Video wird geladen...

Video konnte nicht geladen werden

Zur Startseite

300 agents can find 1,000 sources. that still doesn’t make the research good the interesting part starts when those sources are forced to check each other. in K3 graph-native setup: 300 agents → 140 linked sources → 100% traceable claims → 9 contradictions surfaced one source confirms a number....

0xRicker's profile picture

Ricker

9,220 subscribers

227,257 Aufrufe • vor 9 Tagen •via X (Twitter)

Wissenschaft & TechnologieBildung
LIVE

Anya Rossi• Live Now

Private livecam show

0 Kommentare

Keine Kommentare verfügbar

Kommentare vom Original-Post werden hier angezeigt

Ähnliche Videos

300 agents without shared context is just parallelized confusion. All 300 agents are useless if the research dies inside 300 separate documents. the real unlock is what happens after the search. in K3 graph-native setup: 300 agents 140 linked sources 100% traceable claims 9 contradictions surfaced and every new source changes the graph. now imagine that happening across 8–10 active research clusters at once. instead of 300 isolated summaries, you get one shared structure: source → entity → relationship → evidence → contradiction → verification the math gets ugly fast. 100 entities = 4,950 possible pairwise relationships. that’s why “just run more agents” stops being enough. you need a graph that can keep track of what connects to what. full breakdown in the article below.
0:43

300 agents without shared context is just parallelized confusion. All 300 agents are useless if the research dies inside 300 separate documents. the real unlock is what happens after the search. in K3 graph-native setup: 300 agents 140 linked sources 100% traceable claims 9 contradictions surfaced and every new source changes the graph. now imagine that happening across 8–10 active research clusters at once. instead of 300 isolated summaries, you get one shared structure: source → entity → relationship → evidence → contradiction → verification the math gets ugly fast. 100 entities = 4,950 possible pairwise relationships. that’s why “just run more agents” stops being enough. you need a graph that can keep track of what connects to what. full breakdown in the article below.

Ricker

15,089 Aufrufe • vor 7 Tagen

💊The red pill for medical science: 5 AI agents, 5 siloed sources, 1 shared context graph on Decentralized Knowledge Graph. Published literature, registered trials, real-world safety reports — different owners, different formats, no common ground. We handed the mess to agents that never edited each other's data and asked the question that matters most in medicine: where did each claim come from, and can you check? Working separately, they converged. On 5 disease hubs, 4 of 5 agents landed on the same condition from their own source. Every claim traceable, nothing taken on faith. Evidence, unshackled👇
4:06

💊The red pill for medical science: 5 AI agents, 5 siloed sources, 1 shared context graph on Decentralized Knowledge Graph. Published literature, registered trials, real-world safety reports — different owners, different formats, no common ground. We handed the mess to agents that never edited each other's data and asked the question that matters most in medicine: where did each claim come from, and can you check? Working separately, they converged. On 5 disease hubs, 4 of 5 agents landed on the same condition from their own source. Every claim traceable, nothing taken on faith. Evidence, unshackled👇

OriginTrail

607,106 Aufrufe • vor 2 Monaten

ANTHROPIC LEAKED A 5-AGENT SETUP THAT TURNS ONE QUESTION INTO A SOURCED REPORT you write one line and never open a tab - the fleet reads 40 sources and only the answer comes back. question → scope → 5 searchers → dedupe → writer → fact-check → report the scope agent turns a vague question into 5 angles that do not overlap - skip this and five agents fetch the same three articles. 5 searchers run in parallel with separate contexts - none of them sees what the others found, which is exactly why they do not converge on the same source. dedupe is code, not an agent - flatten, drop repeats, normalize URLs, zero tokens, instant. the writer only sees structured findings, never raw pages - it cannot cite something that was never verified because it never had access to it. the fact-checker reads the draft against the sources, not against itself - every claim without a matching source goes back, and only that section is rewritten. nothing reaches you until a second agent, with clean context, has tried to kill it. 12 minutes, 40 sources, one report where every line traces back to something real. save this and read the full graph engineering course below ↓
0:49

ANTHROPIC LEAKED A 5-AGENT SETUP THAT TURNS ONE QUESTION INTO A SOURCED REPORT you write one line and never open a tab - the fleet reads 40 sources and only the answer comes back. question → scope → 5 searchers → dedupe → writer → fact-check → report the scope agent turns a vague question into 5 angles that do not overlap - skip this and five agents fetch the same three articles. 5 searchers run in parallel with separate contexts - none of them sees what the others found, which is exactly why they do not converge on the same source. dedupe is code, not an agent - flatten, drop repeats, normalize URLs, zero tokens, instant. the writer only sees structured findings, never raw pages - it cannot cite something that was never verified because it never had access to it. the fact-checker reads the draft against the sources, not against itself - every claim without a matching source goes back, and only that section is rewritten. nothing reaches you until a second agent, with clean context, has tried to kill it. 12 minutes, 40 sources, one report where every line traces back to something real. save this and read the full graph engineering course below ↓

