Show HN: SteadyText: Deterministic LLMs: Same input → same output, every time https://ift.tt/GW5Lrt0

Show HN: SteadyText: Deterministic LLMs: Same input → same output, every time Hey HN! After spending way too many nights debugging flaky AI tests, I built SteadyText. It's a simple python library for deterministic llm generations and embeddings. We use it in production for: - Testing our AI features (zero flakes in 3 months) - CLI tools that need consistent outputs - Reproducible documentation examples It's not for creative tasks - this is specifically for when you need AI to be boring and predictable. Think of it as the opposite of ChatGPT. The coolest part? It includes a Postgres extension. You can now do: SELECT steadytext_generate('explain this query: ...'); And it will always return the same explanation. :) How it works: 1. Greedy decoding- Always pick the highest probability token (no randomness) 2. 8-bit quantization- Same numerics across all platforms It's easy to get started: uv tool install steadytext echo Hello | st https://ift.tt/6RDC4p3 July 3, 2025 at 10:57PM

Show HN: I made a social media platform https://ift.tt/Rb1CPqU

Show HN: I made a social media platform https://onelined.tech/ July 3, 2025 at 07:53AM

Show HN: I made a Chrome extension to export web element to code https://ift.tt/cWJuhvO

Show HN: I made a Chrome extension to export web element to code Recently I'm working on CopyUI which is an extension to copy UI element from websites and export html(or jsx) and css(or tailwind). I'm building this tool in order to create better landing pages because I'm really not good at layout and colors. So I hope to learn from others' design and innovate later, not to simply replicate. https://copyui.online July 3, 2025 at 06:02AM

Show HN: I created a privacy respecting ad blocker for apps https://ift.tt/dgNG3Yx

Show HN: I created a privacy respecting ad blocker for apps Hey HN, I’ve been working on developing my ad blocker for the last number of years and am proud to share that I have now released a new feature that blocks ads directly in apps — not just in a web browser. What makes this app ad blocker feature special? - All ad blocking is done directly on device, - Using a fast, efficient Swift-based architecture (based upon Swift-NIO) - Follows a strict ZERO data collection and logging policy - Blocks ads in all apps on iPhones, iPads and Macs It works as a local VPN proxy, so it filters all of your traffic locally without going through any third-party servers. The app ad blocker works across News apps, Social media, Games and even browsers like Chrome and Firefox. After using ad blocking in Safari for a long time, it is eye-opening how many ads and trackers are also embedded in apps themselves. The app is available via the App Store, with a 30 day free trial, before an annual subscription is required. I know there are many other ad blockers available, but I hope the combination of performance, efficiency and respect for privacy will mean that this particular feature is a valuable option. It also took a LOT of work to get this working seamlessly within the App Store and iOS / macOS limitations, so am glad the app has been able to finally be released into the world. Full details on the feature are in the release post: https://ift.tt/5T1xGbX https://ift.tt/5T1xGbX July 3, 2025 at 05:04AM

Show HN: Issue Duration Labeler – a GitHub Action that labels issue by age https://ift.tt/pBPVwbj

Show HN: Issue Duration Labeler – a GitHub Action that labels issue by age I’ve built *Issue Duration Labeler*, a GitHub Action that automatically adds *color-coded duration labels* to every issue in a repo: Default label thresholds: Green – ≤ 7 days (configurable) Orange – ≤ 30 days Red – > 30 days For open issues we compute “age” (creation → now). You can adjust the day thresholds and label colors in the workflow file, and choose whether labels update daily or only when they cross the next threshold. *Why?* I often lost track of how long tickets had been lingering, especially in older projects. A quick glance at the issue list or github project now tells us what’s fresh, what’s getting stale, and what’s officially ancient. It’s also handy for post-mortems: sort by red labels to see which bugs took the longest to close. *Link* https://ift.tt/F6GktU9... https://ift.tt/Fg5P9Vd July 3, 2025 at 01:45AM

Show HN: Terminal in Browser https://ift.tt/v8yRQkY

Show HN: Terminal in Browser I wrote a small golang project to render terminal on browser. It is a single binary that can be deployed on any server and you can access the terminal over web. https://ift.tt/Savln2g July 2, 2025 at 01:26AM

Show HN: Generate presentation slides from Jira backlog. + Demo-playground https://ift.tt/xTeOlDy

Show HN: Generate presentation slides from Jira backlog. + Demo-playground https://agileplus.io/ July 2, 2025 at 12:22AM

Show HN: Core – open source memory graph for LLMs – shareable, user owned https://ift.tt/KsMbqTv

Show HN: Core – open source memory graph for LLMs – shareable, user owned I keep running in the same problem of each AI app “remembers” me in its own silo. ChatGPT knows my project details, Cursor forgets them, Claude starts from zero… so I end up re-explaining myself dozens of times a day across these apps. The deeper problem 1. Not portable – context is vendor-locked; nothing travels across tools. 2. Not relational – most memory systems store only the latest fact (“sticky notes”) with no history or provenance. 3. Not yours – your AI memory is sensitive first-party data, yet you have no control over where it lives or how it’s queried. Demo video: https://youtu.be/iANZ32dnK60 Repo: https://ift.tt/A7MVfZw What we built - CORE (Context Oriented Relational Engine): An open source, shareable knowledge graph (your memory vault) that lets any LLM (ChatGPT, Cursor, Claude, SOL, etc.) share and query the same persistent context. - Temporal + relational: Every fact gets a full version history (who, when, why), and nothing is wiped out when you change it—just timestamped and retired. - Local-first or hosted: Run it offline in Docker, or use our hosted instance. You choose which memories sync and which stay private. Try it - Hosted free tier (HN launch): https://core.heysol.ai - Docs: https://ift.tt/Xtf0esY https://ift.tt/A7MVfZw July 1, 2025 at 08:24PM