Show HN: AI that extracts brand identity from websites to generate ads https://ift.tt/kiscW18

Show HN: AI that extracts brand identity from websites to generate ads I built this because I kept procrastinating on creating ads for my projects. The technical challenge was interesting: how do you teach AI to extract "brand identity" from a website? Turns out websites are messy. Finding the actual logo vs random images, identifying brand colors vs generic link colors, understanding brand voice from homepage copy. The solution: Custom vision models + CSS parsing + GPT-4 for voice analysis. You paste a URL, it extracts brand elements, generates platform-specific ads. Not trying to "disrupt advertising" or anything dramatic. Just solving the specific problem of "I need a Facebook ad but Canva makes me want to cry." Built with Next.js, custom image processing pipeline, OpenAI API. The brand extraction accuracy is around 85% for well-structured sites, lower for sites that are... creative with their CSS. Happy to discuss the technical approach or share code snippets if anyone's curious about the brand extraction pipeline. https://board.ad https://www.board.ad June 8, 2025 at 10:45AM

Show HN: A free, fast, and modern vehicle diagnostics tool https://ift.tt/eHSZ074

Show HN: A free, fast, and modern vehicle diagnostics tool https://ift.tt/YxHn56f June 7, 2025 at 11:57PM

Show HN: Solomon's Agent - a CLI to simplify the web https://ift.tt/jHoEDMb

Show HN: Solomon's Agent - a CLI to simplify the web https://ift.tt/Hc7kCWR June 6, 2025 at 10:54PM

Show HN: AI game animation sprite generator https://ift.tt/rIUE6gN

Show HN: AI game animation sprite generator I tried to build AI game animation generator last year ( https://ift.tt/LTxgMGn ), a lot of people were interested, but it failed, mainly because the technology was not good enough. 1 year passed, there were a lot of developments in video/image generation. I tried it again, I think it works super well now. Actually beyond my expectation. You can generate all kinds of game character animation sprites with only 1 image. 1, upload your image of your character 2, choose the action you want 3, generate! Support basic actions like Run, Jump, Punch and complicated ones like: Shoryuken, Spinning kick, etc. High quality sprite sheet will be directly generated to use in Unity and any game engine. If you are an indie game developer, you don't need to high an artist or animator to develop you game. For studios, it's 10x cost saving and 10x efficiency as no more creating animations for 100 NPCs 100 times. Please check it out, looking forward to your feedback! https://ift.tt/Qo9zu6D June 7, 2025 at 01:00AM

Show HN: Lightweight Durable Workflows Built on Postgres https://ift.tt/kMdEGje

Show HN: Lightweight Durable Workflows Built on Postgres Hi HN! This is Qian here with Peter (KraftyOne) and Jeremy (jedberg). We’re building DBOS, an open-source, lightweight durable workflows library that you can add to Python apps in just a few lines of code. It’s comparable to popular open-source workflow and queue libraries like Airflow and Celery, but more lightweight with a greater focus on reliability and automatically recovering from failures. Our goal in building DBOS is to make workflows lightweight and flexible so you can add them to your existing apps with minimal work. Everything you need to run durable workflows and queues is contained in this Python library. You don’t need to manage a separate workflow server: just install the library, connect it to a Postgres database (to store workflow/queue state) and you’re good to go. DBOS workflows make your program durable by checkpointing its state in Postgres. If your program ever fails, when it restarts all your workflows will automatically resume from the last completed step. You add durable workflows to your existing program by annotating ordinary functions as workflows and steps: from dbos import DBOS @DBOS.step() def step_one(): ... @DBOS.step() def step_two(): ... @DBOS.workflow() def workflow(): step_one() step_two() The workflow is just an ordinary Python function. You can call it any way you like–from a FastAPI handler, in response to events, wherever you’d normally call a function. We’ve just released DBOS Python 1.0. This enhances workflows with many powerful features we’ve been building over the last few months, including: - Durable queues. Postgres-backed queues with all the queuing features of BullMQ/Celery (concurrency limits, rate limits, timeouts, priority, deduplication, etc.). Plus, they integrate with durable workflows, so you can write a workflow that enqueues 1K tasks, waits for and processes their results, and automatically recovers from any interruption. - Programmatic workflow management. Your workflows are stored as rows in a Postgres table, so you have full programmatic control over them. Write scripts to query workflow executions, batch pause or resume workflows, or even restart failed workflows from a specific step. This makes it much easier to diagnose and recover from bugs and failures that affect thousands of workflows. - Full support for both sync and async Python–write your workflows and steps as code either synchronously or asynchronously, it all works out of the box. - Improved tooling, including dashboards, workflow graph visualization, workflow management via web UI, and more. We’d love to hear your feedback and hope you can try DBOS out! https://ift.tt/k48LbqE June 6, 2025 at 10:39PM

Show HN: Grab a Random ArXiv Paper https://ift.tt/I1uK7d0

Show HN: Grab a Random ArXiv Paper I needed a way to grab a random paper from arXiv, so I built one and wanted to share it with you. It 1) picks a random topic (of all the cs. , econ. , math.* etc. topics) 2) finds the maximum amount of papers in that topic, and 3) queries for a random paper in that topic. Note that this skews the distribution heavily in favor of topics that are less common, but it should get the job done. Suggestions for improvements are welcome. https://ift.tt/xncuhms June 5, 2025 at 11:13PM

Show HN: This database never puts you on hold https://ift.tt/9JwkIGN

Show HN: This database never puts you on hold Hey everyone! I hope you’re all having a great day. Today I’m sharing an experimental open-source project I’ve been working on for the past few months called Wildcat. Wildcat is an embedded persistent storage engine implementing an lsm tree similar to RocksDB and or LevelDB. The motivation for this system was to try to solve the multi-writer bottlenecks that most embedded systems incur. With that, during my journey with storage systems especially the log structured flavour I’ve implemented a lot of interesting optimizations and algorithms in regards to the write and read paths. I hope you check it out :) Alex https://ift.tt/3Hv4N1u June 5, 2025 at 11:02PM