KIMI K3 + OBSIDIAN + LOOP ENGINEERING = A... VAULT THAT RUNS ITSELF the core idea: the vault is the loop's state, not the chat window everything Kimi K3 knows lives in a .md file the loop: > capture - a thought lands in 00-inbox > context - K3 pulls links, tags, and neighbouring notes > draft - edits happen inside a git worktree, never the live vault > review - a critic agent checks the diff before anything ships > commit - appended to the vault, nothing gets rewritten the key insight: frontmatter fields like supports, contradicts, and supersedes are graph edges, not metadata - the note format is the write API start with a plain loop, it runs about 2-4x the cost of one direct call > only move to a full graph once state has to outlive the session, several agents need to coordinate, or you have to explain what changed - that jump can run 10-50x one review assistant climbed from 55% to 72% to 84% just by moving through these shapes in ordershow more

CLAUDE + OBSIDIAN + LOOP ENGINEERING = A VAULT... THAT RUNS ITSELF the core idea: the vault is the loop's state, not the chat window everything Claude knows lives in a .md file the loop: > capture - a thought lands in 00-inbox > context - claude pulls links, tags, and neighbouring notes > draft - edits happen inside a git worktree, never the live vault > review - a critic agent checks the diff before anything ships > commit - appended to the vault, nothing gets rewritten the key insight: frontmatter fields like supports, contradicts, and supersedes are graph edges, not metadata - the note format is the write API start with a plain loop, it runs about 2-4x the cost of one direct call > only move to a full graph once state has to outlive the session, several agents need to coordinate, or you have to explain what changed - that jump can run 10-50x one review assistant climbed from 55% to 72% to 84% just by moving through these shapes in ordershow more

THIS GUY CONNECTED HIS AI AGENTS TO HIS OBSIDIAN... AND BUILT A BRAIN THAT LEARNS ON ITS OWN. HERE'S HOW TO BUILD IT Obsidian is just markdown files sitting in a folder. That turns out to be the perfect memory for an AI agent, because an agent can read and write those files directly. He wired his agents into the vault so they pull context from it, do the work, and write what they learned back. The notes aren't the point. The loop is, and it gets sharper every cycle How to build it: 1. Point an agent at your vault. The fastest way, no plugins, no API keys: open a terminal and run npx obsidian-mcp /path/to/your/vault. That exposes your Obsidian folder to Claude as a tool it can read, search, and write to. Add it to your Claude Code or Cowork config and restart 2. Confirm it can see the brain. Ask it: "list the notes in my vault and summarize what's in them." If it reads them back, the connection is live. Now it starts every task with everything the vault already holds instead of from zero 3. Give each agent one job and a write-back rule. Tell it: "research this, then save what you found as a new note in /brain with links to related notes." One agent researches, one summarizes, one plans. Each writes its output back into the vault 4. Close the loop. Add one line to every agent's instructions: "read /brain before starting, write your result back when done." Now each task leaves the vault richer, and the next run reads that before it works. It compounds instead of resetting 5. You only steer. Review what the brain produces, point it at the next thing. The agents handle the reading, writing, and connecting The edge isn't better notes. It's a brain that feeds itself, so the work gets sharper every cycle instead of starting over Bookmark thisshow more

A Chinese developer just explained the shift from Loop... Engineering to Graph Engineering better than anyone. most people are still building agents the way that's about to be obsolete. > why single-agent loops break and go "goal blind" > the 4 parts of a graph: nodes, edges, state, policy > 3 topologies that run everything: diamond, supervisor, pipeline > Anthropic's 5 official workflow patterns the punchline: it's not how many agents you run. it's the determinism you build with verifiers, code fallbacks, and reality anchors. I broke the same architecture down with Kimi K3. Full A-Z guide below.show more