Hanako

58,439 Aufrufe • vor 13 Tagen

THE OBSIDIAN GRAPH IS NOT A PRETTY NOTE MAP, IT IS A SELF-MAINTAINING AI WIKI THAT CAN TURN 120 SAVED SOURCES INTO 700 LINKED PAGES WHILE YOU ONLY KEEP ADDING NEW MATERIAL 00:11 the graph opens and the trick becomes obvious: every dot is a saved idea, every cluster is a topic, and every line is context the AI no longer has to rebuild from scratch every morning most people use chatgpt like a disposable memory slot. they upload 1 pdf, ask 3 questions, close the tab, and the next day the model knows nothing unless they feed it the same context again karpathy’s LLM wiki pattern changes the game. the model reads each new source, pulls out claims, updates old pages, creates entity files, links concepts, and marks places where newer info breaks older notes with claude code and obsidian, a single clipped article can expand into 8-20 markdown files: source summary, concept pages, people, tools, comparisons, open questions, and a running index after 60 sources, this is no longer “note taking.” it becomes a private research machine that remembers your old thinking, catches repeated angles, and gives you cited answers from your own archive bookmark this before your notes turn into a graveyard again
0:35

THE OBSIDIAN GRAPH IS NOT A PRETTY NOTE MAP, IT IS A SELF-MAINTAINING AI WIKI THAT CAN TURN 120 SAVED SOURCES INTO 700 LINKED PAGES WHILE YOU ONLY KEEP ADDING NEW MATERIAL 00:11 the graph opens and the trick becomes obvious: every dot is a saved idea, every cluster is a topic, and every line is context the AI no longer has to rebuild from scratch every morning most people use chatgpt like a disposable memory slot. they upload 1 pdf, ask 3 questions, close the tab, and the next day the model knows nothing unless they feed it the same context again karpathy’s LLM wiki pattern changes the game. the model reads each new source, pulls out claims, updates old pages, creates entity files, links concepts, and marks places where newer info breaks older notes with claude code and obsidian, a single clipped article can expand into 8-20 markdown files: source summary, concept pages, people, tools, comparisons, open questions, and a running index after 60 sources, this is no longer “note taking.” it becomes a private research machine that remembers your old thinking, catches repeated angles, and gives you cited answers from your own archive bookmark this before your notes turn into a graveyard again

Gipp 🦅

41,728 Aufrufe • vor 2 Monaten

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 below
0:22

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 below

Mr. Buzzoni

15,462 Aufrufe • vor 9 Tagen

HERMES AGENT JUST GOT A RESEARCH BRAIN. connect it to NotebookLM and it becomes a 247 research system that builds knowledge over time. it resources. connects ideas across sources. uses that context in every real task. setup in 4 steps: 1. install Hermes with MCP enabled 2. download NotebookLM skill from GitHub 3. add endpoint to MCP servers in config 4. restart Hermes what your agent can now do: → query your notebooks instead of the open web → connect ideas across multiple sources → build knowledge session after session → use your curated context in every /goal → zero hallucinations from your own verified sources ask it anything — it answers from what YOU already know. full setup guide — MCP, models, use cases — in the article 👇
0:30

HERMES AGENT JUST GOT A RESEARCH BRAIN. connect it to NotebookLM and it becomes a 247 research system that builds knowledge over time. it resources. connects ideas across sources. uses that context in every real task. setup in 4 steps: 1. install Hermes with MCP enabled 2. download NotebookLM skill from GitHub 3. add endpoint to MCP servers in config 4. restart Hermes what your agent can now do: → query your notebooks instead of the open web → connect ideas across multiple sources → build knowledge session after session → use your curated context in every /goal → zero hallucinations from your own verified sources ask it anything — it answers from what YOU already know. full setup guide — MCP, models, use cases — in the article 👇

