nowfound

AI · May 10, 2026

IB

I built a 500K LOC production app alone in 7 months. Here is the proof

Here is the proof, a 5-hour uncut live session, no edits, no cuts: https://youtu.be/VPrU8WZJOVs Full article: https://medium.com/@bonjourjoel/i-built-a-500-000-line-produ... I believe I am the first human to have done this in a documented, verifiable way: maintaining a stable production-grade 500,000-line TypeScript codebase as a solo developer, using an AI coding assistant I built myself. If you know someone who has done the same, one person, 500k lines, documented proof, please write their name in the comments.

Alternativestop 10% of May 2026

Does the same job

all alternatives →
  • C3
    Codemaxxed – 350M+ LOC and a GitHub cease and desistApr 2026 · github.com · ▲5

    Built this code art project as a commentary on the recent wave of using LOC as a primary measure of engineering productivity It's now up to 350M lines of useless (but hopefully funny) code, constantly growing using GitHub actions and https://github.com/jshchnz/codemaxxing Unfortunately, GitHub has now sent me a notice to remove the repo within the next 14 days, so enjoy it while you can

  • FP
    First project and lessons learned2011 · ▲22

    A little background. For the last 1.5 years I lost what could be considered an embarrassing amount of money hiring other people to work on a project that I thought had potential, I got some important people involved, had some great coders, but couldn't launch. The failure was depressing, rejection by YC didn't help.. I had to take a job, I didn't enjoy and I had a girlfriend who stood by me despite going into debt. But bouncing back over the last 45 days I've taught myself Rails some Jquery, and Javascript and built this www.hangout.io. It's empowering to build something myself because I'm…

  • 2G
    2 guys -- Learned to code in 3 months and built this2012 · ▲27

    4 months ago sucked. Our technical co-founder quit after 6 months and we still had no product. My co-founder and I had been 'working' on our startup for 8 months. I say 'working' because as the "business people" - there wasn't a whole lot we could do except philosophize. We had gotten really awesome intros to some of the top VCs and entrepreneurs, but had nothing to show. And now we felt stranded. Had we wasted 8 months of our lives? Identity crisis? Check. So we did what any rational person would do - we ran to the mountains. Literally. In Boone, NC - we talked about why we started Knowit,…

  • BA
    Build apps with 500 models locally. No tracking, no cloud, just codeDec 2025 · github.com · ▲6

    I built CodinIT because I wanted that "Bolt-like" experience, but on my own terms. 100% Open Source The core idea: You should be able to prompt a full-stack application into existence, but the environment should be local, the models should be swappable (Ollama/LM Studio support was a priority), and the output should be standard code you actually own. A few things I focused on: Context Management: One of the hardest parts was figuring out how to feed the right file context back to the LLM without blowing out the token limit. I’ve implemented a custom indexing approach to keep the "vibe…

  • MP
    My programming language, building in public for 1 year2022 · petersaxton.uk · ▲7

    My weekly(ish) video logs tracking my progress of building a completely sound statically typed language and structural editor. The motivation is to make lots of invalid programs unrepresentable.

  • CS
    Case study: A coding agent refactors a 750k LOC app, no code reviewJul 2026 · ▲6

    In the following case study, the AI coding agent rebuilds a core system invariant in just three days, with minimal human input, running 31 verification passes and correcting 201 errors, before shipping code with zero bugs, zero regressions, and zero technical debt. https://aisovereignlabs.ai/docs/case-study/liveSession/case-... Disclaimers: This case study is NOT: - a project written from scratch - yet another Rust transpilation - a clone of an open-source project found in the LLM's training data - a Super Mario clone in HTML It IS: - a complex application…

More ai this month

the category →
  • I trained a 125M-parameter transformer to autocomplete piano performances in real time (~108 notes/sec on an iPhone 15). The idea is basically GitHub Copilot or Tabnine, except instead of prompting it with code, you prompt it by playing a few notes on a MIDI piano. The model then continues what you played, entirely on-device. The app is free if anyone wants to try it. Happy to answer questions about the model, training, Core ML, or the many things that didn't work.

    AI · 17d ago · simedw.com

  • Astute585

    Automate your B2B brand going viral, with new media creators

    AI · 18d ago · company-app.joinastute.com

  • Grok Bot547

    AI teammates that you can give real work to

    AI · 25d ago · x.ai

  • Hey HN, Henry from Cactus here! We previously released Cactus Needle, a 14MB agentic LLM for tool call, device use, and structured extraction for phones, wearables, smart homes, small robots and microcontrollers. We got really great feedback here, and have now incorporated the suggestions to release Needle 2. The whole model is a single 14MB binary that runs a full session in 28MB of RAM; 45m parameters at 2bit compression. Needle hits 500 tokens/sec decode speed on a Raspberry Pi 5, sits between 400-1,500 tokens/sec on VR devices like Meta Quest 3S and Apple Vision Pro, and ranges…

    AI · 27d ago · cactuscompute.com

  • Turn website visitors into qualified pipeline

    AI · 19d ago · clarasdr.ai

  • Kane CLI446

    Natural language browser & mobile app tests from terminal

    AI · 24d ago · testmuai.com

Launched alongside, May 2026

the whole month →
  • Brew 905

    Like Claude design for email marketing

    AI · May 2026 · brew.new

  • Parallel agents, diff reviewer, and multi-model comparisons

    Dev tools · May 2026 · kilo.ai

  • StoreClaw805

    Grow your store profits with agents that know how to sell

    AI · May 2026 · storeclaw.ai

  • Give your agent a real number and voice to make calls.

    AI · May 2026 · pollyreach.ai

  • NW

    Hey HN, Henry here from Cactus. We open-sourced Needle, a 26M parameter function-calling (tool use) model. It runs at 6000 tok/s prefill and 1200 tok/s decode on consumer devices. We were always frustrated by the little effort made towards building agentic models that run on budget phones, so we conducted investigations that led to an observation: agentic experiences are built upon tool calling, and massive models are overkill for it. Tool calling is fundamentally retrieval-and-assembly (match query to tool name, extract argument values, emit JSON), not reasoning. Cross-attention…

    Life & fun · May 2026 · github.com

  • FM

    Dev tools · May 2026 · github.com