A DOCTOR BUILT AN AI-QUERYABLE DATABASE OF EVERY DISEASE... HE KNOWS IN OBSIDIAN. THE SAME STACK CAN RUN AN ENTIRE COMPANY ON ONE PERSON'S BRAIN Zoomed out, his vault looks like a constellation. Every disease linked to its symptoms, every symptom to the conditions it shows up in, every treatment to what it treats. Adding a new case is one note that wires itself into the rest. It's a personal database, and the structure has nothing to do with medicine. It's just nodes and links. Once you see that, the same setup runs anything: > a startup that needs to remember every customer, decision, and meeting; > a school whose curriculum links to every lecture and student question; > a business where SOPs, clients, and vendors all sit in one queryable graph. Drop Claude on top, and the vault stops being a map. It becomes something you can ask, in plain English, across everything you've ever written down. Full Claude + Obsidian build in the article below. Bookmark thisshow more

the loop is not the whole agent it is... only one layer of the system LOOP vs GRAPH vs HARNESS ENGINEERING LOOP ENGINEERING controls iteration turns retries budgets stop conditions success checks stalled progress use durable execution when the run must survive crashes → GRAPH ENGINEERING controls structure nodes edges state branches checkpoints routing handoffs build stateful agents as explicit graphs → inspect the topology without putting a model in the loop → HARNESS ENGINEERING controls exposure tools permissions memory sandboxes evals traces humans isolate generated code from the host machine → test behavior before users ever see it → preserve one trace across every model step and tool call → without loop control it keeps running without graph structure the path stays invisible without harness control it can reach anything the loop runs inside the graph the graph runs inside the harness the model is only one component debug the layer that actually owns the failure save this then read the article belowshow more

HERMES AGENT + OBSIDIAN IS A COMBINATION NOBODY IS... TALKING ABOUT. Hermes ships with a bundled Obsidian skill. read, search, and create notes in your vault out of the box. why this combination is powerful: Hermes built-in memory is capped. MEMORY.md: 2,200 chars (~800 tokens). USER.md: 1,375 chars (~500 tokens). Obsidian vault has no cap. your agent writes research, session summaries, project context, and learned patterns as linked markdown notes. unlimited depth. the agent creates indexed notes by design. timestamps, backlinks, tags. every note connects to the knowledge graph. three ways to integrate: 1. BUNDLED OBSIDIAN SKILL (simplest) ships with Hermes. reads, searches, creates notes in your vault directly. hermes skills list | grep obsidian 2. OBSIDIAN MCP SERVER (deepest) 30+ tools: full-text search, tag lookup, note management, vault analysis, link analysis, orphan detection. add it via: hermes mcp 3. TELEGRAM + CRON → VAULT (always-on) set a cron job that writes daily summaries, research findings, or task reports directly into your Obsidian vault. your agent feeds the vault while you sleep. you review in Obsidian when you're ready. the unlock: Hermes memory handles what the agent needs to know per session (capped, injected). Obsidian handles everything the agent has ever learned (uncapped, searchable). short-term in Hermes. long-term in Obsidian. both accessible. both persistent. keep the vault scope narrow at first. start with one /Hermes folder. expand once you trust the workflow. 8 Loops Indise Hermes Agent👇show more

While AI timeline argues about loop engineering, a 20-year-old... student in Shenzhen built the biggest loop anyone's aimed at money: 300 agents, one brain, $1,200 -> 395,000. Not a prompt. Not a bot. A loop that runs the whole job on its own - and never asks him a thing. No fund. No backers. Just a laptop, a dorm room, and a bet that a swarm beats a genius. His wallet: The smartest single model still works one step at a time. His loop moves in 300 directions at once - and never checks in with him. Claude Opus 4.8 runs the floor as the brain. 300 agents are the hands. One loop ties them together: > Decompose - Opus breaks the market into targets > Dispatch - 300 agents scatter across them at once > Execute - thousands of reads in a single pass, not one by one > Review - Opus grades every edge before a cent moves The hands find. The brain judges. The loop learns what failed and runs again, tighter each time. One daily loss cap, and it shuts itself down. It's not a bot you babysit. It's a loop that runs the whole desk. Everyone's just learning to run one loop. He runs 300 in one. The edge was never the genius model - it's the size of the loop, and the brain in charge of it. Save this - the full 300-agent loop is laid out above, start to finish. You'll want it when you build your own. 300 agents are looping right now, hunting the markets everyone skips. Two clicks and their trades land in your wallet too:show more