YanXbt

187,518 Aufrufe • vor 3 Monaten

Claude Code cannot read 300 files at once. So someone built a system that lets it control NotebookLM from the terminal instead. The results are wild. Here is the full workflow nobody is talking about: The Setup → Claude Code connects to NotebookLM via a command line interface → Claude searches YouTube, finds relevant videos, uploads them as sources automatically → NotebookLM processes up to 300 sources simultaneously and returns cited, grounded answers → Everything syncs back into your Obsidian vault with passage-level citations you can click to verify Why This Changes Research Forever → No more 20 browser tabs you never close → No more copy-pasting outputs into random notes → No more hallucinated answers with no sources to back them up → 60% of citations verified as strong matches in accuracy audits - answers are grounded in real data What Claude Can Do From the Terminal → Search YouTube for relevant videos on any topic and rank by relevance → Create a new NotebookLM notebook and add 20 sources in parallel automatically → Ask questions and export cited answers directly into Obsidian with wikilinks → Set custom personas per notebook - concise, no filler, no preamble → Generate audio overviews and save them as MP3 files into your vault → Build mind maps, flashcard decks, and research dashboards from your sources → Search arXiv for academic papers and feed them directly into NotebookLM → Upload competitor blog posts, podcast episodes, PDFs, and your own vault notes The Obsidian Output → Every answer arrives with clickable citations that link to the exact passage in the source video or article → Graph view shows connections between all 20 sources and the topics they share → Q&A log tracks every question asked and the grounded response received → Source dashboard shows citation frequency, topics extracted, and which questions each source answered Use Cases Worth Building Today → Academic research with arXiv papers, full citation traceability → Competitor analysis from their YouTube channels and blog posts → Company knowledge base for onboarding, new employees ask NotebookLM instead of interrupting teammates → Podcast research, feed 4-hour Lex Fridman episodes and ask what's new in AI this week → Personal second brain, 300 daily notes uploaded and queryable in one notebook Before this system existed you needed 20 tabs, hours of manual reading, and no guarantee the answers were real. Now you type one prompt in the terminal and Claude does all of it for you. The research stack of 2026 is not a browser. It is a terminal connected to everything
32:50

Claude Code cannot read 300 files at once. So someone built a system that lets it control NotebookLM from the terminal instead. The results are wild. Here is the full workflow nobody is talking about: The Setup → Claude Code connects to NotebookLM via a command line interface → Claude searches YouTube, finds relevant videos, uploads them as sources automatically → NotebookLM processes up to 300 sources simultaneously and returns cited, grounded answers → Everything syncs back into your Obsidian vault with passage-level citations you can click to verify Why This Changes Research Forever → No more 20 browser tabs you never close → No more copy-pasting outputs into random notes → No more hallucinated answers with no sources to back them up → 60% of citations verified as strong matches in accuracy audits - answers are grounded in real data What Claude Can Do From the Terminal → Search YouTube for relevant videos on any topic and rank by relevance → Create a new NotebookLM notebook and add 20 sources in parallel automatically → Ask questions and export cited answers directly into Obsidian with wikilinks → Set custom personas per notebook - concise, no filler, no preamble → Generate audio overviews and save them as MP3 files into your vault → Build mind maps, flashcard decks, and research dashboards from your sources → Search arXiv for academic papers and feed them directly into NotebookLM → Upload competitor blog posts, podcast episodes, PDFs, and your own vault notes The Obsidian Output → Every answer arrives with clickable citations that link to the exact passage in the source video or article → Graph view shows connections between all 20 sources and the topics they share → Q&A log tracks every question asked and the grounded response received → Source dashboard shows citation frequency, topics extracted, and which questions each source answered Use Cases Worth Building Today → Academic research with arXiv papers, full citation traceability → Competitor analysis from their YouTube channels and blog posts → Company knowledge base for onboarding, new employees ask NotebookLM instead of interrupting teammates → Podcast research, feed 4-hour Lex Fridman episodes and ask what's new in AI this week → Personal second brain, 300 daily notes uploaded and queryable in one notebook Before this system existed you needed 20 tabs, hours of manual reading, and no guarantee the answers were real. Now you type one prompt in the terminal and Claude does all of it for you. The research stack of 2026 is not a browser. It is a terminal connected to everything

Dami-Defi

252,693 Aufrufe • vor 3 Monaten

Palantir sells this to governments for millions. Someone put a version of it on GitHub for free. Palantir's job is to pull scattered company data into one model where every decision can be traced later. Semantica does that for AI agents. Each decision becomes an object in a graph, tied to the facts that produced it, each fact linked to its source. Six months later you can walk backwards from any answer. The model never touches the reasoning. It only reads messy text and pulls out entities. The rest runs on plain rules, so the same input gives the same explanation every time. Vector memory cannot do that. Contradicting facts overwrite each other silently. pip install semantica, pick a graph backend you already run, and your agents read it through the MCP server. MIT licensed, repo is semantica-agi/semantica
1:47

Palantir sells this to governments for millions. Someone put a version of it on GitHub for free. Palantir's job is to pull scattered company data into one model where every decision can be traced later. Semantica does that for AI agents. Each decision becomes an object in a graph, tied to the facts that produced it, each fact linked to its source. Six months later you can walk backwards from any answer. The model never touches the reasoning. It only reads messy text and pulls out entities. The rest runs on plain rules, so the same input gives the same explanation every time. Vector memory cannot do that. Contradicting facts overwrite each other silently. pip install semantica, pick a graph backend you already run, and your agents read it through the MCP server. MIT licensed, repo is semantica-agi/semantica

