GBrain Dashboard
Browse Notes
New Note
Edit: github-backup/research/hermes-obsidian-second-brain-recommendation-2026-05-27.md
Cancel
Note Content (Markdown)
# 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 - Official Hermes Agent website, documentation, GitHub repository and current release notes. - Andrej Karpathy's original `llm-wiki` gist. - Hermes' bundled `llm-wiki` skill derived from Karpathy's pattern. - Rhys Fisher's public Cognitive Shift articles, especially the May 5 search article and May 20 Hermes/research-swarm article. - Tobi Lutke's public QMD repository as the implementation cited by Fisher. - Public Easier Agency pages and the public Easier Now login surface. - Relevant academic/preprint literature on agent memory and retrieval. ### Access Notes - The supplied Notion page was not accessed during the first research pass because no Notion connector was available and the request explicitly said to check/ask first. In the later planning pass, Anthony explicitly approved using the browser route, so selected strategy/SOP pages were sampled for planning context. No bulk export was performed. - Authenticated Easier Now content. The public route is a sign-in form; no credential entry or account access was attempted. - Private business tools, customer records or advertising accounts. ### Infrastructure Limitation The existing GCE instance could not be altered from this environment: - `gcloud` is not installed. - No Google Cloud/GCE connector is available. - A local SSH key called `easier_validation_gce_ed25519` and known host `34.27.189.109` exist, but a non-interactive attempt as user `astra` was rejected with `Permission denied (publickey)`. 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: - An always-available conversational front end to an owned Markdown vault. - Skill-guided research, briefs, meeting preparation and weekly synthesis. - A later controlled route into n8n for approval-based workflows. - A deployable server-resident agent that does not depend on a laptop being on. ### Where Hermes Alone Is Insufficient Hermes' built-in memory is explicitly bounded and curated. It should not be asked to hold: - Client histories, commitments or commercial facts. - Campaign evidence, revenue calculations or experimentation records. - Relationship intelligence and source transcripts. - Product/R&D decisions that need provenance and review. 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: - Fast `inbox/` capture and daily/weekly review over a burdensome taxonomy. - Notes in Anthony's own voice as the high-value input, with agent-authored synthesis distinguishable from human thinking. - Simple commands for "prepare me", "what changed?", "what am I forgetting?" and "challenge this decision?" before ambitious automation. - Privacy and approval boundaries before using the same approach on customers, prospects or commercially sensitive operations. ### 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: - Markdown remains the source of truth. - Retrieval combines lexical/BM25 and semantic search with reranking. - Results return ranked snippets and paths. - The index is disposable local state, not the canonical memory. - Structured frontmatter contributes useful high-signal tokens even when the indexer treats Markdown as text. 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: - Observable checkpoint files make unattended work inspectable. - Flat dispatch of independent paper tasks proved more reliable than nested agents recursively spawning agents. 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: - Hybrid retrieval as an evaluated layer over Markdown. - Retrieval-before-write for proposed compiled notes. - Immutable evidence and explicit provenance. - Checkpoints and run reports for every eventual unattended workflow. - Flat, bounded worker batches for research rather than open-ended swarms. Validate before enabling: - QMD relevance on a private, hand-judged Easier question set. - Disk/CPU effect on the GCE instance that already houses n8n. - Its handling of sensitive material and backup exclusions. - Any LLM-generated frontmatter backfill, which should be reviewed rather than applied wholesale to business data. Do not adopt yet: - Unattended browser automation into third-party business systems. - Agents extracting and acting on relationship data without a privacy, retention and human-review policy. - Overnight code or workflow modifications in production. ## 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: - Client commercial and margin context. - Creative hypotheses, ads and post-mortems. - Customer/prospect relationships and commitments. - Fulfilment methods and quality lessons. - Product discovery for Easier Now and free tools. 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 ```text 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. ```text 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 ```yaml --- 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: - Hermes official wiki navigation plus file/keyword search. - QMD local hybrid search against the same vault. Build a set of 30-50 judged questions after the first real sources are present: - Exact: "What is the source of the Bier Company revenue claim?" - Fuzzy: "Who had a margin anxiety but was open to creative testing?" - Temporal: "What changed in the Easier Now onboarding view last month?" - Contradictory: "What evidence argues against our current positioning?" - Operational: "Which promises are waiting on Anthony?" 