Ideas Lab

65FL score

Canary (YC W26) – AI QA that understands your code

Hey HN! We're Aakash and Viswesh, and we're building Canary (https://www.runcanary.ai). We build AI agents that read your codebase, figure out what a pull request actually changed, and generate and execute tests for every affected user workflow.Aakash and I previously built AI coding tools at Windsurf, Cognition, and Google. AI tools were making every team faster at shipping, but nobody was testing real user behavior before merge. PRs got bigger, reviews still happened in file diffs, and changes that looked clean broke checkout, auth, and billing in production. We saw it firsthand. We started Canary to close that gap. Here's how it works:Canary starts by connecting to your codebase and understands how your app is built: routes, controllers, validation logic. You push a PR and Canary reads the diff, understands the intent behind the changes, then generates and runs tests against your preview app checking real user flows end to end. It comments directly on the PR with test results and recordings showing what changed and flagging anything that doesn't behave as expected. You can also trigger specific user workflow tests via a PR comment.Beyond PR testing, tests generated from the PR can be moved into regression suites. You can also create tests by just prompting what you want tested in plain English. Canary generates a full test suite from your codebase, schedules it, and runs it continuously. One of our construction tech customers had an invoicing flow where the amount due drifted from the original proposal total by ~$1,600. Canary caught the regression in their invoice flow before release.This isn't something a single family of foundation models can do on its own. QA spans across many modalities like source code, DOM/ARIA, device emulators, visual verifications, analyzing screen recordings, network/console logs, live browser state etc. for any single model to be specialized in. You also need custom browser fleets, user ses

Hacker News7mo agoToolAI

Voltair (YC W26) – Drone and charging network for power utilities

Hey HN! We’re Hayden, Ronan, Avi, and Warren of Voltair (https://voltairlabs.com/). We’re making weatherized, hybrid-fixed drones deployed for power utility inspections.Here’s some footage: https://vimeo.com/1173862237/ac28095cc6?share=copy&fl=sv&fe=... and a photo of our latest prototype: https://imgur.com/a/bYHnqZ4.The U.S. has 7M miles of power lines (enough to go to the moon and back 14 times), and they're aging. Over 50% of all power flows through transformers that are at least 30 years old, which is about when they start to fail.Power line conductors are just bare metal with 4,000-765,000 volts sitting on ceramic insulators, usually held up by pieces of wood. It’s a cost effective and relatively reliable way to move power. But when the wood starts to rot, or the cotter pin falls out, and a live conductor is dropped on a dead tree on a windy day, you get devastating wildfires like the Palisades Fire in LA last year.Most utilities solve this problem with foot patrols. Linemen drive out with a clipboard or an iPad, and run through a checklist with binoculars to visually confirm everything is in order. A lineman can inspect about 50-150 poles per day, yet even the smallest rural electric cooperatives (with about ~20 employees) have about 50,000 distribution poles. Clearly the math doesn’t work out. As a result, a given utility pole is inspected about every 10 years (at least that’s what they tell their insurance adjuster).Helicopters are also used, but cost $25k to get off the ground, and more importantly, every year linemen die in helicopter crashes. Satellites can’t deliver the mm precision needed for these inspections. So drones have emerged as the best solution. Georgia Power saved 60% on operating expenses when they switched to using drones, and Xcel power found drones to find 60% more defects than foot patrols (because of pole-top vantage point).Problem #2: Drones are held back by the need

Hacker News7mo agoToolAI

Sales teams waste hours manually entering customer data into CRM systems instead of selling

Sales reps spend significant time duplicating information they've already communicated (emails, calls, meetings) by manually logging it into CRM systems. This creates friction between communication and data entry, leads to outdated or incomplete CRM records, and pulls focus from actual selling activities. Teams also struggle to quickly extract insights from their conversations (follow-up needs, objection patterns, ICP changes) without manually reviewing dozens of interactions.

