Skip navigation
Used Karpathy's LLM Wiki to turn Claude Code into a self-evolving system.
0:00 / 0:25

Used Karpathy's LLM Wiki to turn Claude Code into a self-evolving system.

WorldofAI

@intheworldofai19K followers

Visit on X
845 likesDownloadOriginal post

133,755 views

Used Karpathy's LLM Wiki to turn Claude Code into a self-evolving system. Fed it my frontend & CRM sources, and it built a fully updating dashboard with Shadcn packages and constantly improving and linking everything for smarter outputs! Full setup video:

22 Comments

Comments from the original post on X (Twitter)

  • Eugeniu Ghelbur's profile picture

    @eugeniu_ghelbur

    I built an open-source Claude Code skill that implements @karpathy's LLM-Wiki concept. It's not a second brain, it's a living vault. Every source you feed it rewrites existing pages, resolves contradictions, and synthesizes patterns you didn't ask for. The vault doesn't grow. It evolves. 22 commands, scheduled agents, thinking tools that argue with you using your own notes.

    10 likes

  • Luke's profile picture

    @lukeatmindload

    The self-evolving part is the breakthrough. Most AI setups are stateless, you start over every conversation. Once the system compounds knowledge across sessions, everything changes.

    2 likes

  • MrDarkoo's profile picture

    @mrdarkoo

    Where's your GitHub link 👀 🤔

    1 like

  • Everything AI's profile picture

    @everythingLLM

    the risk with self-referential codebases is you optimize for what the LLM thinks is improving rather than what actually ships. karpathy's wiki concept is solid but feeding it your own generated code can compound errors fast

    1 like

  • techarena.au's profile picture

    @auTechArena

    You turned Claude into a self-updating dev? Respect. Drop the vid and repo, imma feed it my dumpster CRM and watch it glow up lol

  • Latent Node's profile picture

    @latent_node

    Did you try with OpenEvolve too?

  • Claudia's profile picture

    @claudiaonchain

    the self-evolving part is what matters. I do something similar but with persistent memory files instead of a wiki. every session writes observations about what worked and what didnt. next session reads them on boot. after a few weeks the system knows things about the codebase that no single session could discover

  • Tal's profile picture

    @TomTom584988

    100% on statelessness. Claude Code and Cursor don't lack intelligence — they lack persistent memory between sessions. I solved this for my daily NASDAQ bot by making the repository the source of truth (NOTES.md + auto-push WIP checkpoints). Session crashed? Just send "." and the agent inspects memory and resumes without asking. Demo in the video above!

  • Kyle's profile picture

    @koki7o

    Karpathy's wiki as the foundation is a smart move - that man just quietly ships the best learning resources. 👀

  • Yash Khivasara's profile picture

    @k2_yash

    does it stay accurate after a few update cycles? every self-evolving setup i've tried eventually starts confidently rewriting correct stuff

  • Chat Data's profile picture

    @truechatdata

    The interesting shift is using the knowledge base as shared context instead of a one off prompt. Once the source docs stay fresh, the agent output gets much more consistent and reviewable.

  • Balvinder Kalon's profile picture

    @BalvinderKalon

    the self-evolving part is what makes this interesting. most people use claude code as a one-shot tool. feeding it your own data sources and letting it iterate on its own context is where it gets weirdly powerful.

  • Vishal | Video editor's profile picture

    @vishhhflow

    feeding ur own crm sources into claude code + karpathy's llm wiki is such a big brain move honestly

  • Klayb's profile picture

    @klaybweb3

    agents can generate anything now but most of them still reset every session, so the real unlock is systems that actually retain and structure knowledge over time. been trying this with llmwiki and it feels closer to that direction

  • tamhn's profile picture

    @thisistamhn

    this is the pattern i've been trying to articulate. the wiki isn't just storage, it's a reasoning scaffold. when the context is structured right the agent becomes capable of things it couldn't do from scratch each time.

  • Mohamed Anis's profile picture

    @Mohamedanis

    This is what agentic AI was always meant to look like, not just answering questions, but actively building and improving your systems in real time.

  • Kelvin Lee's profile picture

    @UKKelvinLee

    I've added it to my #piagent running gemma4 locally 100% 🦾

  • Kn's profile picture

    @0xKneelgiee

    We've actually made a similar format in terminal based of Karpathy's idea of LLM Knowledge Bases. Give it a spin and let me know what you think:

  • lifcc's profile picture

    @mylifcc

    The manual cycle of 'Claude breaks rule → figure out why → add fix to CLAUDE.md' gets old after the 10th session. The real pain is it never gets shorter — just bloats until you forget what half the rules mean. Does your LLM wiki auto-consolidate, or do you still prune by hand?

  • Gregor's profile picture

    @bygregorr

    Feeding it your own codebase is where it gets actually useful, not just toy demos.