Ideas Lab
Real problems people complain about online, pulled every morning and scored out of 100. Build, validate, or skip. How scoring works
- Ideas
- 4,157
- BUILD
- 689
- Sources
- 8
- Last sync
- 15h ago
AI Agent Reliability and Performance Optimization
AI agents are unreliable in production. Developers lack tools to debug, test, and improve agent behavior systematically.
YC Graveyard3y agoToolAI/B2B
Brain-Computer Interface for Communication
Paralyzed or severely motor-impaired individuals (ALS, locked-in syndrome, spinal cord injury) cannot communicate naturally. Current BCIs are expensive, require clinical settings, and have low bandwidth. A scalable consumer BCI could enable thought-to-speech or thought-to-text for affected populations.
YC Graveyard5y agoToolConsumer/Healthcare
Access to Quality OB/GYN Care
Patients struggle to find quality OB/GYN care due to physician shortages, long wait times, and geographic constraints. Telehealth adoption is fragmented.
YC Graveyard4y agoToolHealthcare
Fragmented Procurement Process for SMBs
Small-to-medium businesses struggle with manual, fragmented procurement workflows. Sourcing, vendor management, invoice matching, and approval chains are still largely manual email/spreadsheet-based, creating inefficiency and errors.
YC Graveyard5y agoToolB2B
Agricultural Credit Access in Brazil
Brazilian smallholder and mid-size farmers lack access to affordable, streamlined credit products. Traditional banking is slow and expensive for this segment.
YC Graveyard5y agoToolAgriculture/Fintech
Browser-based light pollution simulator using real photometric data
Hi HN — author here. iesna.eu is a browser-based ecosystem for working with photometric data: parsing standard luminaire files (LDT/EULUMDAT, IES LM-63, Oxytech, ATLA-S001), running design calculations against EN 13201 / ANSI/IES RP-8 / CJJ 45 / IES-IDA MLO, and (the part I most want to show off here) rendering real urban scenes in Bevy with the photometric data driving actual streetlight behavior, including sky-glow contribution. The Skyglow Analysis demo loads a real LDT file into a Bevy scene (Khronos Bistro test asset). The luminaire's intensity distribution drives the streetlight rendering directly — no fudging — and the sky-glow grade updates live as you adjust the uplight percentage. Swap to a full-cutoff fixture and the sky goes from F (Severe) back to A (Excellent). You can see the difference on the buildings as well as in the sky. Stack: Rust core (eulumdat-rs and friends, ~20 crates handling photometric formats), Bevy for the 3D rendering, WASM for browser deployment. No backend; everything runs client-side. About a thousand lines of new code on top of the existing photometric library to make the Bevy integration work. Things I'd love feedback on:The atmospheric scattering model is currently single-scattering Rayleigh+Mie. Is that defensible for the use case, or should I move toward multi-scattering? The Bistro test scene works well visually but isn't a controlled environment. Anyone know of a public urban geometry asset that's more typical of real road-lighting evaluation? The CJJ 45 implementation (China's national road lighting standard) is the only one I've had to reverse-engineer from translated PDFs. If anyone has primary-source experience with it, I'd value a sanity check.Open-source on GitHub (eulumdat-rs and the related crates). Crates.io: eulumdat
Hacker News4mo agoToolAI
Tilde.run – Agent sandbox with a transactional, versioned filesystem
Hacker News4mo agoToolOther
Filling PDF forms with AI using client-side tool calling
Hey HN!I built SimplePDF Copilot: an AI assistant that can interact with the PDF editor. It fills fields, answers questions, focuses on a specific field, adds fields, deletes pages, and so on.It's built on top of SimplePDF that I started 7 years ago, pioneering privacy-respecting client-side pdf editing, now used monthly by 200k+ people.As for the privacy model: the PDF itself never leaves the browser. Parsing, rendering, and field detection all run client-side.The text the model needs (and your messages) goes to whatever LLM you point at. By default that's our demo proxy (DeepSeek V4 Flash, rate-capped), but you can BYOK and point it at any cloud provider, or go fully local (I've been testing with LM Studio).Unlike the existing "Chat with PDF" tools that only retrieve the text/OCR layer, Copilot can act on the PDF: filling fields, adding fields (detected client-side using CommonForms by Joe Barrow [1], jbarrow on HN with some post-processing heuristics I added on top), focusing on fields, deleting pages, and so on.I built this because SimplePDF is mostly used by healthcare customers where document privacy is paramount, and I wanted an AI experience that