletion policies. Consider separate vault partitions for confidential client data.

Exit gate: privacy review and tested access boundary.

Phase 4: n8n and Easier Now

Expose narrowly scoped read or draft actions via n8n/Easier Now. Human approval remains mandatory for messages, spend, client deliverables, data export and workflow mutation.

Exit gate: per-workflow audit, undo plan, monitoring and budget control.

Key Risks and Controls

Risk Consequence Initial control
Memory becomes plausible fiction Bad client/business decisions Raw evidence, citations, confidence and review
Fuzzy retrieval misses key fact Wrong follow-up or repeated work QMD evaluation with judged query set
Stale belief is repeatedly reinforced Strategic entrenchment review_by, contested claims, minority evidence audit
Private data leaks through tools/model Legal/trust damage No private ingestion initially; no connectors; sensitivity policy
Agent takes external action too early Reputation or spend damage No gateway/API/n8n MCP; draft-only phases
Hermes consumes n8n VM resources Production disruption Isolated container, preflight inventory and resource limits later
Supply-chain/change drift Unexpected behaviour Pin release and review upgrades
Sync/backup mistake destroys vault Loss of knowledge Backup and restore drill before imports

Conclusion

Hermes is unusually well aligned with the ambition of an AI-augmented owner/operator because it already supports persistent context, skills, server-resident operation and a Karpathy-style Markdown wiki workflow. Its built-in memory should be treated as a small navigation layer. The valuable asset is the owned, auditable knowledge vault.

The best implementation for Easier is therefore a layered one:

The system should earn autonomy through reliable recall, auditability and approval discipline, rather than starting with access to every operational surface.

Sources Consulted

Primary Product and Implementation Sources

Supplied and Business Context Sources

Academic and Advanced Sources