Obsidian just became the most dangerous folder on your... computer, and Andrej Karpathy predicted it with 1 markdown file. His method is called append-and-review. He described it years ago and almost nobody listened: 1 single note, every thought appended to the top, reviewed on random scrolls. No tags, no folders, no Notion dashboards with 40 linked databases. The problem was always the same the note remembers, but it can't act. That changed the moment people pointed Claude Code at an Obsidian vault. Here's the setup that's quietly spreading: Part 1 — The vault becomes a database. Obsidian stores everything as plain markdown on your disk, which means Claude Code can read it like a codebase. You open a terminal inside the vault folder and your 2,000 notes turn into queryable memory. Part 2 — The CLAUDEmd file becomes the brain stem. One file at the root tells the agent who you are, what you're building, and how your notes are structured. From that point every session starts with full context instead of a blank chat window. Part 3 — Karpathy append log becomes fuel. You dump raw thoughts all day ideas, links, half-sentences. Then 1 command at night: review today's appends, extract action items, draft the 3 posts hiding in there, link them to existing notes. The messy log goes in, structured output comes out, and the vault rewrites itself while you sleep. Part 4 — Agents start living in your notes. People are running weekly reviews, content calendars, even market research as scheduled Claude Code runs over their vault. Your second brain stops being a graveyard of highlights and starts shipping. The honest math: setup takes about 90 minutes, the first week feels like overkill, and by day 30 you're sitting on a system where every note you've written in 5 years is working for you instead of rotting in a folder. Notion needed a server, a subscription and your data on someone else's machine. Obsidian needed a text file and now the text file has an employee.show more

THIS CREATOR MADE HIS HERMES AGENT 10X FASTER WITHOUT... CHANGING THE MODEL, JUST BY ADDING ONE FILE TO HIS OBSIDIAN VAULT 00:02 the screen shows a massive second brain with hundreds of connected notes, but without a clear map an AI agent still treats every file like it could be the answer Hermes used to open 7 different documents and spend nearly 2 minutes searching for the current brief, even though the correct file was already sitting inside the vault the fix was one index file inside each major folder, listing the important subfolders, canonical files, and the exact document the agent should open first after reorganizing the vault, the same search dropped from 2 minutes to around 10 seconds, while several tasks went from 5 or 6 opened files to just one the model never changed, the $30 agent stack never changed, only the structure around it did, because a powerful agent without a map is still just wandering through folders blindlyshow more

one agent → a loop → a graph →... a system that throttles itself Google just put the whole ladder in one free course. most people never leave the first rung. 2 hours 4 minutes, taught by two Google Cloud engineers. no signup, no paywall. 17:55 - build your first agent 39:55 - loop engineering: iterate, check, break 1:13:25 - graph engineering 1:35:27 - agents that throttle themselves 1:56:19 - the full graph for multi-agent systems the fourth one is the step nobody talks about. an agent that cannot throttle itself is not autonomous, it is just unattended. everyone builds one agent and calls it done. this is the version where the agents wire themselves into a graph and decide their own rate. and the thing that decides when one of them is allowed to stop is not in the course. that part you build yourself. bookmark and watch it today, then read the eval setup belowshow more

LOOP + GRAPH + CONTEXT ENGINEERING = THE KIMI... K3 STACK THAT KEEPS RUNNING 300 Kimi K3 agents built one graph out of 100 companies. no 300 documents to read yourself kimi-swarm/ ├── swarm_launch.md task, sources, stop condition ├── CONSTRAINTS.md corrections from every past run ├── graph/ 384 entities, 1,064 typed edges, 8 closed verbs └── cron/ re-fires the swarm on schedule > one node sits at the center with 12 inbound edges - the vendor everyone depends on and nobody flagged in the prompt > 2 hops already answers most of what you'd actually ask it loop decides when it fires -> graph decides what's kept -> context decides what survives after the session closes how people are getting paid on this: > one build sold as a competitive teardown - replaces a four-figure analyst contract, done in an hour, unattended > the same graph on retainer - charge weekly for every new edge that shows up > wire the stack for someone else's market once it's proven on your own full version of this tree is in the article belowshow more