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: - Anthony is the owner/operator and prioritises profitable growth. - The canonical knowledge base path and its privacy rules. - Required approval boundaries. - A few stable interaction preferences. 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 - Keep the existing n8n service untouched. - Keep infrastructure/templates in a private repository such as `easiermarketing/easier-hermes-ops`, but keep the living confidential vault, secrets, sessions and retrieval indexes out of Git by default. - Run Hermes as a separate container from a pinned source release, with a dedicated data directory and vault directory. - Execute any later Hermes terminal tools only inside that container; do not mount the host Docker socket or permit control of the n8n containers. - Do not publish port `8642` during preparation. If an API is later required, bind privately behind authenticated access and an explicit firewall rule. - Keep all MCP integrations disabled until a capability-by-capability review. - Use encrypted disk/snapshot policy and private backup for the vault before ingesting private documents. - Monitor memory, disk and CPU before indexing with QMD; a 2 GB local-model download is cited by the QMD migration guide. ### Inert Preparation Performed Locally The deployment pack: - Targets pinned Hermes source tag `v2026.5.16`. - Stages the pinned source and can build an image later, but should skip the build on the current small live n8n host unless a maintenance window and disk headroom are confirmed. - Creates empty storage and a minimal empty vault skeleton. - Writes non-secret inactive config templates. - Profile-gates the Compose service so ordinary `docker compose up` does not start Hermes accidentally. ### 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. ## Recommended Rollout ### 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: - Karpathy/Hermes for compiled, interlinked knowledge. - Fisher/QMD for stronger fuzzy recall and retrieval-before-write. - Memory research for tiering, evidence preservation, consolidation and counterevidence. - Obsidian for ownership and human review. - Hermes plus later n8n/Easier Now integration for carefully bounded action. 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 - Nous Research, Hermes Agent docs: https://hermes-agent.nousresearch.com/docs/ - Nous Research, official repository: https://github.com/NousResearch/hermes-agent - Nous Research, release `v2026.5.16` / Hermes Agent v0.14.0: https://github.com/NousResearch/hermes-agent/releases/tag/v2026.5.16 - Hermes Agent, Persistent Memory: https://hermes-agent.nousresearch.com/docs/user-guide/features/memory - Hermes Agent, Skills System: https://hermes-agent.nousresearch.com/docs/user-guide/features/skills - Hermes Agent, Context Files: https://hermes-agent.nousresearch.com/docs/user-guide/features/context-files - Hermes Agent, MCP: https://hermes-agent.nousresearch.com/docs/user-guide/features/mcp - Hermes Agent, Security: https://hermes-agent.nousresearch.com/docs/user-guide/security - Hermes Agent, Docker: https://hermes-agent.nousresearch.com/docs/user-guide/docker/ - Hermes Agent bundled `llm-wiki` skill: https://github.com/NousResearch/hermes-agent/blob/main/skills/research/llm-wiki/SKILL.md - Andrej Karpathy, `LLM Wiki` gist: https://gist.github.com/karpathy/442a6bf555914893e9891c11519de94f - Greg Isenberg with Internet Vin, `How I Use Obsidian + Claude Code to Run My Life`, 2026-02-23 (episode index linking to original video): https://podwise.ai/episodes/7288813 - Tobi Lutke, QMD: https://github.com/tobi/qmd ### Supplied and Business Context Sources - Rhys Fisher, `Let Them Run`: https://thecognitiveshift.com/publications/let-them-run/ - Rhys Fisher, `Your AI Second Brain Has a Quiet Search Problem`, 2026-05-05: https://thecognitiveshift.com/publications/let-them-run/your-ai-second-brain-has-a-quiet-search-problem/ - Rhys Fisher, `Outrunning the AI Hype Train`, 2026-05-20: https://thecognitiveshift.com/publications/let-them-run/outrunning-the-ai-hype-train/ - Rhys Fisher, QMD transplant companion repository: https://github.com/RhysEJF/cognitive-shift-resources/tree/main/second-brain-transplant-to-qmd - Easier Agency: https://new.easieragency.com/ - Easier Agency free tools: https://new.easieragency.com/free-tools/ - Easier Now public route: https://prod-easiernow.vercel.app/now - Easier Agency Notion knowledgebase, sampled with approval: https://www.notion.so/stratton-digital/86b9c355cc0c4438b964beb0141ecab9 ### Academic and Advanced Sources - Packer et al., `MemGPT: Towards LLMs as Operating Systems`, 2023: https://arxiv.org/abs/2310.08560 - Park et al., `Generative Agents: Interactive Simulacra of Human Behavior`, 2023: https://arxiv.org/abs/2304.03442 - Gutierrez et al., `HippoRAG`, 2024: https://arxiv.org/abs/2405.14831 - Adler and Zehavi, `Storage Is Not Memory: A Retrieval-Centered Architecture for Agent Recall`, 2026 preprint: https://arxiv.org/abs/2605.04897 - Miteski, `Memory as Metabolism: A Design for Companion Knowledge Systems`, 2026 preprint: https://arxiv.org/abs/2604.12034 - `From BM25 to Corrective RAG: Benchmarking Retrieval Strategies for Text-and-Table Documents`, 2026 preprint: https://arxiv.org/abs/2604.01733
Save Changes