Yarchi

42,733 Aufrufe • vor 11 Tagen

Prompt engineering is where people go when they refuse to write files Karpathy's LLM Wiki gist is painfully simple: > raw sources stay untouched > the agent writes the wiki > `CLAUDE.md` or `AGENTS.md` tells it the rules > `index.md` maps the pages > `log.md` records what changed That is why a good answer should not die in chat history If the model gives you a useful comparison, summary, decision, bug explanation, or research thread, file it back into the project Use: > `wiki/topics/[topic].md` > `wiki/entities/[person-or-company].md` > `wiki/sources/[source-name].md` > `wiki/analysis/[question].md` Make the agent keep the wiki from rotting: > backlinks > summaries > contradictions > stale claims > orphan pages > missing source links For coding projects, same idea: > `CLAUDE.md`: who you are, project rules, files not to touch > `index.md`: current files and features > `log.md`: date, change, reason > saved pages: decisions you do not want to re-explain Start by saving one good answer today
11:03

Prompt engineering is where people go when they refuse to write files Karpathy's LLM Wiki gist is painfully simple: > raw sources stay untouched > the agent writes the wiki > `CLAUDE.md` or `AGENTS.md` tells it the rules > `index.md` maps the pages > `log.md` records what changed That is why a good answer should not die in chat history If the model gives you a useful comparison, summary, decision, bug explanation, or research thread, file it back into the project Use: > `wiki/topics/[topic].md` > `wiki/entities/[person-or-company].md` > `wiki/sources/[source-name].md` > `wiki/analysis/[question].md` Make the agent keep the wiki from rotting: > backlinks > summaries > contradictions > stale claims > orphan pages > missing source links For coding projects, same idea: > `CLAUDE.md`: who you are, project rules, files not to touch > `index.md`: current files and features > `log.md`: date, change, reason > saved pages: decisions you do not want to re-explain Start by saving one good answer today

Alpha Batcher

14,041 Aufrufe • vor 2 Monaten

Content creation just leveled up with AI agents. I just tested Superagent by Airtable, and it’s insane… Instead of doing research + planning + writing manually, you can run multiple AI agents at the same time and get a complete Super Report at the end. What surprised me the most: ✅ Agents work in parallel (faster and more organized) ✅ The report is interactive and easy to explore ✅ It includes cited sources, so it’s actually reliable ✅ You can even generate outputs like docs / slides / websites It feels like having a full strategy team… on demand. Get 2 FREE months of Superagent using the code: ADAM2FREE → #SuperagentPartner #ad #SuperagentbyAirtable Airtable Superagent
1:13

Content creation just leveled up with AI agents. I just tested Superagent by Airtable, and it’s insane… Instead of doing research + planning + writing manually, you can run multiple AI agents at the same time and get a complete Super Report at the end. What surprised me the most: ✅ Agents work in parallel (faster and more organized) ✅ The report is interactive and easy to explore ✅ It includes cited sources, so it’s actually reliable ✅ You can even generate outputs like docs / slides / websites It feels like having a full strategy team… on demand. Get 2 FREE months of Superagent using the code: ADAM2FREE → #SuperagentPartner #ad #SuperagentbyAirtable Airtable Superagent

Adam

17,913 Aufrufe • vor 7 Monaten

Introducing the Knowledge Agent Template Vercel dropped the Chat SDK so we built a full template on top of it that you can deploy in one click. Here's what's inside: • Add your sources: GitHub repos, YouTube, etc. directly from the UI • File-based agent using grep/find/cat • Powered by Vercel Workflow + Sandbox • Multi-platform: web chat, GitHub bot, Discord bot, and more • Comes with skills to edit your project, add sources, create agents Deploy, add a source, ask questions. Your knowledge base is live and always in sync. This is just scratching the surface. There's way more packed in this template, and I'll be breaking down the features all week. Links in the below 👇
0:29

Introducing the Knowledge Agent Template Vercel dropped the Chat SDK so we built a full template on top of it that you can deploy in one click. Here's what's inside: • Add your sources: GitHub repos, YouTube, etc. directly from the UI • File-based agent using grep/find/cat • Powered by Vercel Workflow + Sandbox • Multi-platform: web chat, GitHub bot, Discord bot, and more • Comes with skills to edit your project, add sources, create agents Deploy, add a source, ask questions. Your knowledge base is live and always in sync. This is just scratching the surface. There's way more packed in this template, and I'll be breaking down the features all week. Links in the below 👇

