🚨 BREAKING: Someone just built the exact tool Andrej Karpathy said someone should build.
48 hours after Karpathy posted his LLM Knowledge Bases workflow, this showed up on GitHub.
It's called Graphify. One command. Any folder. Full knowledge graph.
Point it at any folder. Run /graphify inside Claude Code. Walk away.
Here is what comes out the other side:
-> A navigable knowledge graph of everything in that folder
-> An Obsidian vault with backlinked articles
-> A wiki that starts at index. md and maps every concept cluster
-> Plain English Q&A over your entire codebase or research folder
You can ask it things like:
"What calls this function?"
"What connects these two concepts?"
"What are the most important nodes in this project?"
No vector database. No setup. No config files.
The token efficiency number is what got me:
71.5x fewer tokens per query compared to reading raw files.
That is not a small improvement. That is a completely different paradigm for how AI agents reason over large codebases.
What it supports:
-> Code in 13 programming languages
-> PDFs
-> Images via Claude Vision
-> Markdown files
Install in one line:
pip install graphify && graphify install
Then type /graphify in Claude Code and point it at anything.
Karpathy asked. Someone delivered in 48 hours.
That is the pace of 2026.
Open Source. Free.
This is the most complete Claude Code setup that exists right now.
27 agents. 64 skills. 33 commands. All open source.
The Anthropic hackathon winner open-sourced his entire system, refined over 10 months of building real products.
What's inside:
→ 27 agents (plan, review, fix builds, security audits)
→ 64 skills (TDD, token optimization, memory persistence)
→ 33 commands (/plan, /tdd, /security-scan, /refactor-clean)
→ AgentShield: 1,282 security tests, 98% coverage
60% documented cost reduction.
Works on Claude Code, Cursor, OpenCode, Codex CLI. 100% open source.
I'm Boris and I created Claude Code. I wanted to quickly share a few tips for using Claude Code, sourced directly from the Claude Code team. The way the team uses Claude is different than how I use it. Remember: there is no one right way to use Claude Code -- everyones' setup is different. You should experiment to see what works for you!
İSTANBUL'UN GÜZEL ZAMANLARIYDI..
Nüfus, daha üç milyon bile olmamıştı.
İstanbul dediğiniz; SUR içinden ibaretti.
Eyüp'te, Rami'de, Zeytinburnu'nda oturan insanlar sokakta karşılaştıklarında...
Faiz artarsa başka bozulmalar yaşanacak ve "işte gördünüz mü faizi artırdık her şey bozuldu" denecek. Faizi yanlış belirlerseniz her şeyi bozabilirsiniz ama bozduklarınızı düzeltmek için faizi artırmanın yanında birçok başka adım atmanız lazım.
https://t.co/w8zPravv9T
Aynı gün başında bir kadın olan partiye kurşun sıkılırken, bir başka kadın New York'ta Chanel mağazasından alışveriş yapıyor. Hem de daha depremin külleri tazeyken...
Bu gece uzun olacak ülkeler Twitter'ı da yavaşlatmak istiyor... Bunlar kan emici. Kan.
Google girin pandora belgeleri yazın.
Çökmenin nedeni bu. Büyük soygun oldu. Hemde uluslararası liderler yaptı. Google girin. Veriler siliniyor.
#WhatsApp#Instagram ve #Facebook#çökmüş