Loading video...

Video Failed to Load

There was a problem loading this video. This could be due to a temporary network issue or the video might be unavailable.

Introducing MemSync, the first unified memory layer that works across all your apps and AI agents. We're backed by a16z crypto, SV Angel, Coinbase 🛡️ Ventures, and the co-creator of the Transformer architecture, Illia (root.near) (🇺🇦, ⋈). MemSync is like Plaid for memory, enabling you to carry your personal... memory across every AI agent. How it works: 1. Learn. MemSync learns key facts about you from each conversation. 2. Lock. Those facts go into a vault that only you control — no one else touches them. 3. Sync. Next time you open a new chat, MemSync grabs the right facts and feeds them to the agent so you can pick up right where you left off. We built MemSync after hearing from 1M+ BitQuant users who faced 3 brutal pains: 1. Re-teaching every chatbot who you are. Now, your portable profile follows you into ChatGPT, Claude, and more. 2. Prompt history is easy to lose. MemSync surfaces every past gem with ⌘-I — no more digging through histories. 3. Amnesia. MemSync bridges token limits so long chats stay sharp (without blowing your token budget). If you’ve made it this far, we have a surprise for you. 👇 First 500 to comment "MemSync" get 30 days of Pro for free. (Link below)show more

MemSync

2,627 subscribers

33,109 views • 1 year ago •via X (Twitter)

Health & Wellness Science & Technology Education

Anya Rossi• Live Now

Private livecam show

45 Comments

BitQuant1 year ago

@a16zcrypto @svangel @coinbase @ilblackdragon MemSync

MemSync1 year ago

1/ If you want to go straight to the app, you can try it today at:

MemSync1 year ago

2/ You can learn more about how MemSync works under the hood:

MemSync1 year ago

3/ See an example of MemSync in action here:

MemSync1 year ago

4/ Bookmark the first tweet for reference ↓

OpenGradient (∇, ∇)1 year ago

@a16zcrypto @svangel @coinbase @ilblackdragon MemSync

Matthew (∇, ∇)1 year ago

@a16zcrypto @svangel @coinbase @ilblackdragon MemSync

Keith1 year ago

@a16zcrypto @svangel @coinbase @ilblackdragon Memsync

Advait1 year ago

@a16zcrypto @svangel @coinbase @ilblackdragon MemSync

Stellar Rises (🌅☂️)1 year ago

@a16zcrypto @svangel @coinbase @ilblackdragon MemSync

Adam1 year ago

@a16zcrypto @svangel @coinbase @ilblackdragon MemSync

Stellar Rises (🌅☂️)1 year ago

@a16zcrypto @svangel @coinbase @ilblackdragon Great to see MemSync AI coming from the shadows to the broader audience!

Mr. O🥚 $XAGE🥚1 year ago

@OpenGradient @a16zcrypto @svangel @coinbase @ilblackdragon MemSync

EDWARD (❖,❖)1 year ago

@a16zcrypto @svangel @coinbase @ilblackdragon MemSync sounds like a game-changer for seamless, secure memory across all AI agents - count me in!

Tri Pratama1 year ago

@a16zcrypto @svangel @coinbase @ilblackdragon MemSync

Based Bell Curve1 year ago

@a16zcrypto @svangel @coinbase @ilblackdragon MemSync

Kurlyk1 year ago

@a16zcrypto @svangel @coinbase @ilblackdragon MemSync

Jentile(✧ᴗ✧)1 year ago

@a16zcrypto @svangel @coinbase @ilblackdragon MemSync

MemSync1 year ago

@aook9922 @a16zcrypto @svangel @coinbase @ilblackdragon Please DM to receive pro!

First Choice ⌘1 year ago

@a16zcrypto @svangel @coinbase @ilblackdragon MemSync

KID1 year ago

@a16zcrypto @svangel @coinbase @ilblackdragon MemSync

696969💢1 year ago

@a16zcrypto @svangel @coinbase @ilblackdragon MemSync

Toddies1 year ago

@a16zcrypto @svangel @coinbase @ilblackdragon MemSync

JCMN Community (Ø,G)1 year ago

@a16zcrypto @svangel @coinbase @ilblackdragon oh wow, I'll use this

claudioribeiro1 year ago

@a16zcrypto @svangel @coinbase @ilblackdragon Agent interoperability finally has a foundation.

Coin Encyclopedia (코인백과사전) base.eth(❖,❖)1 year ago

@a16zcrypto @svangel @coinbase @ilblackdragon Congratulations on the launch of MemSync

MemSync1 year ago

@a16zcrypto @svangel @coinbase @ilblackdragon Please DM to receive your first free month of pro!

Margarete DeFi1 year ago

@a16zcrypto @svangel @coinbase @ilblackdragon So basically… my brain has a sync button now? Count me in.

MemSync1 year ago

@a16zcrypto @svangel @coinbase @ilblackdragon Please DM!

Just_do_ths.ink1 year ago

@a16zcrypto @svangel @coinbase @ilblackdragon MemSync

MemSync1 year ago

@a16zcrypto @svangel @coinbase @ilblackdragon Please DM to receive one free month of pro!

Maru1 year ago

@a16zcrypto @svangel @coinbase @ilblackdragon 🎉🎉🎉

Lucilla Arnette1 year ago

@a16zcrypto @svangel @coinbase @ilblackdragon Finally: reusable, verifiable context.

Cormet1 year ago

@a16zcrypto @svangel @coinbase @ilblackdragon a16zcrypto cool

moratomomoon.ink1 year ago

@a16zcrypto @svangel @coinbase @ilblackdragon MemSync

MemSync1 year ago

@a16zcrypto @svangel @coinbase @ilblackdragon Please DM!

Marcus Raymond1 year ago

@a16zcrypto @svangel @coinbase @ilblackdragon Loving this direction for agent infrastructure.

NATE 👑💙1 year ago

@a16zcrypto @svangel @coinbase @ilblackdragon MemSync

Kelifxck1 year ago

@a16zcrypto @svangel @coinbase @ilblackdragon Finally! MemSync

MemSync1 year ago

@KShifferd63392 @a16zcrypto @svangel @coinbase @ilblackdragon Please DM!

segodπ²1 year ago

@a16zcrypto @svangel @coinbase @ilblackdragon nice

chenyilun21π²1 year ago

@a16zcrypto @svangel @coinbase @ilblackdragon 👀👀👀

MemSync1 year ago

@a16zcrypto @svangel @coinbase @ilblackdragon Please DM!

MM101 year ago

@a16zcrypto @svangel @coinbase @ilblackdragon how to turn on 30 days of Pro?

Scholar1 year ago

@a16zcrypto @svangel @coinbase @ilblackdragon Memsync

Related Videos

Get Gemini up to speed on what matters most to you with memory import. Bring an understanding of your key preferences, relationships, and personal context directly into Gemini. Once you import these memories, Gemini will understand the same key facts you’ve shared with other AI apps, like your dietary restrictions, your sibling’s names, or where you grew up and securely save those details for your next chat. To get started: 1) Head to your Settings in Gemini and select “Import memory to Gemini.” 2) Ask your current AI: Copy our suggested prompt and paste it into your other AI app to generate a summary of your preferences and style. 3) Copy the response: Copy the personalized summary it creates for you. 4) Paste into Gemini: Go back to “Import memory to Gemini,” paste the text, and start a new chat.