A DEVELOPER CONNECTED CLAUDE CODE TO OBSIDIAN SO HIS... AI AGENT WOULD STOP FORGETTING THE PROJECT EVERY MORNING. Every coding session used to start the same way. Claude would understand the repo, fix the bug, explain the architecture, and then the moment the session ended, all of that context disappeared. Same codebase. Same decisions. Same architecture. Same mistakes repeated again. So he added a memory layer. Instead of treating Claude Code like a smart terminal, he connected it to a local Obsidian vault through MCP. Now Claude can read the repo, open the vault, create notes, link concepts, and write important decisions back into the system. When it studies the codebase, it does not just answer once and forget. It creates notes for the major services, maps how the architecture works, links auth to the database, connects APIs to storage, and records why certain migrations or design choices exist. Obsidian becomes the project graph. Now when he asks why something was built a certain way, Claude does not guess from the current prompt. It reads the decision notes. When he starts a new branch, Claude checks the active context file. When the work is done, it updates what changed, what is blocked, and what the next agent needs to know before touching the repo. That is the real loop: read context, write code, capture decisions, update memory. Most people are still using AI coding tools like disposable chat windows. Ask, patch, close, forget. This setup turns Claude Code into infrastructure. The repo gets a memory layer that survives every session, and multiple AI agents can work from the same project map without stepping on each other. The unlock is not better prompting. The unlock is giving the agent somewhere to remember what it already learned.show more

Loops vs. Graphs, clearly explained! loops are great, but... they have a ceiling: a loop makes one unit of work better. it cannot decide which units exist. so you end up with a very good agent running the wrong three steps, in the wrong order, one at a time. Graph engineering fixes this by moving the decision up a layer: what runs, what runs at the same time, and what never runs at all. you need both. here's how it works: a graph splits your system into two kinds of decision. ↳ inside a unit: the loop. produce, check, correct, repeat until green ↳ between units: the graph. split, fan out, merge, gate, send back Prompts → Context → Harness → Loops → Graphs you get parallel work, isolated contexts, and steps that stop running when nothing needs them. the trick is being selective about what becomes a node. only spend a model where judgment lives. merging, ranking, deduping and schema checks are edges, and edges are code. free, instant, and they cannot be argued out of a verdict. a graph where every edge is an agent pays rent on its own wiring. one thing to know before you scale it. a graph has two return paths, and almost everyone builds one. ↳ the correction edge is short. a gate rejects one unit back to the step that produced it, and it fixes the run you are in ↳ the learning edge is long. an accepted result goes back to the splitter as a constraint, and it fixes every run after skip the second and you get a graph that is fast and never gets smarter. next week it starts from the same place with the same blind spots. and a smaller one that eats whole nights: when a unit fails, return that unit, not the batch. send back four slices because one failed and you have just rewritten three correct ones. do it twice in a run and the run never converges. below i have quoted my full guide on graph engineering. it covers the three topologies, the verifier patterns, and where the gate should actually open. save this and read it below ↓show more

ANTHROPIC LEAD ENGINEER MAKING $2.3M/YEAR JUST LEAKED A 12-PAGE... DOCUMENT - AND GOT FIRED 15 MINUTES AFTER PUBLISHING most developers build loops - but almost every loop breaks in one of five ways, and each failure has a symptom visible from the outside without reading a single line of code > Blind loop - the agent waits for a human to hand it work every morning - automating execution but not discovery > Tangled loop - parallel agents share one directory and overwrite each other parallelism that destroys instead of multiplies > Nodding loop - the agent grades its own work and approves it every time a loop that has never said no to itself is broken > Amnesiac loop - results live only in the context window every morning the system wakes up with no memory of yesterday > Manual loop - no trigger a human presses the button to start it that is not a loop that is a script waiting for a person a real loop finds its own work - remembers what it did has something that can say no never lets two agents touch the same file and fires itself on a timer remove any one of the five - and the loop either breaks or never starts 12 pages that changed how I build agentic systems todayshow more

