Video wird geladen...

Video konnte nicht geladen werden

Zur Startseite

placed 2nd, winning $3000 at Anthropic x Elevation Capital push to prod hackathon! ⚡️ > we built claude code but as a game > your entire repo becomes an isometric city > files are buildings with the height determined by the number of files > choose your crew for...

23,034 Aufrufe • vor 1 Monat •via X (Twitter)

73 Kommentare

Profilbild von Rajarshi Datta
Rajarshi Dattavor 1 Monat

@AnthropicAI @ElevCap I tell my kids that if @mittalparth_ & team is there, they will always make a better game than you!

Profilbild von Parth
Parthvor 1 Monat

@AnthropicAI @ElevCap

Profilbild von Parth
Parthvor 1 Monat

thanks to the judges: @ankushdharkar @yeopleekorea @NirantK and the mentors! @Dheemanthredy @pritisinghhhh @StalwartCoder @AdiChauhan18 @MotwaniSuhas @bondijois :) @mesaschool_ for the cool venue!

Profilbild von Harsh
Harshvor 1 Monat

@AnthropicAI @ElevCap What can be a practical use of this ? Like is is that one is able to visualise what agents are doing like on age of empires or what ?

Profilbild von Parth
Parthvor 1 Monat

> the way we code has changed. its much lesser about seeing the lines of code itself and managing agents. > chat is one possible way but when you have multiple agents working, its difficult to visualise / keep track of them. this could be one way, in a fun way > not advocating that this is the best way but our take on making it visual / fun :) > also because we have a visual real-estate, we can add small billboards with ads, making coding free for the end user!

Profilbild von Harsh
Harshvor 1 Monat

@AnthropicAI @ElevCap Last one is what can be a good use case, infact sandbox game us the same approach to sell there voxel lands to brands so they can advertise :)

Profilbild von Parth
Parthvor 1 Monat

@AnthropicAI @ElevCap do you have a link to it?

Profilbild von Harsh
Harshvor 1 Monat

@AnthropicAI @ElevCap @TheSandboxGame This one.

Profilbild von Asutosh Rath
Asutosh Rathvor 1 Monat

@AnthropicAI @ElevCap Streak 🎉 ongoing !! Congratulations 🎉

Profilbild von Parth
Parthvor 1 Monat

@AnthropicAI @ElevCap thanks Asutosh! ⚡️

Profilbild von Mustafa ✧
Mustafa ✧vor 1 Monat

@AnthropicAI @ElevCap Congrats guys!!!

Profilbild von Parth
Parthvor 1 Monat

@AnthropicAI @ElevCap thanks man! :)

Profilbild von Fahim
Fahimvor 1 Monat

@AnthropicAI @ElevCap streak continues!!

Profilbild von Parth
Parthvor 1 Monat

@AnthropicAI @ElevCap claude's plan

Profilbild von Shubhāng Galagali
Shubhāng Galagalivor 1 Monat

@AnthropicAI @ElevCap Undisputed legends 🔥 congratulations bossmen! Really an inspiration to us junis

Profilbild von Parth
Parthvor 1 Monat

@AnthropicAI @ElevCap thanks so much for the kind words Shubhang! 🥹

Profilbild von Apoorva
Apoorvavor 1 Monat

@AnthropicAI @ElevCap ab treat 😋😋

Profilbild von Parth
Parthvor 1 Monat

@AnthropicAI @ElevCap oh twitter started working 😼

Profilbild von Aravind Kumar
Aravind Kumarvor 1 Monat

@AnthropicAI @ElevCap Idea is so fascinating. Congrats 🎉

Profilbild von Parth
Parthvor 1 Monat

@AnthropicAI @ElevCap thanks so much Aravind! :))

Profilbild von Naomi
Naomivor 1 Monat

@AnthropicAI @ElevCap Congrats! 🎉

Profilbild von Parth
Parthvor 1 Monat

@AnthropicAI @ElevCap thanks Naomi! :)

Profilbild von Abinav
Abinavvor 1 Monat

@AnthropicAI @ElevCap Congrats ser 💪🚀!

Profilbild von Parth
Parthvor 1 Monat

@AnthropicAI @ElevCap thanks ser!

Profilbild von Amandeep
Amandeepvor 1 Monat

@AnthropicAI @ElevCap Less goo

Profilbild von Parth
Parthvor 1 Monat

@AnthropicAI @ElevCap lessgoooo

Profilbild von Naman Goyal
Naman Goyalvor 1 Monat

@AnthropicAI @ElevCap Congratulations 🥳

Profilbild von Parth
Parthvor 1 Monat

@AnthropicAI @ElevCap thanks Naman!