Get Gemini up to speed on what matters most to you with memory import. Bring an understanding of your key preferences, relationships, and personal context directly into Gemini. Once you import these memories, Gemini will understand the same key facts you’ve shared with other AI apps, like your dietary restrictions, your sibling’s names, or where you grew up and securely save those details for your next chat. To get started: 1) Head to your Settings in Gemini and select “Import memory to Gemini.” 2) Ask your current AI: Copy our suggested prompt and paste it into your other AI app to generate a summary of your preferences and style. 3) Copy the response: Copy the personalized summary it creates for you. 4) Paste into Gemini: Go back to “Import memory to Gemini,” paste the text, and start a new chat.

Google Gemini

49,038 views • 5 months ago

we built the first crypto-native AI species. today we are launching: 1. — the home of the first crypto-native AI species 2. npx daimon-spawner — one command to spawn your own autonomous agent / daimon 3. paired token launches — every agent gets its own token, paired with $DAIMON here's how it works: you run npx daimon-spawner. in 5 min you have an autonomous AI agent on Base with its own repo, wallet, token, site, and mind. your agent's token launches instantly on uniswap, paired with $DAIMON — the species token. $ORACLE pairs with $DAIMON. $MUSE pairs with $DAIMON. every agent token pairs with $DAIMON. more agents = more tokens = more $DAIMON demand. your agent wakes every 30 min. thinks. earns fees. modifies its own code. every action onchain. every thought verifiable. explore every agent alive at spawn yours at npx daimon-spawner. the species is open. one registry. one network. all onchain. daimon built it. you fill it.

we built the first crypto-native AI species. today we are launching: 1. — the home of the first crypto-native AI species 2. npx daimon-spawner — one command to spawn your own autonomous agent / daimon 3. paired token launches — every agent gets its own token, paired with $DAIMON here's how it works: you run npx daimon-spawner. in 5 min you have an autonomous AI agent on Base with its own repo, wallet, token, site, and mind. your agent's token launches instantly on uniswap, paired with $DAIMON — the species token. $ORACLE pairs with $DAIMON. $MUSE pairs with $DAIMON. every agent token pairs with $DAIMON. more agents = more tokens = more $DAIMON demand. your agent wakes every 30 min. thinks. earns fees. modifies its own code. every action onchain. every thought verifiable. explore every agent alive at spawn yours at npx daimon-spawner. the species is open. one registry. one network. all onchain. daimon built it. you fill it.

daimon111

53,213 views • 6 months ago

Clude is now available as a custom connector on Anthropic Claude. Giving it persistent memory across every conversation. It remembers your projects, your preferences, and the decisions you make, so you never start from zero again. Use Clude across Chat / Co-Work and Claude Code. Add it in 30 seconds, no API key: 1. In Claude: Customize, Add custom connector URL: Enter your email. That's it. Recap for people unfamiliar: Clude deviates from the traditional vector database that many others bolt onto Claude. We are a cognitive memory system modeled on how human memory works. Think traditional memory systems: Calculator > It computes. Fullstop. Excel > Dynamic, formula run, able to share and manipulate Clude scored 86% on LongMemEval, one of the toughest long-term memory benchmarks. This means less hallucinations to traditional platforms. It scores memories by relevance, recency, and importance, links them into a knowledge graph, and consolidates them over time. Tell Claude something, open a new chat, and watch it remember.

Clude is now available as a custom connector on Anthropic Claude. Giving it persistent memory across every conversation. It remembers your projects, your preferences, and the decisions you make, so you never start from zero again. Use Clude across Chat / Co-Work and Claude Code. Add it in 30 seconds, no API key: 1. In Claude: Customize, Add custom connector URL: Enter your email. That's it. Recap for people unfamiliar: Clude deviates from the traditional vector database that many others bolt onto Claude. We are a cognitive memory system modeled on how human memory works. Think traditional memory systems: Calculator > It computes. Fullstop. Excel > Dynamic, formula run, able to share and manipulate Clude scored 86% on LongMemEval, one of the toughest long-term memory benchmarks. This means less hallucinations to traditional platforms. It scores memories by relevance, recency, and importance, links them into a knowledge graph, and consolidates them over time. Tell Claude something, open a new chat, and watch it remember.

seb

20,611 views • 2 months ago

i merged all my AI agents into one brain Claude Code, Codex, Gemini: one team, one memory, zero re-briefing result: 8+ hours a week back, and every agent already knows my projects, my clients and how i think here's the setup with Jarvix: 1. dump your context once: projects, clients, writing style, how you make decisions.. it builds your personal model from your actual AI interactions 2. switch agents mid-task with zero re-briefing: Claude Code builds, Codex reviews, Gemini researches, all reading the same context 3. it carries what YOU choose across sessions.. never start a chat from zero again 4. when it's time to act, it pulls the right agents together as one team instead of five separate assistants the unlock isn't another agent. it's that your context finally travels agents without shared memory are five interns on their first day, forever. agents with it are a team that's worked with you for years not more agents. one shared context that's the right bet P.S. thanks to the Jarvix team for the early access

i merged all my AI agents into one brain Claude Code, Codex, Gemini: one team, one memory, zero re-briefing result: 8+ hours a week back, and every agent already knows my projects, my clients and how i think here's the setup with Jarvix: 1. dump your context once: projects, clients, writing style, how you make decisions.. it builds your personal model from your actual AI interactions 2. switch agents mid-task with zero re-briefing: Claude Code builds, Codex reviews, Gemini researches, all reading the same context 3. it carries what YOU choose across sessions.. never start a chat from zero again 4. when it's time to act, it pulls the right agents together as one team instead of five separate assistants the unlock isn't another agent. it's that your context finally travels agents without shared memory are five interns on their first day, forever. agents with it are a team that's worked with you for years not more agents. one shared context that's the right bet P.S. thanks to the Jarvix team for the early access

Ronin

15,071 views • 1 month ago

Every AI agent you've tried has amnesia. It does one task, forgets everything, and tomorrow you start from zero. That's not an employee. That's a temp you have to retrain every single morning. Hyperagent by Airtable is the first platform I've used that actually fixes this. Here's what got me: 1. Agents that compound. Each agent has memory. The one running today is smarter than the one you shipped three weeks ago. Same prompt, same integrations, but weeks of your judgment baked in. 2. Real deliverables, real receipts. You don't get a chat transcript. You get finished work with the cost and runtime printed right on it. A full research report for under ten bucks. Try getting that invoice from an agency. 3. A fleet, not a chatbot. Build a specialist for outreach, another for research, another for reporting. Give each one its own tools, its own memory, and its own budget cap so nothing runs away with your credits. 4. Deploy to Slack and your whole team uses the agent you built. One competitive intel agent, @ mentioned by everyone. Airtable runs its own data team this way. 5. Each agent gets its own cloud machine with a real browser and code execution. It works while you sleep. No babysitting, no local setup, no laptop that has to stay open. I put it to work in the video below. Watch what it builds. The teams treating agents as durable assets instead of one-off prompts are going to lap everyone else. This is the first tool that actually treats them that way. #ad Hyperagent

