Turn any Github Repository into a prompt-friendly LLM-ready text!
Just replace "hub" with "ingest" in a GitHub URL and receive a prompt-friendly text ingest for LLMs.
100% Open Source
You can now use Knowledge Graphs with Claude 3.5 Sonnet in Cursor! 🤩
CodeGPT’s Knowledge Graphs (KG) let you explore your entire codebase. In this case, we're navigating through @AnthropicAI Python SDK.
We asked how to send messages in batches and the tool identified the nodes and relationships in all relevant functions and classes.
If you're curious about how LLMs will start handling large code repositories, you'll want to start programming CodeGPT’s KGs... I bet @karpathy will find this fascinating!
I hope you get to try them out, because for me, reading documentation feels so 2024... now I just turn repos into KGs and get to work! 🧑🏽💻
Giving an AI agent access to my iPhone.
Your phone knows you better than anyone. What if your AI agent could go through your phone to truly understand you?
The EXO Agent uses iPhone mirroring to look through your apps including YouTube/Netflix watch history, X likes and photos. With every swipe, it learns who you are.
No logins or APIs. Just your phone, mirrored.
Available in preview with the EXO Desktop App (link below).
We’re kicking off 2025 with everything we've got! 🤩
Introducing CodeGPT's Knowledge Graphs, navigating through the entire Anthropic SDK repository.
In this example, we loaded @AnthropicAI Python SDK repository and successfully provided the LLM with all the knowledge it needs to fully understand the codebase.
You can leverage these knowledge graphs using the CodeGPT extension in VSCode by simply calling the @codebase command 👏
Stay tuned for more tutorials on how to use this powerful tool!
Happy 2025! 🎉
I’ve built 9+ products for clients using Cursor, and I’ve cracked the most efficient way to use it with minimal mistakes.
If you’re a beginner, this thread has everything you need to get started and make Cursor work for you – thread below.
@chandlerjward @rileybrown_ai @cursor_ai Composer + agent I don't have to do that as much as I would in Zed. But still have to do that occasional as well.
I don't know what the .cursorrules is, will check it out. Thanks!
@chandlerjward @rileybrown_ai @cursor_ai Part (2/2)
Also, this is actually pretty sweet. Get Claude to run its own test against the code that it built. I have my Claude spinning up virtual env servers and testing the code prior to me even reviewing it. At a point now where stuff just "works" after 1 or 2 tries.
@chandlerjward @rileybrown_ai @cursor_ai My recommendation is to provide high level overview of what project you're building during init. Then focus on building out one feature at a time. This keeps context smaller and more specified. Simple but single biggest key.
We shipped several upgrades to our Apply model this month. It can now accurately edit over 5k tokens per second.
Try it out in chat, composer, or agent!
The more I read and use AI the more I realize I have nothing to contribute to the world intellectually.
I think that's one reason I ran out of steam to make YouTube videos. I said before, it felt like an increasingly futile act.
It's really kind of a relief though. I was "the man in the chair" during my career. The one fixing million-dollar-per-hour outages. The one planning and deploying central infrastructure.
I had sort of learned that the world depended on me, and people like me, to keep turning. (Seriously you have no idea...)
But now I see the writing on the wall. Within a few years we're going to have a global operating system powered by billions of agents several standard deviations more intelligent than me.
The very thin line of experts that keep the ship afloat today will soon have armies of support. Intellectual scarcity is about to get nuked out of existence.
I can finally rest.
Came across an hour-long talk on YouTube that I wanted to watch. Rather than spend an hour watching it, I pasted the URL into a site that generates transcripts of YouTube videos and then pasted the transcript into Grok and asked for a summary. Got the gist in three minutes.
Wait this is fucking insane — Claude immediately guessed I was French.
How can anyone still think these things are stochastic parrot and not reasoning? Do they really think there is much "people guessing what people's native languages are" in the training data?