Show HN: SteadyText: Deterministic LLMs: Same input → same output, every time https://ift.tt/8lg6P2x

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/Zk3I12R July 4, 2025 at 12:27AM

Show HN: Bookmark and organise your mobile links with ease with this free app https://ift.tt/V6uPZFH

Show HN: Bookmark and organise your mobile links with ease with this free app Do you have lists scattered all over your phone? Are you tired of saving recipes, books or restaurants in Notes, screenshots or Whatsapp groups? Listee is the bookmark tool to privately save and structure the things you love. Never lose track anymore of the places you loved, movies you wish to see or shoes you want to buy. Save any content in seconds using the share function on your phone or the search engine within Listee. Connect with your friends to share your favourites or create lists together. Listee is the new way to save, share and explore with the ones you love and trust. Also for your wish lists! https://ift.tt/6Pu1pk5 July 3, 2025 at 02:13PM

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

Show HN: I made a social media platform https://onelined.tech/ July 3, 2025 at 09:23AM

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

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 07:32AM

Show HN: Issue Duration Labeler – a GitHub Action that labels issue by age https://ift.tt/GteJCs2

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/sdl59P0... https://ift.tt/kA07Jyq July 3, 2025 at 03:15AM

Show HN: Core – open source memory graph for LLMs – shareable, user owned https://ift.tt/mVZIBn6

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/K7tV82w 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/aoA8Mvx https://ift.tt/K7tV82w July 1, 2025 at 09:54PM

Show HN: Fixstars AIBooster – Accelerate AI Training and Cut GPU Costs https://ift.tt/87iNcvG

Show HN: Fixstars AIBooster – Accelerate AI Training and Cut GPU Costs Hi HN, We're excited to introduce Fixstars AIBooster, our new performance engineering tool designed to significantly accelerate AI model training while optimizing GPU utilization. AIBooster provides: Real-time monitoring of GPU, CPU, memory, and power consumption. Clear visibility into performance bottlenecks, helping developers optimize AI workloads. Proven acceleration of AI training processes—users commonly achieve up to 2-3x speed improvements. Significant cost savings by maximizing infrastructure efficiency. It's free to try, requires minimal setup, and integrates seamlessly into your existing infrastructure. We've built this tool to empower AI developers to get the most from their GPU infrastructure without complicated tuning. We'd love your feedback, questions, or suggestions! https://ift.tt/fY2nmQr July 2, 2025 at 12:15AM

Show HN: Runik – Turn fan wikis into e-reader dictionaries https://ift.tt/F92wi7Y

Show HN: Runik – Turn fan wikis into e-reader dictionaries Hey HN! As a reader of epic fantasy and sci-fi, I often find myself reaching for my phone to look up an obscure side character — or the difference between “Genebackis” and “Genebaris”. So I built runik to bring in-world definitions directly onto my e-reader and stay immersed in the story. Runik parses the contents of fan wikis into Kobo and Kindle compatible dictionaries. It uses the device’s built-in word lookup feature, so there’s no jailbreaking required and definitions can be used offline. It’s still in early development and is built with Go (Wails) + Svelte + Dictutil — feedback is appreciated! Note: Kindle support requires kindlegen, which comes bundled with the Kindle Previewer app (details in the README). https://runik.app/ https://ift.tt/xSp8JGZ https://ift.tt/xSp8JGZ July 1, 2025 at 11:25PM

Show HN: C.O.R.E – Opensource, user owned, shareable memory for Claude, Cursor https://ift.tt/VogWu3E

Show HN: C.O.R.E – Opensource, user owned, shareable memory for Claude, Cursor Hi HN, 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/K7tV82w 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. Why this matters - Ask “What’s our roadmap now?” and “What was it last quarter?” — timeline and authorship are always preserved. - Change a preference (e.g. “I no longer use shadcn”) — assistants see both old and new memory, so no more stale facts or embarrassing hallucinations. - Every answer is traceable: hover a fact to see who/when/why it got there. Try it - Hosted free tier (HN launch): https://core.heysol.ai - Docs: https://ift.tt/aoA8Mvx https://ift.tt/K7tV82w July 1, 2025 at 02:40AM

Show HN: Audiopipe – Pipeline for audio diarization, denoising and transcription https://ift.tt/L8R2jXN

Show HN: Audiopipe – Pipeline for audio diarization, denoising and transcription Audiopipe is a one-liner for denoising, diarization and transcription with demucs + pyannote + insanely-fast-whisper. Made it to transcribe podcasts and Dungeons And Dragons sessions, figured it could be useful. It also has a wasm UI to load transcriptions and audio. Feel free to contribute! Feedback appreciated. https://ift.tt/b1Yk5GW July 1, 2025 at 01:02AM

Show HN: Attach Gateway – one-command OIDC/DID auth for local LLMs https://ift.tt/WzLAplN