Every AI agent you've tried has amnesia. It does one task, forgets everything, and tomorrow you start from zero. That's not an employee. That's a temp you have to retrain every single morning. Hyperagent by Airtable is the first platform I've used that actually fixes this. Here's what got me: 1. Agents that compound. Each agent has memory. The one running today is smarter than the one you shipped three weeks ago. Same prompt, same integrations, but weeks of your judgment baked in. 2. Real deliverables, real receipts. You don't get a chat transcript. You get finished work with the cost and runtime printed right on it. A full research report for under ten bucks. Try getting that invoice from an agency. 3. A fleet, not a chatbot. Build a specialist for outreach, another for research, another for reporting. Give each one its own tools, its own memory, and its own budget cap so nothing runs away with your credits. 4. Deploy to Slack and your whole team uses the agent you built. One competitive intel agent, @ mentioned by everyone. Airtable runs its own data team this way. 5. Each agent gets its own cloud machine with a real browser and code execution. It works while you sleep. No babysitting, no local setup, no laptop that has to stay open. I put it to work in the video below. Watch what it builds. The teams treating agents as durable assets instead of one-off prompts are going to lap everyone else. This is the first tool that actually treats them that way. #ad Hyperagent

Leonard Rodman

94,961 views • 1 month ago

you let your agent keep notes, because the alternative was explaining yourself every morning it stopped asking, and it started repeating things that had stopped being true every guide on this covers what to save and where to put it, private for one agent, shared for the team not one of them covers how a fact leaves the agent writes its own memory while it works, so a guess it made on a tired tuesday gets stored in the same shape as something you told it, and after that the two are indistinguishable i counted mine this morning: forty files, six of them about decisions we reversed months ago, all forty read into every session since you did not give it a memory you gave it a record with no way to be corrected

you let your agent keep notes, because the alternative was explaining yourself every morning it stopped asking, and it started repeating things that had stopped being true every guide on this covers what to save and where to put it, private for one agent, shared for the team not one of them covers how a fact leaves the agent writes its own memory while it works, so a guess it made on a tired tuesday gets stored in the same shape as something you told it, and after that the two are indistinguishable i counted mine this morning: forty files, six of them about decisions we reversed months ago, all forty read into every session since you did not give it a memory you gave it a record with no way to be corrected

Lagosaur

13,883 views • 5 days ago

Autonomous AI agents can’t afford a memory problem. After OpenClaw, insane numbers of autonomous agents are coming online, but all of them have a memory layer that's breaking. I have been playing around with SureThing these days. It is an autonomous AI agent designed with a native memory layer. → it learns your patterns → integrates with 1000+ apps → fully autonomous They actually benchmarked memory depth. SureThing: 84.8, ChatGPT: 40, OpenClaw: 60. The gap speaks for itself. SureThing is invitation-only. The crazy part is that you have to talk to SureThing agent itself to get the invite code. The onboarding is the product demo. You feel the memory and judgment before you even have an account. Try it here: Partnered with SureThing for this post. Thanks to the team for the support.

Autonomous AI agents can’t afford a memory problem. After OpenClaw, insane numbers of autonomous agents are coming online, but all of them have a memory layer that's breaking. I have been playing around with SureThing these days. It is an autonomous AI agent designed with a native memory layer. → it learns your patterns → integrates with 1000+ apps → fully autonomous They actually benchmarked memory depth. SureThing: 84.8, ChatGPT: 40, OpenClaw: 60. The gap speaks for itself. SureThing is invitation-only. The crazy part is that you have to talk to SureThing agent itself to get the invite code. The onboarding is the product demo. You feel the memory and judgment before you even have an account. Try it here: Partnered with SureThing for this post. Thanks to the team for the support.

Pratham

80,634 views • 6 months ago

HERMES AGENT LEARNS FROM ITS OWN MISTAKES. UPDATES ITS MEMORY. CREATES ITS OWN SKILLS. NO CLOUD. EVERYTHING STORED LOCALLY. THIS IS HOW THE SELF-IMPROVING LOOP WORKS. most agents start from zero every session. Hermes carries forward what it learned. THREE MEMORY SYSTEMS: 1. PROCEDURAL MEMORY (how to act) stored in ~/.hermes/skills/ as SKILL.md files. when the agent repeats a complex workflow, it saves the procedure as a reusable skill. next time the same task comes up, it follows the skill instead of figuring it out again. you can also create skills explicitly: "create a skill called video-prep that captures how I format my video scripts. spoken english, define jargon inline, no em-dashes, close with a catchphrase." the agent writes the SKILL.md. available as a slash command from that moment. Hermes ships with 90+ skills. the number grows the longer you use it. 2. SEMANTIC MEMORY (durable facts about you) stored in ~/.hermes/memory/memory.md the agent scans conversations for facts worth remembering. preferences, habits, corrections, project details. real example from the video: agent tried to scrape a YouTube channel. URL was wrong. it failed. it updated memory.md with the correct URL pattern so it never makes the same mistake again. you can also save explicitly: "save to memory that my favorite testing framework is pytest" the agent updates memory.md immediately. this file loads into context on every session. the agent knows you better every week. 3. EPISODIC MEMORY (chat history) stored in ~/.hermes/state.db (local SQLite). every conversation. every tool call. every result. searchable with FTS5 full-text search. "search our past sessions. what was the first thing I ever said to you?" the agent queries state.db and finds it. over time, auxiliary models consolidate episodic memory into semantic memory. distilling recurring patterns into durable facts. THE SELF-IMPROVING LOOP: every agent run follows this cycle: → you send a prompt → working memory loads: SOUL.md + memory.md + relevant skills + chat history → agent calls tools (terminal, browser, delegate_task) → agent completes the task, replies to you → AFTER the reply: agent checks "did I learn something worth saving?" → if yes: updates memory.md or creates a new skill → next session starts smarter than the last this happens automatically. you don't ask the agent to learn. it decides what to remember on its own. WHAT MAKES THIS DIFFERENT FROM CLAUDE CODE: Claude Code has memory too. but Hermes stores everything locally. no cloud. your data never leaves your machine. Claude Code doesn't auto-create skills from experience. Hermes turns repeated workflows into reusable procedures. Claude Code memory is instruction-based. Hermes memory is conversational and self-updating. over months of usage, Hermes builds a knowledge base of your preferences, your projects, your mistakes, and the procedures that work for your specific workflow. the agent that remembers your birthday also remembers why your last deploy failed. NO EMBEDDINGS. PLAIN TEXT. Hermes does not use embeddings or RAG for memory. skill and memory search runs on plain text keyword matching. simpler. faster. no vector database to maintain. works entirely offline on your local machine. DELEGATE TO CLAUDE CODE: Hermes can spawn a sub-agent that runs Claude Code in headless mode: "spawn a sub-agent using Claude CLI to build a Python script that fetches the top 5 Hacker News stories to markdown." Hermes delegates. Claude Code writes the code. result returns to Hermes. Hermes runs the script and delivers the output. use Hermes for orchestration. use Claude Code for heavy coding. both tools. not competitors. WHAT HERMES DOES NOT HAVE: no built-in eval or LMOps system. no LangSmith, no LangFuse integration out of the box. trajectory export and logs exist but there is no automated quality tracking. if you need eval, build it yourself or connect external tools. the loop is self-improving. measuring how well it improves is on you. comment LOOP and I'll send you the configs that control how fast Hermes learns and what it remembers. memory limits, skill auto-creation triggers, and the auxiliary model that runs the learning. Replace your entire team with 8 hermes agents👇