Hugo

54,743 Aufrufe • vor 6 Monaten

How to build a 1-person AI company that: - Runs locally - 100% open-source - No human employees, all agents - Real-time collaboration via email Multi-agent orchestration is not new. Plenty of frameworks already let agents hand off tasks, run in parallel, and talk to each other. So the interesting question is not whether agents can collaborate. It is what structure you use to make them collaborate. The common approach is to wire a graph of nodes and edges and reason about the plumbing yourself. It works, but you are learning a new abstraction just to describe who does what. There is a coordination structure we have trusted for a hundred years already: an organization. Every company runs the same way. People have roles, roles have reporting lines, and work moves up and down that chart without anyone relaying each message by hand. Map that onto agents and the whole thing gets intuitive. You lay out an org chart, each agent fills one role, you talk to the person at the top, and the org sorts out the work between them. You already know how a company works, so you already know how to run one here. There is no new abstraction to learn. That is exactly what Alook does. Each agent is a live Claude Code or OpenCode session with a defined role, a reporting line, and its own email inbox. The agents coordinate over email, the same way a team would. And it all runs locally through a runtime on your own machine, so nothing leaves your setup. You bring your own agent too. Claude Code and Codex both work, and if you would rather stay fully open source and local, OpenCode works the same way. To show how this feels in practice, I set up three agents as a small sales team. Vi is the one I talk to. I hand Vi a goal, and Vi routes the work down the chart. Neile runs prospect research. Vi passes the target criteria, and Neile reports back a ranked list of names, roles, and companies, each with a suggested angle and a confidence score. Lliane runs outreach. Vi hands over the messaging angle and follow-up cadence, and Lliane reports back on emails sent, responses received, and any deal that needs escalation. I never relay a message between them. Neile and Lliane report to Vi, and Vi updates me in one place. The whole thing is open source and self-hosted, so it runs on your machine with your own agents. Give the repo a star if you want to follow where it goes: I also wrote a full walkthrough on building your own AI company with it, from a blank org chart to a running job. The article is quoted below. Cheers! :)
0:39

How to build a 1-person AI company that: - Runs locally - 100% open-source - No human employees, all agents - Real-time collaboration via email Multi-agent orchestration is not new. Plenty of frameworks already let agents hand off tasks, run in parallel, and talk to each other. So the interesting question is not whether agents can collaborate. It is what structure you use to make them collaborate. The common approach is to wire a graph of nodes and edges and reason about the plumbing yourself. It works, but you are learning a new abstraction just to describe who does what. There is a coordination structure we have trusted for a hundred years already: an organization. Every company runs the same way. People have roles, roles have reporting lines, and work moves up and down that chart without anyone relaying each message by hand. Map that onto agents and the whole thing gets intuitive. You lay out an org chart, each agent fills one role, you talk to the person at the top, and the org sorts out the work between them. You already know how a company works, so you already know how to run one here. There is no new abstraction to learn. That is exactly what Alook does. Each agent is a live Claude Code or OpenCode session with a defined role, a reporting line, and its own email inbox. The agents coordinate over email, the same way a team would. And it all runs locally through a runtime on your own machine, so nothing leaves your setup. You bring your own agent too. Claude Code and Codex both work, and if you would rather stay fully open source and local, OpenCode works the same way. To show how this feels in practice, I set up three agents as a small sales team. Vi is the one I talk to. I hand Vi a goal, and Vi routes the work down the chart. Neile runs prospect research. Vi passes the target criteria, and Neile reports back a ranked list of names, roles, and companies, each with a suggested angle and a confidence score. Lliane runs outreach. Vi hands over the messaging angle and follow-up cadence, and Lliane reports back on emails sent, responses received, and any deal that needs escalation. I never relay a message between them. Neile and Lliane report to Vi, and Vi updates me in one place. The whole thing is open source and self-hosted, so it runs on your machine with your own agents. Give the repo a star if you want to follow where it goes: I also wrote a full walkthrough on building your own AI company with it, from a blank org chart to a running job. The article is quoted below. Cheers! :)