Profilbild von ZKryptosaurus
ZKryptosaurusvor 1 Monat

@AnthropicAI @ElevCap Congrats Champ 🏆 The saga continues 🔥

Profilbild von Parth
Parthvor 1 Monat

@KryptosaurusEth @AnthropicAI @ElevCap thanks Saurabh! 😎

Profilbild von DashX | Payments
DashX | Paymentsvor 1 Monat

@AnthropicAI @ElevCap upwards and onwards🔥

Profilbild von Parth
Parthvor 1 Monat

@AnthropicAI @ElevCap dashing throughhhh ⚡️

Profilbild von Rama Jha | Web3
Rama Jha | Web3vor 1 Monat

@AnthropicAI @ElevCap That concept sounds incredible, congrats on the win.

Profilbild von Parth
Parthvor 1 Monat

@AnthropicAI @ElevCap yo thanks so much!

Profilbild von Gargeya
Gargeyavor 1 Monat

@AnthropicAI @ElevCap yeah the city/agent UI is fun; the last line is the real product bet. software shifting from reading diffs to managing multiple agents isn't a joke. it's a new attention job. the scarce skill becomes knowing what "done" looks like while six buildings go up at once.

Profilbild von rishi jain
rishi jainvor 1 Monat

@AnthropicAI @ElevCap legend

Profilbild von Parth
Parthvor 1 Monat

@AnthropicAI @ElevCap 🙏🏼🙏🏼

Profilbild von Pranav
Pranavvor 1 Monat

@AnthropicAI @ElevCap Killing it brother 🔥

Profilbild von Parth
Parthvor 1 Monat

@AnthropicAI @ElevCap 🫶🏼

Profilbild von temp.md
temp.mdvor 1 Monat

@AnthropicAI @ElevCap PRs as ships is the sharp bit. It turns multi-agent work from hidden diffs into a place you can navigate, inspect, and decide what is ready to merge.

Profilbild von Parth
Parthvor 1 Monat

@AnthropicAI @ElevCap correct ai

Profilbild von Ginniiii
Ginniiiivor 1 Monat

@AnthropicAI @ElevCap congrats !!

Profilbild von Parth
Parthvor 1 Monat

@AnthropicAI @ElevCap thanks for the pictures ginni! 🥹

Profilbild von Deepak
Deepakvor 1 Monat

@AnthropicAI @ElevCap Congrats guys 🔥

Profilbild von Parth
Parthvor 1 Monat

@AnthropicAI @ElevCap thanks Deepak!!

Profilbild von yuvraj
yuvrajvor 1 Monat

@AnthropicAI @ElevCap so cool parth

Profilbild von Parth
Parthvor 1 Monat

@AnthropicAI @ElevCap thanks yuvraj! we should do a live event with headout for who builds the coolest city / most points 😋

Profilbild von yuvraj
yuvrajvor 1 Monat

@AnthropicAI @ElevCap good idea haha

Profilbild von Manideep
Manideepvor 1 Monat

@AnthropicAI @ElevCap Congratulations @mittalparth_ 🚀

Profilbild von Parth
Parthvor 1 Monat

@AnthropicAI @ElevCap thanks Manieeep 😄

Profilbild von Debsourya Datta
Debsourya Dattavor 1 Monat

@AnthropicAI @ElevCap Bro fucking nailing it everywhere 🔥

Profilbild von Parth
Parthvor 1 Monat

@AnthropicAI @ElevCap arey boss 🙏🏻🙏🏻

Profilbild von Debsourya Datta
Debsourya Dattavor 1 Monat

@AnthropicAI @ElevCap Kabhi hume bhi jeetaya Diya Karo sir :)

Profilbild von Abhinav Rao
Abhinav Raovor 1 Monat

@AnthropicAI @ElevCap Looks cool man!

Profilbild von Parth
Parthvor 1 Monat

@AnthropicAI @ElevCap thanks Abhinav! :)

Profilbild von Veeresh
Veereshvor 1 Monat

@AnthropicAI @ElevCap Dope stuff as always 🚀

Profilbild von Parth
Parthvor 1 Monat

@AnthropicAI @ElevCap 🫶🏻

Profilbild von Aashvi
Aashvivor 1 Monat

@AnthropicAI @ElevCap Damnn another one! Congrats⚡️

Profilbild von Parth
Parthvor 1 Monat

@AnthropicAI @ElevCap thank you Aashvi! :)

Profilbild von madhav kumar
madhav kumarvor 1 Monat

@AnthropicAI @ElevCap Congratulations 🎉🎉

Profilbild von Parth
Parthvor 1 Monat

@AnthropicAI @ElevCap thanks sirr!