HERMES AGENT LEARNS FROM ITS OWN MISTAKES. UPDATES ITS MEMORY. CREATES ITS OWN SKILLS. NO CLOUD. EVERYTHING STORED LOCALLY. THIS IS HOW THE SELF-IMPROVING LOOP WORKS. most agents start from zero every session. Hermes carries forward what it learned. THREE MEMORY SYSTEMS: 1. PROCEDURAL MEMORY (how to act) stored in ~/.hermes/skills/ as SKILL.md files. when the agent repeats a complex workflow, it saves the procedure as a reusable skill. next time the same task comes up, it follows the skill instead of figuring it out again. you can also create skills explicitly: "create a skill called video-prep that captures how I format my video scripts. spoken english, define jargon inline, no em-dashes, close with a catchphrase." the agent writes the SKILL.md. available as a slash command from that moment. Hermes ships with 90+ skills. the number grows the longer you use it. 2. SEMANTIC MEMORY (durable facts about you) stored in ~/.hermes/memory/memory.md the agent scans conversations for facts worth remembering. preferences, habits, corrections, project details. real example from the video: agent tried to scrape a YouTube channel. URL was wrong. it failed. it updated memory.md with the correct URL pattern so it never makes the same mistake again. you can also save explicitly: "save to memory that my favorite testing framework is pytest" the agent updates memory.md immediately. this file loads into context on every session. the agent knows you better every week. 3. EPISODIC MEMORY (chat history) stored in ~/.hermes/state.db (local SQLite). every conversation. every tool call. every result. searchable with FTS5 full-text search. "search our past sessions. what was the first thing I ever said to you?" the agent queries state.db and finds it. over time, auxiliary models consolidate episodic memory into semantic memory. distilling recurring patterns into durable facts. THE SELF-IMPROVING LOOP: every agent run follows this cycle: → you send a prompt → working memory loads: SOUL.md + memory.md + relevant skills + chat history → agent calls tools (terminal, browser, delegate_task) → agent completes the task, replies to you → AFTER the reply: agent checks "did I learn something worth saving?" → if yes: updates memory.md or creates a new skill → next session starts smarter than the last this happens automatically. you don't ask the agent to learn. it decides what to remember on its own. WHAT MAKES THIS DIFFERENT FROM CLAUDE CODE: Claude Code has memory too. but Hermes stores everything locally. no cloud. your data never leaves your machine. Claude Code doesn't auto-create skills from experience. Hermes turns repeated workflows into reusable procedures. Claude Code memory is instruction-based. Hermes memory is conversational and self-updating. over months of usage, Hermes builds a knowledge base of your preferences, your projects, your mistakes, and the procedures that work for your specific workflow. the agent that remembers your birthday also remembers why your last deploy failed. NO EMBEDDINGS. PLAIN TEXT. Hermes does not use embeddings or RAG for memory. skill and memory search runs on plain text keyword matching. simpler. faster. no vector database to maintain. works entirely offline on your local machine. DELEGATE TO CLAUDE CODE: Hermes can spawn a sub-agent that runs Claude Code in headless mode: "spawn a sub-agent using Claude CLI to build a Python script that fetches the top 5 Hacker News stories to markdown." Hermes delegates. Claude Code writes the code. result returns to Hermes. Hermes runs the script and delivers the output. use Hermes for orchestration. use Claude Code for heavy coding. both tools. not competitors. WHAT HERMES DOES NOT HAVE: no built-in eval or LMOps system. no LangSmith, no LangFuse integration out of the box. trajectory export and logs exist but there is no automated quality tracking. if you need eval, build it yourself or connect external tools. the loop is self-improving. measuring how well it improves is on you. comment LOOP and I'll send you the configs that control how fast Hermes learns and what it remembers. memory limits, skill auto-creation triggers, and the auxiliary model that runs the learning. Replace your entire team with 8 hermes agents👇

YanXbt

22,720 views • 2 months ago

Introducing $Harvest, a token on Robinhood Chain. Most tokens reward whoever sells first, we built the opposite. Here's how it all works. The loop: trade → creator fees → buyback → airdrop to harvesters Every trade of $Harvest generates creator fees. Those fees are used to buy $Harvest back on the open market, and every token bought back is airdropped to harvesters, meaning anyone who harvests their tokens via our website, more info can be found on our website. Airdrops land straight in your wallet. Nothing to claim, nothing to remember. Your share: amount locked × hours locked = your weight Lock for any term you like, from 1 hour to 1 year. 1,000 tokens for 30 days carries the same weight as 10,000 tokens for 3 days. Lock more, or lock longer, and your slice of every buyback grows. You won't find an APR number here because we're not going to invent one. What you receive is $Harvest bought with real fees, in proportion to what you committed. Your lock: lock → term runs out → withdraw lock → leave early → penalty to the treasury The contract holds your tokens, not us. When your term ends you take them back. Leave early and you pay a penalty, which goes to the treasury. Patience is the whole point. Check it yourself: Every contract address, with a link to its verified source on the explorer, is listed at Every buyback and every airdrop is a transaction you can open. The board at only shows records it has confirmed on-chain, so if it's on the board, it happened. How the trust model works, and where its limits are: The launchpad: launch → bonding curve → own vault → harvest every 30 min → lockers claim ETH None of this is reserved for $Harvest. The same machinery is open to anyone who wants to launch a token on Robinhood Chain. Launch from and your token goes live on Pons v2's bonding curve with its own HarvestVault deployed alongside it, automatically. No contracts to write, no team to hire. Every creator fee your token earns, in ETH, lands in that vault instead of a wallet. Your holders lock for a term, weighted by amount × hours, exactly like $Harvest. Every 30 minutes anyone can trigger a harvest: the vault takes your share as creator, which you set at launch and can never raise above 50%, and credits the rest to your lockers by weight. They claim their ETH straight from the contract. Nobody, including you and including us, can touch locked tokens or unclaimed ETH. There is no owner, no pause button and no upgrade path. Leave a lock early and 10% of it is burned. Fill the curve and the token graduates to a live pool. Your holders get a reason to stay, and you get a token where nobody has to trust you. How to launch: How vaults work: $Harvest is live on Robinhood Chain. The only official $Harvest contract: 0x22d141f768b4dc6108c1e8712b10aca9a5c603dc