OBSIDIAN TURNED 4,000+ IDEAS INTO A KNOWLEDGE GRAPH THAT... REBUILDS ITSELF EVERY NIGHT every lecture adds another point. every saved article adds another signal. every old note becomes part of the map again instead of sitting dead inside a folder. a $599 mac mini runs the loop 24/7, claude extracts the useful parts, verifies the note, then links it to 2-3 related ideas inside obsidian before saving it back into the vault. after 30 days the graph starts getting dense. random notes become clusters, forgotten ideas resurface, and the whole system begins to look less like storage and more like a private memory engine. this is what a second brain looks like when it stops waiting for you to open the app.show more

HOW TO USE AI LOOPS TO RUN YOUR BUSINESS... 24/7 A lot has been written about loop engineering for building products. Almost nothing about using loops to run the business itself. That's the bigger idea. A loop is when you give an agent a goal, a way to check its own work, and permission to keep trying until it hits that goal. Build. Verify. Repeat. Stop when the condition is met. Here's what it looks like in practice: 1/SEO loop You're position 30 for a term you want. The loop runs once a month, makes changes, checks where you rank, and keeps pushing until you're on page one. This is running in production right now on Inbox Zero. 2/Ads loop You're spending $100 a day and losing money. The loop tests creative, checks profitability, kills what fails, and keeps going until the account is in the black. 3/Eval loop Your AI feature is only 88% accurate. The loop keeps adjusting the prompt and swapping the model until it passes 90%. 4/LLM visibility loop People search in ChatGPT now, not just Google. Same loop, new scoreboard. Are we the answer or not? The whole thing hinges on one thing: a metric that comes back black and white. Where do I rank? Did it hit profitability? Did the evals pass? Give an agent that scoreboard and it runs for months. Loops used to run for 30 minutes. These run for a year. Take a step, sleep, wake up next month, take another one. You're basically hiring an agency that never sleeps, gets paid in tokens instead of invoices, and undoes its own mistakes when the number goes down. Full episode on The Startup Ideas Podcast (SIP) 🧃 watchshow more

context engineering vs graph engineering. every few months the... list gets a new word and everyone treats it as a replacement for the last one. these two are not on the same list. one decides what the model sees this turn, the other decides what exists at all. the cleanest way to tell them apart is to ask what a single unit of work looks like. > context engineering is the window the window opens empty, every single time. you assemble what goes in it. the prompt, the docs, the history, the tool results. the assembling is the work. the window only grows. it never shrinks on its own, so eventually something gets dropped. usually from the middle. usually without telling you. then the turn ends and the window is thrown away. not archived, thrown away. the next turn opens empty again and you re-explain what you already explained. good context engineering is knowing what to leave out, not what to pack in. the unit of work is one window. > graph engineering is the structure the same material arrives from the same sources. instead of packing it into a window, you pull entities out of it, resolve the duplicates into one node, and write typed edges between them. nothing here is stored as text you hope to find again. it is stored as a thing with a name and its connections to other things. when the turn ends, the graph is still there. the next turn does not start from zero. it starts by querying what already exists, and the query walks edges instead of guessing at similarity. good graph engineering is deciding what counts as the same thing twice. the unit of work is one relationship. > they are not alternatives the graph is what refills the window. context engineering decides what fits. graph engineering decides what there is to choose from. remove the graph and every session starts blind. remove the context work and the best structure in the world arrives as an unreadable dump. that also tells you which one broke. the answer drifted from what you actually said, or forgot something from this same session. that is the window. the answer is coherent but invents a connection that does not exist, or cannot join two facts it has clearly seen. that is the structure. people debug the prompt because the prompt is the easiest thing to edit. it keeps taking the blame for failures that live a layer down. save this - then read the full breakdown belowshow more