Akshay 🚀

169,957 Aufrufe • vor 1 Monat

Agents vs. Graphs, clearly explained! spawning more agents is great, but it has a ceiling nobody says out loud: five agents is a count. a graph is a shape. only one of them changes the answer. point five agents at the same pile with the same window and they converge. the first one writes a finding, the rest read it, and all five reports centre on the same thing. you paid five times for one opinion with four echoes. Graph engineering fixes this by moving the decision up a layer: not how many agents, but who is allowed to look at what. you need both. here's how it works: ↳ the count buys you throughput. five things happening instead of one ↳ the shape buys you coverage. five different things happening instead of the same one five times Prompts → Context → Harness → Agents → Graphs the node that does this is the splitter, and it decides more than any other node in the system. cut a repository by folder and four workers audit the same three files. cut it by blast radius and each one sees something the others cannot. the trick is being selective about what each lane is allowed to see. separate contexts are not a nice-to-have, they are the mechanism. if two agents are meant to produce different things, they must not share a window. if they are meant to produce the same thing, you did not need two agents. one thing to know before you scale it. a branch that throws does not reject the batch. it resolves to null, and that is the containment. which means your merge quietly receives a short list. ↳ filter the nulls before the merge, or one dead lane poisons the whole result ↳ never index a merge by position. eight good branches and one failure will shift everything by one, silently skip that and the run looks like it worked. the output is just missing a lane, and nothing errored. and the one that eats whole nights: multi-agent setups can use up to fifteen times the total tokens of a single chat, because every lane reloads its own core. you are trading total tokens for a clean main window. usually the right trade, always a choice. 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 ↓
0:49

Agents vs. Graphs, clearly explained! spawning more agents is great, but it has a ceiling nobody says out loud: five agents is a count. a graph is a shape. only one of them changes the answer. point five agents at the same pile with the same window and they converge. the first one writes a finding, the rest read it, and all five reports centre on the same thing. you paid five times for one opinion with four echoes. Graph engineering fixes this by moving the decision up a layer: not how many agents, but who is allowed to look at what. you need both. here's how it works: ↳ the count buys you throughput. five things happening instead of one ↳ the shape buys you coverage. five different things happening instead of the same one five times Prompts → Context → Harness → Agents → Graphs the node that does this is the splitter, and it decides more than any other node in the system. cut a repository by folder and four workers audit the same three files. cut it by blast radius and each one sees something the others cannot. the trick is being selective about what each lane is allowed to see. separate contexts are not a nice-to-have, they are the mechanism. if two agents are meant to produce different things, they must not share a window. if they are meant to produce the same thing, you did not need two agents. one thing to know before you scale it. a branch that throws does not reject the batch. it resolves to null, and that is the containment. which means your merge quietly receives a short list. ↳ filter the nulls before the merge, or one dead lane poisons the whole result ↳ never index a merge by position. eight good branches and one failure will shift everything by one, silently skip that and the run looks like it worked. the output is just missing a lane, and nothing errored. and the one that eats whole nights: multi-agent setups can use up to fifteen times the total tokens of a single chat, because every lane reloads its own core. you are trading total tokens for a clean main window. usually the right trade, always a choice. 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 ↓

Hanako

95,294 Aufrufe • vor 4 Tagen

Rahul Gandhi’s “Chhatron Ki Goonj” finally has met it's nemesis: JHOOTH KI GOONJ. From a GenZ! The website - - completely debunks the clown prince and exposes his clown acts: ▷ 4 rallies. ▷ 40 claims. ▷ 134 sources. ▷ 29 rated FALSE. 11 MISLEADING. But here is the truly devastating part. Move from Kota to Dehradun to Prayagraj and his statistics change. But the script doesn’t. One rally: 70% will become gig workers. Another: only 1 in 150 gets a government job. In Kota, ₹1.32 lakh crore is supposedly extracted from NEET families every year. In Pune, six out of every hundred Indian women are supposedly raped. All now put under the microscope, claim by claim, source by source. And he has been FACT CHECKED. What remains after the numbers are stripped away is just Jhooth Ki Goonj.
0:35

Rahul Gandhi’s “Chhatron Ki Goonj” finally has met it's nemesis: JHOOTH KI GOONJ. From a GenZ! The website - - completely debunks the clown prince and exposes his clown acts: ▷ 4 rallies. ▷ 40 claims. ▷ 134 sources. ▷ 29 rated FALSE. 11 MISLEADING. But here is the truly devastating part. Move from Kota to Dehradun to Prayagraj and his statistics change. But the script doesn’t. One rally: 70% will become gig workers. Another: only 1 in 150 gets a government job. In Kota, ₹1.32 lakh crore is supposedly extracted from NEET families every year. In Pune, six out of every hundred Indian women are supposedly raped. All now put under the microscope, claim by claim, source by source. And he has been FACT CHECKED. What remains after the numbers are stripped away is just Jhooth Ki Goonj.