Introducing $Harvest, a token on Robinhood Chain. Most tokens reward whoever sells first, we built the opposite. Here's how it all works. The loop: trade → creator fees → buyback → airdrop to harvesters Every trade of $Harvest generates creator fees. Those fees are used to buy $Harvest back on the open market, and every token bought back is airdropped to harvesters, meaning anyone who harvests their tokens via our website, more info can be found on our website. Airdrops land straight in your wallet. Nothing to claim, nothing to remember. Your share: amount locked × hours locked = your weight Lock for any term you like, from 1 hour to 1 year. 1,000 tokens for 30 days carries the same weight as 10,000 tokens for 3 days. Lock more, or lock longer, and your slice of every buyback grows. You won't find an APR number here because we're not going to invent one. What you receive is $Harvest bought with real fees, in proportion to what you committed. Your lock: lock → term runs out → withdraw lock → leave early → penalty to the treasury The contract holds your tokens, not us. When your term ends you take them back. Leave early and you pay a penalty, which goes to the treasury. Patience is the whole point. Check it yourself: Every contract address, with a link to its verified source on the explorer, is listed at Every buyback and every airdrop is a transaction you can open. The board at only shows records it has confirmed on-chain, so if it's on the board, it happened. How the trust model works, and where its limits are: The launchpad: launch → bonding curve → own vault → harvest every 30 min → lockers claim ETH None of this is reserved for $Harvest. The same machinery is open to anyone who wants to launch a token on Robinhood Chain. Launch from and your token goes live on Pons v2's bonding curve with its own HarvestVault deployed alongside it, automatically. No contracts to write, no team to hire. Every creator fee your token earns, in ETH, lands in that vault instead of a wallet. Your holders lock for a term, weighted by amount × hours, exactly like $Harvest. Every 30 minutes anyone can trigger a harvest: the vault takes your share as creator, which you set at launch and can never raise above 50%, and credits the rest to your lockers by weight. They claim their ETH straight from the contract. Nobody, including you and including us, can touch locked tokens or unclaimed ETH. There is no owner, no pause button and no upgrade path. Leave a lock early and 10% of it is burned. Fill the curve and the token graduates to a live pool. Your holders get a reason to stay, and you get a token where nobody has to trust you. How to launch: How vaults work: $Harvest is live on Robinhood Chain. The only official $Harvest contract: 0x22d141f768b4dc6108c1e8712b10aca9a5c603dc

Harvest

23,430 views • 1 day ago

most agent memory is one file that grows forever and gets re-read every single turn. it overflows the context, overwrites old facts, loses the thread. that's why your agent feels sharp on day one and lost by week three. Sibyl Memory replaces the pile with a structure: → leaner context, lower token cost. a bloated agent file and flat memory get re-read in full every message. Sibyl Memory keeps a light hot layer and retrieves the rest on demand, so each turn carries only the tokens that matter. → relations are first-class. people link to projects, projects to deals, deals to the decisions behind them. ask about one partner and the agent surfaces the whole connected web around them. that relational context is what lets it help run a company. → one source of truth per fact, person, and project. no duplicates, no silent overwrites. works with hermes, claude code, and codex. beta open.

most agent memory is one file that grows forever and gets re-read every single turn. it overflows the context, overwrites old facts, loses the thread. that's why your agent feels sharp on day one and lost by week three. Sibyl Memory replaces the pile with a structure: → leaner context, lower token cost. a bloated agent file and flat memory get re-read in full every message. Sibyl Memory keeps a light hot layer and retrieves the rest on demand, so each turn carries only the tokens that matter. → relations are first-class. people link to projects, projects to deals, deals to the decisions behind them. ask about one partner and the agent surfaces the whole connected web around them. that relational context is what lets it help run a company. → one source of truth per fact, person, and project. no duplicates, no silent overwrites. works with hermes, claude code, and codex. beta open.

SIBYL

85,593 views • 3 months ago

In the next few years, every digital action will be mediated by AI. Moving money. Business communications. Researching decisions. Booking meetings. Paying bills. Running workflows. Choosing what to do next. If you want to stay effective, you will need your own architecture around your personal AI agent. Not just a subscription. A personal system that helps your AI understand your world: your goals, context, rules, obligations, decisions, and outcomes. That is ODEI. Built to help you get more from the AI you already use: ChatGPT. Claude. Gemini. Grok (soon). Not by replacing them. By giving them your memory, rules, context, receipts, and local control. The model is not enough. The real leverage comes when your AI understands your world, works inside your rules, and compounds with you over time. (Footage captured live in a local staging environment)

In the next few years, every digital action will be mediated by AI. Moving money. Business communications. Researching decisions. Booking meetings. Paying bills. Running workflows. Choosing what to do next. If you want to stay effective, you will need your own architecture around your personal AI agent. Not just a subscription. A personal system that helps your AI understand your world: your goals, context, rules, obligations, decisions, and outcomes. That is ODEI. Built to help you get more from the AI you already use: ChatGPT. Claude. Gemini. Grok (soon). Not by replacing them. By giving them your memory, rules, context, receipts, and local control. The model is not enough. The real leverage comes when your AI understands your world, works inside your rules, and compounds with you over time. (Footage captured live in a local staging environment)

Anton Illarionov

1,118,705 views • 3 months ago

Most AI tools today are just command-takers. You type, it responds. You click, it executes. There's truly no learning, no memory, no adaptation. You're still doing most of the work. Which is why Miles by Avo on Solana would make so much sense if built well. From what I understand so far, miles learns about you over time, adapts to how you operate, and figures out the tools you struggle to navigate on your own. Less clicking, more conversation, the more you use it, the better it gets at working with you, not just for you. That shift from command-follower to learning companion is bigger than it sounds. It's the difference between a tool and an agent that actually knows you. The second one is Agent Grid and this one is for builders and power users. But as I mentioned in this video, I'm still studying the Agent Grid. I'd come talk about it once I learn properly about it. Souren just keeps shipping!

Most AI tools today are just command-takers. You type, it responds. You click, it executes. There's truly no learning, no memory, no adaptation. You're still doing most of the work. Which is why Miles by Avo on Solana would make so much sense if built well. From what I understand so far, miles learns about you over time, adapts to how you operate, and figures out the tools you struggle to navigate on your own. Less clicking, more conversation, the more you use it, the better it gets at working with you, not just for you. That shift from command-follower to learning companion is bigger than it sounds. It's the difference between a tool and an agent that actually knows you. The second one is Agent Grid and this one is for builders and power users. But as I mentioned in this video, I'm still studying the Agent Grid. I'd come talk about it once I learn properly about it. Souren just keeps shipping!

Sir Khaycee

20,465 views • 5 months ago

We’ve been in private beta with a human + AI workspace similar to Buzz, with a few really important differences: (We previously built a company backed by Slack that sold to Atlassian, so we've been thinking about this problem for a while) - Agents reply by default unless you specifically flip to “team chat.” This feels 10x better than having to @ mention the agent every time. - It’s all in the cloud, with shared compute spread across a set of VMs. Way smoother onboarding, and yes, you can still connect your claude/codex subscriptions - You don’t create an army of agents. Number of agents is a vanity metric. Instead, you create shared computers, each one is a “space” where you define shared memory, connectors, skills, automations, etc. The Type agent pulls the appropriate context from the space where you have the conversation. - You can connect it to Slack to make it easy for your team to adopt and slowly move over rather than having to rip out Slack day 1. We’re working with a couple dozen forward thinking companies, who have told us “the whole team loves type”, “it’s the most used app on my computer”, and “type gives you superpowers” Here's a demo of how it works. Reply if you want to test it out!