THIS GUY BUILT AN AUTONOMOUS AI AGENT OUT OF... CLAUDE CODE + OBSIDIAN and this is way more interesting than another “use AI to take notes” demo the trick is simple: Obsidian is not the writing app here. it becomes the agent’s memory, task board, and context folder. Claude Code is not just answering prompts. it reads the vault, edits files, follows instructions, and keeps moving through the work like a junior operator with a filesystem. the reusable setup looks like this: 1. create an Obsidian vault for one project 2. keep goals, rules, tasks, decisions, and references as markdown files 3. point Claude Code at the folder 4. give it a clear operating loop: read context → choose next task → execute → write back what changed 5. use the notes as persistent memory instead of re-explaining the project every chat that’s the part people miss. the “agent” is not magic. it’s the boring combination of: - local files - explicit rules - task state - write access - a model that can run through the repo/vault Obsidian makes the memory human-readable. Claude Code makes the memory executable. that combo is why the video worked: it turns a notes app into an operating surface for actual work. best use cases: - content systems - research vaults - coding projects - client ops docs - personal knowledge bases that need actions, not just storage the caveat: if your vault is messy, your agent becomes messy too. folders, naming, “done” criteria, and forbidden actions matter more than the prompt. but once the structure is clean, this is one of the easiest ways to build an agent that remembers what happened yesterday without paying for a full custom app.show more

Obsidian + Claude Code turned a 4,300-note vault into... a second brain that answers back. Most people use Obsidian as a graveyard. You save 40 highlights a week, link nothing, and reread maybe 2% of it. The knowledge is there the retrieval is dead. Claude Code fixes the retrieval, because your vault is just a folder of markdown files and Claude Code lives in folders. The whole setup takes 20 minutes: Open a terminal inside your Obsidian folder and run Claude Code no plugins, no API glue, no export step. It reads all 4,300 files natively. Then drop a CLAUDE.md at the vault root explaining your structure: where daily notes live, how you tag, what your MOCs are. Now every session starts with context instead of chaos. From there you just talk to your vault: > "find every note where I mentioned churn and write a summary with backlinks" > "read my last 30 daily notes and list the 5 ideas I keep circling but never ship" > "build a MOC for everything tagged startup-ideas and link the orphan notes into it" It writes new notes straight into the vault with proper [[wikilinks]], and they show up in your graph view 10 seconds later. The boring layer automates too one command cleans broken links, one merges duplicates, one turns 6 months of meeting notes into a single decisions log. Work that used to eat a Sunday now runs while you make coffee. Before: 4,300 notes, 900 orphans, search by keyword and prayer. After: an agent that read everything you ever wrote and drafts in your own voice, from your own sources, with receipts. People pay $30/month for AI note apps with 10% of this. You already own the other 90%. Your notes stopped being storage. They started being staff.show more

ChatGPT can write you a thousand trading strategies from... one sentence. 999 will quietly bleed your account dry. Every single one of them looks like a winner. One method pulls the real one out. Quant desks have run it for years. It's called loop engineering. It's not a smarter prompt. It's a loop: generate a strategy, test it, score why it failed, feed that back, and run it again until one survives data it has never seen. Man Group runs $150 billion. They built an AI that writes and tests hundreds of strategies a week. And second agent whose only job is to hunt the ones that secretly overfit and kill them before a cent goes live. > describe an idea -> backtest 5 years in 12 seconds > read why it died -> feed that back in > run it again until one survives data it never saw AI can write a thousand strategies. Loop engineering is the only thing that tells you which one was ever real. 89% of retail lost money in 2025. Almost none of it from bad ideas. All of it from trading the first guess and never running it through backtest loop. Horizon just put the whole thing in a chat box, free while the beta's open: You're not losing to smarter traders. You're losing to the ones who opened the tab. Anyone can generate a strategy now. Almost no one runs the loop that proves it. That gap is the whole edge. You'll mean to check it later. Later is a "waitlist closed" page.show more