Show HN: Attach Gateway – one-command OIDC/DID auth for local LLMs We’ve been building local and on-prem agent workflows for open-source LLMs. Engines like Ollama or vLLM ship with no auth, so every team ends up writing the same JWT proxy. Attach Gateway is a single process that sits in front of any model server and handles the boring bits: - verifies OIDC / DID JWTs - adds X-Attach-User and X-Attach-Session headers so downstream agents share the same identity - optional /a2a/tasks/send endpoint for Google-style A2A hand-offs - mirrors prompts + completions to Weaviate (runs in Docker) One `pip install attach-dev`, export a token, run `attach-gateway`, and your local Ollama is protected in under 60 seconds. Repo: https://ift.tt/mtpIW4k PyPI: https://ift.tt/VZDsrIY Would love feedback – especially from teams doing multi-agent or on-prem work. https://ift.tt/mtpIW4k June 30, 2025 at 11:38PM

Show HN: Tablr – Supabase with AI Features https://ift.tt/ltABMro

Show HN: Tablr – Supabase with AI Features https://www.tablr.dev/ June 30, 2025 at 04:35AM

Show HN: Summle – A little maths Game https://ift.tt/pelw48M

Show HN: Summle – A little maths Game https://summle.net June 26, 2025 at 04:28PM

Show HN: Sharpe Ratio Calculation Tool https://ift.tt/JMkqalb

Show HN: Sharpe Ratio Calculation Tool I built a simple but effective Sharpe Ratio calculator that gives the full historical variation of it. Should I add other rations like Calmar and Sortino? https://ift.tt/YwTa9xX June 29, 2025 at 11:08PM

Show HN: Anti-Cluely – Detect virtual devices and cheating tools on exam systems https://ift.tt/sikVIqQ

Show HN: Anti-Cluely – Detect virtual devices and cheating tools on exam systems Anti-Cluely is a lightweight tool designed to detect common virtual environments, device emulators, and system manipulation tools often used to bypass or cheat in online exams. https://ift.tt/GedFhmN June 29, 2025 at 01:11AM

Show HN: Query your Rust codebase and generate types for anything https://ift.tt/LgQ4tDh

Show HN: Query your Rust codebase and generate types for anything Hello HN! As a long-time professional Rust developer. I've always been frustrated by the difficulty and "hackiness" of producing bindings to other languages, whether a frontend, an FFI library, etc. Not just in Rust but in any language. After many years of trying existing solutions and trying to make my own, I've finally developed a solution I'm very happy with. RTK (aka Rust Type Kit) allows you to write Lua scripts that perform queries on your code, such as method calls to Axum's `.route`, function definitions, and more, and then receive rich type information including all argument types, function paths, proc macro attributes, and more. Your Lua script can then read this information and emit an output file in any language of your choosing. Or, you can emit compiler errors and use it as a linter of sorts. You can even directly re-emit Rust code itself and use this as a richer proc macro solution! The code example is a bit verbose, so I encourage you to take a look at the repo's README. I look forward to hearing your thoughts, or any usecases you may come up with! https://ift.tt/qMOTg3f June 29, 2025 at 12:25AM

Show HN: A Go service that exposes a FIFO message queue in RAM https://ift.tt/WfkuE69

Show HN: A Go service that exposes a FIFO message queue in RAM https://ift.tt/o5qPZ6C June 25, 2025 at 05:04PM

Show HN: GPU market is absurd! So I built a dashboard of pricing/restock trends https://ift.tt/dYNbrXT

Show HN: GPU market is absurd! So I built a dashboard of pricing/restock trends Hey HN! This idea started with me not being able to buy a GPU and constantly losing to bots/scalpers. I figured I'd use this as way to see how far I can get with 'vibe-coding and designing'*. The end result was pretty far! Here are more details of behind the scenes. In a future blog post, I'll detail behind the scenes process of building this. - The landing page is React/Typescript/Tailwind.css (which I've never used before) - The dashboard is based on Evidence.dev - which is SQL queries in Markdown + little bit of custom Javascript for chart formatting (again never used before :) - Just being able to get an idea like this in my head into existence would have taken me many months of Stack overflow/Google research to first learn React/Typescript/Javascript but this took about a month (~1-2 hr a day) * 'Vibe-coded' is often a misnomer i.e. people sometime think it's a magic pill. From building this I can tell you that you can't just will the site into existence like a genie's wish. It still took significant effort to guide the LLM, debug when things go wrong, need to have an idea of design and taste of what to build and how to make it look good, work on many iterations. There were probably 500 iterations between the first and the final iteration. https://ift.tt/b9XURxi June 28, 2025 at 12:32AM

Show HN: I built Hispi, an app to design custom jewellery https://ift.tt/ctbV0Xi

Show HN: I built Hispi, an app to design custom jewellery Designing is free and gives you a breakdown of material choices and costs, then you can get a quote if you want to buy the ring. I'm working with around 50 jewellers in London and the UK's Jewellery Quarter but I think just designing a ring is pretty nice. https://hispi.app June 24, 2025 at 07:08PM

Show HN: Do You Know RGB? https://ift.tt/7Md3jpc

Show HN: Do You Know RGB? https://ift.tt/RTsHi0L June 24, 2025 at 01:49PM