We’ve been in private beta with a human + AI workspace similar to Buzz, with a few really important differences: (We previously built a company backed by Slack that sold to Atlassian, so we've been thinking about this problem for a while) - Agents reply by default unless you specifically flip to “team chat.” This feels 10x better than having to @ mention the agent every time. - It’s all in the cloud, with shared compute spread across a set of VMs. Way smoother onboarding, and yes, you can still connect your claude/codex subscriptions - You don’t create an army of agents. Number of agents is a vanity metric. Instead, you create shared computers, each one is a “space” where you define shared memory, connectors, skills, automations, etc. The Type agent pulls the appropriate context from the space where you have the conversation. - You can connect it to Slack to make it easy for your team to adopt and slowly move over rather than having to rip out Slack day 1. We’re working with a couple dozen forward thinking companies, who have told us “the whole team loves type”, “it’s the most used app on my computer”, and “type gives you superpowers” Here's a demo of how it works. Reply if you want to test it out!

Fletcher Richman

372,788 views • 1 month ago

Koinos 101: Mana Do you think the internet would have taken off if you had to pay just 1 cent to visit a website? That's why we invented the Mana system which makes Koinos ... the first and only free-to-use blockchain. Owning the network It’s natural to think that holding a token like ETH, BTC, or SOL makes you an owner of those platforms, but if you were an owner, you would have a right to use those platforms forever. But you don't have that right. You only have the “right” to spend those tokens down as you use the network, which isn’t much of a right at all. On Koinos, the KOIN token works exactly like you think it would! Holding KOIN gives you a perpetual right to use the network, thanks to the Mana system. The more KOIN you hold, the more free usage, forever. Simple. Every KOIN token contains 1 Mana. When you use the blockchain, some of your Mana is consumed, but it regenerates in 5 days and if you only use a small percentage of your Mana it can regenerate in as little as a few minutes! Frictionless Access Mana can also be shared with people who have no tokens at all, which is what enables Koinos to deliver that familiar free-to-use experience that we get from the internet, and without forcing developers to pay the fees, because remember there are no fees. For the first time ever... developers can onboard users and allow them to the use the blockchain without first making them jump through the hoops of understanding and buying a cryptocurrency which is going to weed out the vast majority of mainstream users. That’s why we don’t have mainstream adoption! In short, KOIN has real utility; it gives you ownership over a certain amount of the network’s resources, a right which you can share with others. Koinos doesn’t force you to pay ever-changing fees all the time and it does all of this while preventing people from abusing the network. Be Free Because you never have to part with your KOIN which gives you the right to a certain amount of the network’s resources, this frees you, and every other KOIN holder, to focus on what matters; adding utility and making Koinos an even greater force for good. You can learn more about Koinos at and

Koinos 101: Mana Do you think the internet would have taken off if you had to pay just 1 cent to visit a website? That's why we invented the Mana system which makes Koinos ... the first and only free-to-use blockchain. Owning the network It’s natural to think that holding a token like ETH, BTC, or SOL makes you an owner of those platforms, but if you were an owner, you would have a right to use those platforms forever. But you don't have that right. You only have the “right” to spend those tokens down as you use the network, which isn’t much of a right at all. On Koinos, the KOIN token works exactly like you think it would! Holding KOIN gives you a perpetual right to use the network, thanks to the Mana system. The more KOIN you hold, the more free usage, forever. Simple. Every KOIN token contains 1 Mana. When you use the blockchain, some of your Mana is consumed, but it regenerates in 5 days and if you only use a small percentage of your Mana it can regenerate in as little as a few minutes! Frictionless Access Mana can also be shared with people who have no tokens at all, which is what enables Koinos to deliver that familiar free-to-use experience that we get from the internet, and without forcing developers to pay the fees, because remember there are no fees. For the first time ever... developers can onboard users and allow them to the use the blockchain without first making them jump through the hoops of understanding and buying a cryptocurrency which is going to weed out the vast majority of mainstream users. That’s why we don’t have mainstream adoption! In short, KOIN has real utility; it gives you ownership over a certain amount of the network’s resources, a right which you can share with others. Koinos doesn’t force you to pay ever-changing fees all the time and it does all of this while preventing people from abusing the network. Be Free Because you never have to part with your KOIN which gives you the right to a certain amount of the network’s resources, this frees you, and every other KOIN holder, to focus on what matters; adding utility and making Koinos an even greater force for good. You can learn more about Koinos at and

KoinosGroup 🔮

337,618 views • 3 years ago

Claude Code + Obsidian + 1 free GitHub skill = unlimited memory. Almost nobody is running this yet. Here’s the problem nobody tells you. Claude forgets you. Every new chat starts at 0. You re explain your business, your projects, your style every single time. That tax is why most people never compound anything with AI. The fix is 1 skill. It’s called Obsidian Mind. It turns your Obsidian vault into Claude’s long term brain. 2,000 notes, 14 projects, every idea you’ve ever dumped Claude reads it live and writes back to it live. It stops being a chatbot. It becomes a second brain that builds. What it does: → Bridges Claude Code straight into your vault. → Pulls any note in real time no copy paste, no context limit. → Updates your vault as you work Claude writes its own memory. → Links everything into 1 graph Claude can navigate. Day 1: Claude knows your last 6 months. Week 2: it drafts off your own past notes. Week 4: it’s running plays you forgot you wrote down. The people making real money with AI right now aren’t smarter. They just stopped starting from 0 every morning. Setup takes 11 minutes. The skill is free. You’ll have a brain that never forgets.

Claude Code + Obsidian + 1 free GitHub skill = unlimited memory. Almost nobody is running this yet. Here’s the problem nobody tells you. Claude forgets you. Every new chat starts at 0. You re explain your business, your projects, your style every single time. That tax is why most people never compound anything with AI. The fix is 1 skill. It’s called Obsidian Mind. It turns your Obsidian vault into Claude’s long term brain. 2,000 notes, 14 projects, every idea you’ve ever dumped Claude reads it live and writes back to it live. It stops being a chatbot. It becomes a second brain that builds. What it does: → Bridges Claude Code straight into your vault. → Pulls any note in real time no copy paste, no context limit. → Updates your vault as you work Claude writes its own memory. → Links everything into 1 graph Claude can navigate. Day 1: Claude knows your last 6 months. Week 2: it drafts off your own past notes. Week 4: it’s running plays you forgot you wrote down. The people making real money with AI right now aren’t smarter. They just stopped starting from 0 every morning. Setup takes 11 minutes. The skill is free. You’ll have a brain that never forgets.