didn't require shipping PII to a third party. Stack is pretty standard:- Tanstack Start- AI SDK from Vercel- Tailwind (I personally prefer CSS modules, I'm old-school but the goal since I open source it, I figured that Tailwind would be a better fit)The more interesting part is the client-side tool calling: events are passed back and forth via iframe postMessage.If you're not familiar with "tool calling" and "client-side tool calling", a quick primer:Tool calling is what LLMs use to take actions. When Claude runs grep or ls, or hits an MCP server, those are tool calls.Client-side tool calling means the intent to call a tool comes from the LLM, but the execution happens in the browser.That matters for: speed, you can't go faster than client-to-clie
Hacker News4mo agoToolAI
Agent-desktop – Native desktop automation CLI for AI agents
I've been building computer-use tools for a while, and I quietly launched this about a month ago (122 Stars on GH). I figured it was worth sharing here.Over the last few months, a lot of computer-use agents have come out: Codex, Claude Code, CUA, and others. Most of them seem to work roughly like this: 1. Take a screenshot 2. Have the model predict pixel coordinates 3. Click x,y 4. Take another screenshot 5. RepeatThat works, but it's slow, expensive in tokens, and fragile. If the UI shifts a few pixels, things break. And the model still doesn't know what any element actually is.But the OS already exposes structured UI information: - macOS: Accessibility API - Windows: UI Automation - Linux: AT-SPI Screen readers have used these APIs for years. On the web, Playwright beat screenshot scraping for the same reason: structured access is just a better abstraction than pixels.So I built a desktop equivalent: agent-desktop.It's a cross-platform CLI for structured desktop automation through the accessibility tree. One Rust binary, about 15 MB, no runtime dependencies. It exposes 53 commands with JSON output, so an LLM can inspect and operate native apps without screenshots or vision models. Inspired by agent-browser by Vercel Labs.A typical loop looks like this: agent-desktop snapshot --app Slack -i --compact agent-desktop click @e12 agent-desktop type @e5 "ship it" agent-desktop press cmd+return So the loop becomes: 1. Snapshot 2. Decide 3. Act 4. Snapshot again The main design problem was context size.A naive approach would dump the full accessibility tree into the model, but real apps get huge. Slack can easily exceed 50,000 tokens for a full tree dump, which makes the approach impractical.The approach I ended up using is progressive skeleton traversal: - First pass: return a shallow tree, typically depth 3, with deeper containers truncated and annotated with children_count - Named containers get references
Hacker News4mo agoToolAI
Large Scale Article Extract of Newspapers 1730s-1960s
Hello HN, over the past 7 months I've spent nearly 3,000 hours on building SNEWPAPERS, the first historical newpaper archive with full-text extractions, nearly perfect OCR, a vast categorization taxonomy and of course with semantic and agentic search capabilities.Problem: I wanted to search through newspaper archives, but when I tried every service only lets you search for keywords and dates, and gives you back raw images of the papers, and too many of them with no context. A sea of noise.Solution: I taught machines how to read the newspapers and so far I've extracted the content from > 600k pages (about 5TB) from the Chronicling America collection. Problems I had to deal with were an infinite variety of layouts, font sizes, image scan qualities, resolutions, aspect ratios, navigating around the images on the page. I also had to figure out how to get OCR to be nearly perfect so people wouldn't hate reading the extracts. I stitched together a multi-model pipeline (layout tech, ocr tech, llm, vllm) with heuristics to go from layout -> segmentation -> classification. I put it all in OpenSearch / Postgres and made it semantically searchable and also put an agentic search tool on top that knows how to use the API really well and helps you write queries to find what you're looking for. Happy to discuss AWS architecture and scaling as well, that was tough!If you have five minutes and you just want to jump in and have your own personalized experience, what I would suggest is:Before searching for anything, go to the Sleuth page Ask it about anything from 1736 to 1963, maybe 1 or 2 follow up questions Then go to the search page so you can see the queries it wrote for you (bottom left "saved queries") and uncover more info on whatever it is you're interested inIf you think it's cool and you want to learn more, then there's about 10 minutes of video guides on the various capabilities in "Guide" on the n