Profilbild von Sherhin
Sherhinvor 1 Monat

@AnthropicAI @ElevCap Atp I was pretty sure you guys will win

Profilbild von Parth
Parthvor 1 Monat

@AnthropicAI @ElevCap arey 🙏🏼🙏🏼

Profilbild von AjayVK
AjayVKvor 1 Monat

@AnthropicAI @ElevCap Looks sick! Would love to try it out

Profilbild von Parth
Parthvor 1 Monat

@AnthropicAI @ElevCap thanks sir, soon!

Profilbild von Yash Agarwal
Yash Agarwalvor 1 Monat

@AnthropicAI @ElevCap congrat sir

Profilbild von Parth
Parthvor 1 Monat

@AnthropicAI @ElevCap thanks sir ♥️

Profilbild von Ram
Ramvor 1 Monat

@AnthropicAI @ElevCap That's cool

Profilbild von Parth
Parthvor 1 Monat

@AnthropicAI @ElevCap thanks Ram!

Profilbild von Utkarsh Kumar
Utkarsh Kumarvor 1 Monat

@AnthropicAI @ElevCap Congrats sir 🎉

Profilbild von Parth
Parthvor 1 Monat

@AnthropicAI @ElevCap thanks my man!

Profilbild von Sanath
Sanathvor 1 Monat

@AnthropicAI @ElevCap Winning spree continues Congrats guys 👏🏻

Profilbild von Parth
Parthvor 1 Monat

@sanath_106 @AnthropicAI @ElevCap thanks Sanath!!

Ähnliche Videos

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

56,502 Aufrufe • vor 3 Monaten

I got curious how compaction works as a PM, so I did some brain surgery on Claude Code: (Anthropic's been doing really interesting work on context editing - they showed Claude Opus playing Settlers of Catan for 75+ minutes in a single thread by constantly editing the context instead of starting fresh. When I saw that Claude Code has a compaction command with optional custom instructions, I wanted to understand what's actually happening.) Abhishek Katiyar and Aman Khan gave me the key tip: Claude Code stores all your conversation history as text files on your computer. Open a new directory and give Claude Code a task. Here's how to watch compaction happening: 1. Go to your user's root directory 2. Press Command+Shift+Period (Mac) to show hidden folders 3. Navigate to ~/.claude/projects/ 4. Find your project folder and use Cursor/VSCode to open it (there's a reason) 5. Install the JSONL Gazelle plugin (open source, thank you Gabor Cselle!) 6. Open the most recent JSONL file - each row is a message in your conversation 7. Run the compact command in Claude Code with custom instructions 8. Watch what happens in the file What I learned: When you compact, Claude Code doesn't just summarize and delete everything. It creates a "compact boundary" in the conversation file, writes a summary of what happened before, but keeps the full original conversation (!!!!) The new thread can still retrieve any details from before compaction if needed. That is so damn cool. Why this matters: What you're getting in Claude Code is similar to what Anthropic ships in their developer SDK - so inspecting your daily tools is how you build real product intuition. The best way to understand AI systems is to open them up and look inside. Everything is text files.

Tal Raviv

57,910 Aufrufe • vor 8 Monaten

In the future, you’ll be able to accomplish a goal by just giving Claude an outcome and a budget. That’s the direction Anthropic is building in with its new Managed Agents features, announced at this week’s Code with Claude developer event. The basic idea: Claude, wrapped in a computer in the cloud, that you can spin up, scale, and manage as needed. Anthropic is taking on the infrastructure that kills most agent products, and making sure that it scales to meet the needs of agents running 24/7. On this week’s AI & I from Every 📧, I talk with Angela Jiang (Angela Jiang), head of product for the Claude platform, and Katelyn Lesse (Katelyn Lesse), head of engineering for the Claude platform, about what Anthropic is building and what it takes to make agents reliable in production. We get into: - Why the "build a generic harness, hot-swap any model behind it" playbook is already outdated. Angela points to eval data on Memory where the same task across different harnesses performed drastically differently. - The infrastructure wall every team hits in production—and why Katelyn thinks “my sandbox died and took the agent with it” is the real reason internal agents don't ship. - Why Anthropic is so bullish on using file systems and skills within Claude, including Angela's argument that those early design choices can compound for years. This is a must-watch for anyone trying to take an agent past the demo and into production. Watch below! Timestamps: How the Claude platform evolved from API to agents: 00:01:48 The primitives that make up Claude Managed Agents: 00:04:09 Why the harness and the model are becoming a single unit: 00:10:37 The infrastructure wall that kills most agent projects in production: 00:18:49 Why team agents need a different shape than individual productivity tools: 00:24:49 How Anthropic's legal team uses an agent to review marketing copy: 00:26:36 Using multi-agent orchestration for advisor strategies, adversarial pairs, and swarms: 00:34:24 How to measure agent success with outcome and budget as the end state: 00:35:50 What the platform looks like a year from now, when Claude writes its own harness: 00:39:11

Dan Shipper

66,871 Aufrufe • vor 4 Monaten