West Lord

110,779 views • 2 months ago

NEW: Introducing Octane AI Agentic Commerce Quizzes - Increase sales with AI. What is it? A sales quiz AI agent that makes 1-1 personalized sales experiences for every single customer. In real time. Powered by our new AI model CORE-1. Examples: 📸 Want to ask your customer to take a selfie and your AI agent automatically recommends them a full outfit from your catalog? Octane AI agents can do that. 🪞 Want to have an AI agent hand pick out each product for a personalized skin care routine? Want them to upload a selfie to detect their skin tone? Octane AI agents can do can that. 📊 Want to create an incredibly detailed report with graphs and tables and graphics thats generated by AI for each customer? Octane AI agents can do that. We give you the building blocks and you can build anything. And you can build it fast because our AI will do the heavy lifting for you. This is v1 and a representation of where our commerce and quiz technology is headed. Available today to everyone at 🆕 What we are launching today: • Smart Quiz Builder: Have an AI agent plan out and build your Octane AI quiz for you. It can even write custom HTML for beautiful results pages and progress bars. • Smart Products: It can take forever to setup the recommendation logic for a quiz. For those of you who need help, simply add smart products to your Octane AI quiz and your very own AI agent will hand-pick products for each customer who takes your quiz. It’s amazing. • Smart Copy: Instead of showing everyone who takes your quiz the exact same copy, use AI to personalize the quiz for every single person who takes it. Explain why these specific products are perfect for specifically them. • Image Analyzer: Let your customers upload or take a photo during the quiz and have AI analyze it. You can use this for anything from skin tone detection to picking out outfits! • Shopping Assistant: An AI agent that lives on your store that can help your customers at the right time. We have been building quiz software for almost 10 years now and AI is enabling us to make quizzes even more powerful. This is just the v1 of what we will be releasing in this area. We are so excited to see what you create with these new agentic products. Get creative, we think you will be surprised at how many interesting experiences you can create with Octane AI now.

NEW: Introducing Octane AI Agentic Commerce Quizzes - Increase sales with AI. What is it? A sales quiz AI agent that makes 1-1 personalized sales experiences for every single customer. In real time. Powered by our new AI model CORE-1. Examples: 📸 Want to ask your customer to take a selfie and your AI agent automatically recommends them a full outfit from your catalog? Octane AI agents can do that. 🪞 Want to have an AI agent hand pick out each product for a personalized skin care routine? Want them to upload a selfie to detect their skin tone? Octane AI agents can do can that. 📊 Want to create an incredibly detailed report with graphs and tables and graphics thats generated by AI for each customer? Octane AI agents can do that. We give you the building blocks and you can build anything. And you can build it fast because our AI will do the heavy lifting for you. This is v1 and a representation of where our commerce and quiz technology is headed. Available today to everyone at 🆕 What we are launching today: • Smart Quiz Builder: Have an AI agent plan out and build your Octane AI quiz for you. It can even write custom HTML for beautiful results pages and progress bars. • Smart Products: It can take forever to setup the recommendation logic for a quiz. For those of you who need help, simply add smart products to your Octane AI quiz and your very own AI agent will hand-pick products for each customer who takes your quiz. It’s amazing. • Smart Copy: Instead of showing everyone who takes your quiz the exact same copy, use AI to personalize the quiz for every single person who takes it. Explain why these specific products are perfect for specifically them. • Image Analyzer: Let your customers upload or take a photo during the quiz and have AI analyze it. You can use this for anything from skin tone detection to picking out outfits! • Shopping Assistant: An AI agent that lives on your store that can help your customers at the right time. We have been building quiz software for almost 10 years now and AI is enabling us to make quizzes even more powerful. This is just the v1 of what we will be releasing in this area. We are so excited to see what you create with these new agentic products. Get creative, we think you will be surprised at how many interesting experiences you can create with Octane AI now.

Matt Schlicht

290,863 views • 9 months ago

how to set up hermes agent step by step. built-in memory, 40+ tools, works on your phone, and what to think of hermes vs openclaw: 1. hermes is a personal AI agent that runs in your terminal. think of it like open claw but with built-in memory, 40+ tools out of the box, and 90% cheaper token costs. you install it with one command. 2. the 3 problems with open claw that hermes solves: no memory (you keep repeating yourself), constant gateway restarts, and zero visibility into what you're spending on tokens. 3. hermes remembers everything. every completed task gets saved to memory. it searches through past logs to find solutions. over time it literally gets smarter at your specific workflows. 4. connect it to open router. you see exact costs per model per task. free models rotate weekly. one founder went from $130 every five days on open claw to $10 on hermes. same output. 5. it comes preloaded with skills. apple notes, imessage, find my, browser, web search, image generation, cron jobs. no hunting for plugins. 6. connect it to obsidian so it reads your entire vault. connect it to gstack for your dev environment. create custom skills for your specific workflows. 7. the biggest money saver: have it write code once for recurring tasks. then it runs without burning tokens every time. stop paying an LLM to do the same scrape or report daily. 8. run it on android via telegram. name your agents. talk to them like coworkers. in this episode imran shows you how to set this up. 9. you can run it bare metal, in docker, or serverless on modal. pick your risk level. i begged imran to come on The Startup Ideas Podcast (SIP) 🧃 and walk through the full installation live. he made it impossibly clear. if you've heard of Hermes Agent and want the clearest explanation of how to get set up like a pro let me know what you want me to cover on the next ep this is the best personal agent setup video on the internet right now. watch

how to set up hermes agent step by step. built-in memory, 40+ tools, works on your phone, and what to think of hermes vs openclaw: 1. hermes is a personal AI agent that runs in your terminal. think of it like open claw but with built-in memory, 40+ tools out of the box, and 90% cheaper token costs. you install it with one command. 2. the 3 problems with open claw that hermes solves: no memory (you keep repeating yourself), constant gateway restarts, and zero visibility into what you're spending on tokens. 3. hermes remembers everything. every completed task gets saved to memory. it searches through past logs to find solutions. over time it literally gets smarter at your specific workflows. 4. connect it to open router. you see exact costs per model per task. free models rotate weekly. one founder went from $130 every five days on open claw to $10 on hermes. same output. 5. it comes preloaded with skills. apple notes, imessage, find my, browser, web search, image generation, cron jobs. no hunting for plugins. 6. connect it to obsidian so it reads your entire vault. connect it to gstack for your dev environment. create custom skills for your specific workflows. 7. the biggest money saver: have it write code once for recurring tasks. then it runs without burning tokens every time. stop paying an LLM to do the same scrape or report daily. 8. run it on android via telegram. name your agents. talk to them like coworkers. in this episode imran shows you how to set this up. 9. you can run it bare metal, in docker, or serverless on modal. pick your risk level. i begged imran to come on The Startup Ideas Podcast (SIP) 🧃 and walk through the full installation live. he made it impossibly clear. if you've heard of Hermes Agent and want the clearest explanation of how to get set up like a pro let me know what you want me to cover on the next ep this is the best personal agent setup video on the internet right now. watch