Hacker News4mo agoToolAI
Mljar Studio – local AI data analyst that saves analysis as notebooks
Hi HN,I’ve been working on mljar-supervised (open-source AutoML for tabular data) for a few years. Recently I built a desktop app around it called MLJAR Studio.The idea is simple: you talk to your data in natural language, the AI generates Python code, executes it locally, and the whole conversation becomes a reproducible notebook (*.ipynb file). So instead of just chatting with data, you end up with something you can inspect, modify, and rerun.What MLJAR Studio does:- Sets up a local Python environment automatically, runs on Mac, Windows, and Linux- Installs missing packages during the conversation- Built-in AutoML for tabular data (classification, regression, multiclass)- Works with standard Python libraries (pandas, matplotlib, etc.)- Works with any data file: CSV, Excel, Stata, Parquet ...- Connects to PostgreSQL, MySQL, SQL Server, Snowflake, Databricks, and Supabase.For AI: use Ollama locally (zero data egress), bring your own OpenAI key, or use MLJAR AI add-on.I built this because I wanted something between Jupyter Notebook (flexible but manual) and AI tools that generate code but don’t preserve the workflow. Most tools I tried either hide too much or don’t give reproducible results and are cloud basedDemos:- 60-second demo: https://youtu.be/BjxpZYRiY4c- Full 3-minute analysis: https://youtu.be/1DHMMxaNJxIPricing is $199 one-time, with a 7-day trial.Curious if this is useful for others doing real data work, or if I’m solving my own problem here.Happy to answer questions.
Hacker News4mo agoToolAI
PHP-fts – Full-text search engine in pure PHP, no extensions
Hacker News4mo agoToolOther
Airbyte Agents – context for agents across multiple data sources
I’m Michel, co-founder and CEO of Airbyte (https://airbyte.com/). We’ve spent the last six years building data connectors. Today we're launching Airbyte Agents (https://docs.airbyte.com/ai-agents/), a unified data layer for agents to discover information and take action across operational systems.Here’s a quick walkthrough: https://www.youtube.com/watch?v=ZosDytyf1fgAs agents move into real workflows, they need access to more tools (e.g. Slack, Salesforce, Linear). That means a ton of API plumbing: authentication, pagination, filters, handling schema, and matching entities across systems.Most MCPs don’t fix this. They’re thin wrappers over APIs, so agents inherit their weak primitives and still get it wrong most of the time, especially when working across tools.An even deeper issue is that APIs assume you already know what to query (think endpoints, Object IDs, fields), whereas agents usually start one step earlier: they need first to discover what matters before they can even start reasoning.So we built Airbyte Agents to be a context layer between your Agents and all of your data. The core of this is something we call Context Store: a data index optimized for agentic search, populated by our replication connectors. All that work on data connectors the last six years comes in handy here!This gives agents a structured way to discover data, while still allowing them to read and write directly to the upstream system when needed.What got us working on this was an insane trace from an agent we were migrating to our new SDK. It was supposed to answer "which customers are at risk of leaving this quarter?" The trace had 47 steps. Most were API calls. The agent first had to find a bunch of accounts, then map them to the right customers, then look for tickets, bla bla... and when the Agent finally responded, the answer sounded ok, but was wrong. Not only that, it was excruciatingly slow. So we had to do somethin
Hacker News4mo agoToolAI
Those building Swift apps without touching Xcode, what is your workflow?
It's one thing having to download this monstrosity, and a whole other, having to use it daily to write code.
Hacker News4mo agoToolAI
I built an open-source email builder, alternative to Beefree/Unlayer
Hacker News4mo agoToolAI
Manually sniping arbitrage opportunities on prediction markets
Traders are tired of manually identifying and executing arbitrage opportunities on platforms like Polymarket because liquidity isn't always great and finding an edge requires quick action.
X4mo agoToolFinance
Manually finding and applying to job openings
Job seekers waste time manually searching for and applying to hundreds of job openings across platforms like LinkedIn, Google Forms, and Wellfound, seeking ways to automate discovery.
X4mo agoToolHR & Career
Daily manual content trend research
Content creators spend every morning manually researching trends and content ideas, wishing for automated agents to send daily summaries instead.
X4mo agoToolOther