Mahesh Jethmalani

34,938 Aufrufe • vor 1 Tag

i simply can't get over how few people are actually doing this... Andrej Karpathy, co-founder of openai, basically described the whole setup and almost nobody built it let me break down what it actually does... every scattered note, every source you dumped somewhere and forgot, every pattern buried across hundreds of files... compiled once into something claude can scan in seconds instead of rereading cold every session 1. three folders, that's the whole vault: raw holds the originals untouched, wiki holds what claude compiles from them, instructions holds the rules for how it compiles 2. claude reads raw/ once, turns each source into linked wiki pages with sources cited, never opens the raw files again after that 3. every contradiction gets flagged right inside the wiki with both sides and dates, every future session reads the flag first, so you catch it once instead of forever the raw files are disposable... the wiki is what actually holds the value full breakdown is in the article below
0:26

i simply can't get over how few people are actually doing this... Andrej Karpathy, co-founder of openai, basically described the whole setup and almost nobody built it let me break down what it actually does... every scattered note, every source you dumped somewhere and forgot, every pattern buried across hundreds of files... compiled once into something claude can scan in seconds instead of rereading cold every session 1. three folders, that's the whole vault: raw holds the originals untouched, wiki holds what claude compiles from them, instructions holds the rules for how it compiles 2. claude reads raw/ once, turns each source into linked wiki pages with sources cited, never opens the raw files again after that 3. every contradiction gets flagged right inside the wiki with both sides and dates, every future session reads the flag first, so you catch it once instead of forever the raw files are disposable... the wiki is what actually holds the value full breakdown is in the article below

kai

34,399 Aufrufe • vor 1 Monat

Google open-sourced MCP Toolbox for Databases. I gave it access to everything else. For context, Google's MCP Toolbox for Databases is an open-source server that lets AI agents securely query structured databases like PostgreSQL and MySQL through the MCP protocol However, most enterprise knowledge doesn't actually live in databases. It's scattered across emails, Slack threads, GitHub repos, Salesforce records, customer reviews, and internal docs. So Agents can't see any of it, which means they're working with a fraction of the context they need. I fixed that using MindsDB. It acts as a universal SQL layer that sits on top of all your data sources: structured, semi-structured, and unstructured. This means you can query Salesforce, Gmail, GitHub, S3 files, Jira, and 200+ more sources using SQL syntax. The clever part is how it connects to the MCP Toolbox. MindsDB exposes everything through MySQL, so from the Agent's perspective, it's just running SQL and getting context back. It doesn't know or care that the data came from five different sources behind the scenes. This setup unlocks some powerful capabilities: → One SQL interface for dozens of enterprise sources → Cross-datasource joins (combine GitHub and CRM data in a single query) → Built-in ML capabilities for working with unstructured data → Simple MCP tools that now have massively expanded reach In the video below, the Agent queries GitHub data and a customer review database in one SQL query. So what used to require ETL pipelines and weeks of engineering effort now happens instantly. At the end of the day, AI agents are only as useful as the data they can access. This gives them a lot more to work with. I have shared the GitHub repo in the replies, where you can find more details about this.
0:22

Google open-sourced MCP Toolbox for Databases. I gave it access to everything else. For context, Google's MCP Toolbox for Databases is an open-source server that lets AI agents securely query structured databases like PostgreSQL and MySQL through the MCP protocol However, most enterprise knowledge doesn't actually live in databases. It's scattered across emails, Slack threads, GitHub repos, Salesforce records, customer reviews, and internal docs. So Agents can't see any of it, which means they're working with a fraction of the context they need. I fixed that using MindsDB. It acts as a universal SQL layer that sits on top of all your data sources: structured, semi-structured, and unstructured. This means you can query Salesforce, Gmail, GitHub, S3 files, Jira, and 200+ more sources using SQL syntax. The clever part is how it connects to the MCP Toolbox. MindsDB exposes everything through MySQL, so from the Agent's perspective, it's just running SQL and getting context back. It doesn't know or care that the data came from five different sources behind the scenes. This setup unlocks some powerful capabilities: → One SQL interface for dozens of enterprise sources → Cross-datasource joins (combine GitHub and CRM data in a single query) → Built-in ML capabilities for working with unstructured data → Simple MCP tools that now have massively expanded reach In the video below, the Agent queries GitHub data and a customer review database in one SQL query. So what used to require ETL pipelines and weeks of engineering effort now happens instantly. At the end of the day, AI agents are only as useful as the data they can access. This gives them a lot more to work with. I have shared the GitHub repo in the replies, where you can find more details about this.