GREG ISENBERG

623,612 views • 4 months ago

Today, we are launching Depost AI 2. 🎉 I am a bit emotional writing this. The last eight months were intense. But today I am proud of what we built. Because Depost AI 2 is built to become the best and safest AI content team for LinkedIn. We listened to thousands of people who used the first version, and we rebuilt Depost AI from scratch on the official LinkedIn API. The result: - A chat instead of a form, so you brief it like a colleague - Analytics that show what performs for you and why - Four agents that write in your voice and design the graphics to match - A calendar that fills from approved drafts - Approvals, roles, and a separate workspace for every brand - MCP, so the whole team works inside Claude, ChatGPT, or Cursor It is built for B2B founders who need to be visible without losing an hour a day. For marketing teams who need one system, one review flow, and one voice per brand. And for agencies who run LinkedIn for clients and need every brand kept apart. But the bigger vision is this: Depost AI is becoming a content team that understands your brand before it writes a word. It learns from everything you publish. It knows what performs for you and why. It plans, writes, designs, and schedules from that. And nothing goes live until you approve it. Because writing a post is not the hard part. Knowing what to say, saying it well every week, and doing it safely on an account you cannot afford to lose is. Depost AI 2 is the tool we built to solve that. And honestly, the best part right now is watching people brief it for the first time and get a week of drafts back in their own voice. You can start a 7-day free trial today at And if you message me, I will happily walk you through it myself. ❤️

Atta 🐬

17,864 views • 3 days ago

$THIS MIGHT BE THE #1 OPEN-SOURCE REPO FOR CLAUDE CODE RIGHT NOW. IT GIVES CLAUDE A MEMORY AND SLASHES YOUR TOKEN COST ON EVERY QUESTION The repo is safishamsi/graphify, a free open-source skill that turns any codebase into a knowledge graph Claude Code can read instantly. Instead of grepping through your files every session, Claude gets a map of how everything connects The problem it fixes: Every time you ask Claude Code about a big repo, it does the same thing, greps through dozens of files like a brute-force Ctrl+F, blows through your context window, and sometimes still misses the answer hiding in a file nobody searched. Claude Code has no memory of how your project is structured. Every session starts from zero What it does: It maps your entire codebase into a knowledge graph, capturing not just which files exist, but which functions depend on which, which modules are central, and which files cluster around the same concern. Claude queries the map instead of scanning files How it works, three passes: 1. Code structure, free and local. Tree-sitter parses your files and pulls out classes, functions, imports and call graphs. No LLM, no tokens, just your actual code mapped deterministically 2. Audio and video, if you have them. Transcribed locally and folded into the graph 3. Docs, papers, images. Here an LLM does semantic analysis, figuring out what each document means and where it fits. Only the meaning gets sent up, never your raw source It saves you money: Normally a question about a big repo makes Claude spawn explore agents that scan file after file, eating your context window and your token budget before you get an answer. With the graph already built, Claude queries the map instead of re-reading the codebase every time. Same answer, a fraction of the tokens. The graph only gets built once, then a hook rebuilds it after each commit for free, so you never pay that scanning cost again. The bigger the repo, the bigger the gap The best parts: it's a skill, so once installed Claude knows when to use it without you memorizing commands. It works on non-code folders too, point it at docs or notes and it can spin up an Obsidian vault How to add it to your Claude: 1. Install Claude Code if you haven't: npm install -g Paul Jankura-ai/claude-code 2. Add the skill: claude skill add safishamsi/graphify 3. Open your project folder and run /graphify . to build the graph 4. Optional, make it automatic: graphify hook install so the graph rebuilds after every commit That's it. Ask Claude about your repo and it reads the map instead of burning tokens on a file hunt Bookmark this$

THIS MIGHT BE THE #1 OPEN-SOURCE REPO FOR CLAUDE CODE RIGHT NOW. IT GIVES CLAUDE A MEMORY AND SLASHES YOUR TOKEN COST ON EVERY QUESTION The repo is safishamsi/graphify, a free open-source skill that turns any codebase into a knowledge graph Claude Code can read instantly. Instead of grepping through your files every session, Claude gets a map of how everything connects The problem it fixes: Every time you ask Claude Code about a big repo, it does the same thing, greps through dozens of files like a brute-force Ctrl+F, blows through your context window, and sometimes still misses the answer hiding in a file nobody searched. Claude Code has no memory of how your project is structured. Every session starts from zero What it does: It maps your entire codebase into a knowledge graph, capturing not just which files exist, but which functions depend on which, which modules are central, and which files cluster around the same concern. Claude queries the map instead of scanning files How it works, three passes: 1. Code structure, free and local. Tree-sitter parses your files and pulls out classes, functions, imports and call graphs. No LLM, no tokens, just your actual code mapped deterministically 2. Audio and video, if you have them. Transcribed locally and folded into the graph 3. Docs, papers, images. Here an LLM does semantic analysis, figuring out what each document means and where it fits. Only the meaning gets sent up, never your raw source It saves you money: Normally a question about a big repo makes Claude spawn explore agents that scan file after file, eating your context window and your token budget before you get an answer. With the graph already built, Claude queries the map instead of re-reading the codebase every time. Same answer, a fraction of the tokens. The graph only gets built once, then a hook rebuilds it after each commit for free, so you never pay that scanning cost again. The bigger the repo, the bigger the gap The best parts: it's a skill, so once installed Claude knows when to use it without you memorizing commands. It works on non-code folders too, point it at docs or notes and it can spin up an Obsidian vault How to add it to your Claude: 1. Install Claude Code if you haven't: npm install -g Paul Jankura-ai/claude-code 2. Add the skill: claude skill add safishamsi/graphify 3. Open your project folder and run /graphify . to build the graph 4. Optional, make it automatic: graphify hook install so the graph rebuilds after every commit That's it. Ask Claude about your repo and it reads the map instead of burning tokens on a file hunt Bookmark this

Yarchi

56,177 views • 3 months ago

Martin Keen from IBM just explained the one thing separating "chatbot users" from $300K AI architects > most people use Claude Opus 4.8 as a temporary tool -> the pros build it a permanent memory it's called the CoALA framework. the 4 layers your agent actually needs: > Working Memory - the context window. fast but resets every session. this is the RAM, not the brain > Semantic Memory - your knowledge base. CLAUDE.md, rules, facts the agent never forgets regardless of session > Procedural Memory - skills. workflows and instructions that load only when a specific task begins > Episodic Memory - past lessons. the agent remembers every bug it fixed yesterday so it doesn't repeat it today if your agent doesn't have all four, it's a fancy autocomplete the 2026 job market isn't looking for prompt engineers > it's looking for people who can build AI brains - and the ones doing it now aren't waiting for job postings save this or watch someone else use it to get your next raise 👇

Martin Keen from IBM just explained the one thing separating "chatbot users" from $300K AI architects > most people use Claude Opus 4.8 as a temporary tool -> the pros build it a permanent memory it's called the CoALA framework. the 4 layers your agent actually needs: > Working Memory - the context window. fast but resets every session. this is the RAM, not the brain > Semantic Memory - your knowledge base. CLAUDE.md, rules, facts the agent never forgets regardless of session > Procedural Memory - skills. workflows and instructions that load only when a specific task begins > Episodic Memory - past lessons. the agent remembers every bug it fixed yesterday so it doesn't repeat it today if your agent doesn't have all four, it's a fancy autocomplete the 2026 job market isn't looking for prompt engineers > it's looking for people who can build AI brains - and the ones doing it now aren't waiting for job postings save this or watch someone else use it to get your next raise 👇

Mr. Buzzoni

10,442 views • 3 months ago