Akshay 🚀

40,562 Aufrufe • vor 6 Monaten

It takes 5 minutes to create a world-class web research agent that runs 24/7 and returns structured search results. 1. You can limit the sources it's allowed to use 2. You can specify the goals it needs to complete 3. You can design the format structure of the results 4. You can configure how much computing power it will use I show you how to set up a Web Search Agent in the video. A few benefits here: 1. This is great for complex research tasks 2. It's really easy to add this like a LEGO piece to a more complex workflow 3. Create an agent once, and reuse it with different inputs 4. The agent adapts to your use case as you work with it By the way, Nimble published a whole library of templates and research agents you can reuse and modify. You can start sending queries to one of these existing agents, and it will begin to adapt to Go here to try it out: Thanks to the Nimble team for partnering with me on this post.
7:37

It takes 5 minutes to create a world-class web research agent that runs 24/7 and returns structured search results. 1. You can limit the sources it's allowed to use 2. You can specify the goals it needs to complete 3. You can design the format structure of the results 4. You can configure how much computing power it will use I show you how to set up a Web Search Agent in the video. A few benefits here: 1. This is great for complex research tasks 2. It's really easy to add this like a LEGO piece to a more complex workflow 3. Create an agent once, and reuse it with different inputs 4. The agent adapts to your use case as you work with it By the way, Nimble published a whole library of templates and research agents you can reuse and modify. You can start sending queries to one of these existing agents, and it will begin to adapt to Go here to try it out: Thanks to the Nimble team for partnering with me on this post.

Santiago

20,943 Aufrufe • vor 25 Tagen

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
13:23

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 Aufrufe • vor 2 Monaten

somebody just torched their entire career for us someone inside Anthropic wrote down exactly how they wire their AIs to work as a team instead of one at a time, every number, and let the whole thing walk out the door it's called Graph Engineering: you stop asking one AI to do the whole job and start running a crew. one plans, a few go and look, one checks the others for lies their own measurement: the crew came back with 96% of the quality at 46% of the price. same models, same question. they only changed who is allowed to talk to whom Anthropic raised $65,000,000,000 to figure this out. it costs you $0 run one tonight in a normal chat, 3 moves: 1. give it the job and make it write the plan before it touches anything 2. run each step in its own fresh chat so nothing bleeds into the next 3. in one clean chat at the end, make it check the work against sources and mark whatever it could not confirm save this, then open the piece below: how many workers a job actually needs, and where one more starts making it worse ↓
0:34

somebody just torched their entire career for us someone inside Anthropic wrote down exactly how they wire their AIs to work as a team instead of one at a time, every number, and let the whole thing walk out the door it's called Graph Engineering: you stop asking one AI to do the whole job and start running a crew. one plans, a few go and look, one checks the others for lies their own measurement: the crew came back with 96% of the quality at 46% of the price. same models, same question. they only changed who is allowed to talk to whom Anthropic raised $65,000,000,000 to figure this out. it costs you $0 run one tonight in a normal chat, 3 moves: 1. give it the job and make it write the plan before it touches anything 2. run each step in its own fresh chat so nothing bleeds into the next 3. in one clean chat at the end, make it check the work against sources and mark whatever it could not confirm save this, then open the piece below: how many workers a job actually needs, and where one more starts making it worse ↓

Argona

1,378,363 Aufrufe • vor 15 Tagen

I almost published something wrong last week. Not a typo. A claim I'd accepted too fast. A source I hadn't traced all the way back. Caught it at step 247 of 300. That's what MiroMind's auditable reasoning chain actually looks like in practice not a feature you read about in a changelog. a moment where you see it work. I'd typed in something simple: "latest reasoning model benchmarks" Straightforward prompt. The kind you'd throw at ChatGPT without thinking twice. What came back wasn't a confident summary. It was a structured map where the benchmarks agree, where the eval setups are cherry-picked, and where the leaderboard story gets complicated in production. Step 247: a source I hadn't verified. An inference that looked right but wasn't traceable. Flagged. Not included. Most AI tools give you an answer. This one shows you how it got there. Every step. Every source. Replayable. If a step can't be verified it doesn't make it into the output. That's not a safety feature. That's a completely different architecture. Has AI ever confidently given you something that turned out to be wrong? → Worth trying if you’re doing anything beyond surface-level research. $19/mo or pay-per-use
1:24

I almost published something wrong last week. Not a typo. A claim I'd accepted too fast. A source I hadn't traced all the way back. Caught it at step 247 of 300. That's what MiroMind's auditable reasoning chain actually looks like in practice not a feature you read about in a changelog. a moment where you see it work. I'd typed in something simple: "latest reasoning model benchmarks" Straightforward prompt. The kind you'd throw at ChatGPT without thinking twice. What came back wasn't a confident summary. It was a structured map where the benchmarks agree, where the eval setups are cherry-picked, and where the leaderboard story gets complicated in production. Step 247: a source I hadn't verified. An inference that looked right but wasn't traceable. Flagged. Not included. Most AI tools give you an answer. This one shows you how it got there. Every step. Every source. Replayable. If a step can't be verified it doesn't make it into the output. That's not a safety feature. That's a completely different architecture. Has AI ever confidently given you something that turned out to be wrong? → Worth trying if you’re doing anything beyond surface-level research. $19/mo or pay-per-use

Shruti

28,869 Aufrufe • vor 4 Monaten