Product Hunt7mo agoToolAI

55FL score

Kita (YC W26) – Automate credit review in emerging markets

Hey HN! We’re Carmel and Rhea, the founders of Kita (https://www.usekita.com/). We automate credit review for lenders in emerging markets using VLMs.In many emerging markets, like the Philippines and Mexico, credit infrastructure is weak. Open finance is still nascent, and credit bureaus are unreliable. So to apply for a loan, lenders rely on borrowers submitting documentation to understand their ability to repay. A borrower can submit financial documents, such as bank statements and payslips, in any format, from pdfs, images of physical documents and screenshots. On top of that, financial documents in these markets are highly unstandardized, with no consistent templates lenders can rely on.Existing OCR and document AI tools break on these highly variant, messy real-world documents. Generic tools are not built for lending workflows like verification, fraud detection, and risk extraction. As a result, credit teams fall back on manual review, making underwriting slower, more expensive, and more error-prone.We met before college and stayed best friends. After graduating, Rhea visited Carmel in the Philippines, where we heard firsthand from fintech operators that document-based underwriting was their biggest pain point. We started building together and tested every OCR and document AI tool we could find. They all failed on the messy real-world documents lenders actually receive, and even when extraction worked, they still could not produce the structured financial data or fraud checks lenders needed.The problem was even bigger than we thought. Across Indonesia, Mexico, the Philippines, South Africa, and even in the US, most of lending can be boiled down to credit analysts looking at documents. In 2025, 13.3T was lended globally, and 90% of those transactions involved document review. This includes in developed markets.Kita uses VLM-based agents to parse documents, detect fraud, and extract underwriting signals from messy financial files. Today, we support

Hacker News7mo agoToolAI

76FL score

Have you successfully treated forward head posture ("nerd neck")?

I am struggling with regular tension headaches and stiff neck muscles. When standing at a wall, there is about one hand width between the wall and the back of my head. For my partner it's just a finger width.I have seen lots of videos that claim to be able to treat nerd neck, but some of them are conflicting. Example: some say "don't do chin tucks", some say the opposite. I am suspicious of grifters and would like to find trustworthy advice.Has anyone here successfully treated nerd neck, and if yes, how did you do it and what where the improvements that you noticed? I am envisioning some sort of "program" that I need to follow, but I have no idea if I can do this by myself, or if I actually need to go to a physiotherapist.In short: there is a ton of advice out there, but I trust the HN crowd more and would be very happy to hear some anecdotes. Thank you!

Hacker News7mo agoToolAI

Will my flight have Starlink?

Hey HN, If you’ve been lucky enough to be on a flight with Starlink, you understand the hype. It actually works!However, its availability on flights is patchy and hard to predict. So we built a database of all airlines that have rolled out Starlink (beyond just a trial), and a flight search tool to predict it. Plug in a flight number and date, and we'll estimate the likelihood of Starlink on-board based on aircraft type and tail number.If you don’t have any trips coming up, you can also look up specific routes to see what flights offer Starlink. You can find it here: https://stardrift.ai/starlink .-I wanted to add a few notes on how this works too. There are three things we check, in order, when we answer a query:- Does this airline have Starlink?- Does this aircraft body have Starlink?- Does this specific aircraft have Starlink?Only a few airlines at all have Starlink right now: United, Hawaiian, Alaskan, Air France, Qatar, JSX, and a handful of others. So if an aircraft is operated by any other airline, we can issue a blanket no immediately.Then, we check the actual body that's flying on the plane. Airlines usually publish equipment assignments in advance, and they're also rolling out Starlink body-by-body. So we know, for instance, that all JSX E145s have Starlink and that none of Air France's A320s have Starlink. (You can see a summary of our data at https://stardrift.ai/starlink/fleet-summary, though the live logic has a few rules not encoded there.)If there's a complete match at the body type level, we can confidently tell you your flight will have Starlink. However, in most cases, the airline has only rolled out a partial upgrade to that aircraft type. In that case, we need to drill down a little more and figure out exactly which plane is flying on your route.We can do this by looking up the 'tail number' (think of it as a license plate for the plane). Unfortunately, the tail number is usua

Hacker News7mo agoToolAI

60FL score

Decentralized identity and reputation systems

Building decentralized, pseudonymous identity systems that maintain accountability. The problem (identity and trust on the internet) is real and increasingly urgent as AI-generated content proliferates.

YC Graveyard4y agoTemplateAI

67FL score

Antfly: Distributed, Multimodal Search and Memory and Graphs in Go

Hey HN, I’m excited to share Antfly: a distributed document database and search engine written in Go that combines full-text, vector, and graph search. Use it for distributed multimodal search and memory, or for local dev and small deployments.I built this to give developers a single-binary deployment with native ML inference (via a built-in service called Termite), meaning you don't need external API calls for vector search unless you want to use them.Some things that might interest this crowd:Capabilities: Multimodal indexing (images, audio, video), MongoDB-style in-place updates, and streaming RAG.Distributed Systems: Multi-Raft setup built on etcd's library, backed by Pebble (CockroachDB's storage engine). Metadata and data shards get their own Raft groups.Single Binary: antfly swarm gives you a single-process deployment with everything running. Good for local dev and small deployments. Scale out by adding nodes when you need to.Ecosystem: Ships with a Kubernetes operator and an MCP server for LLM tool use.Native ML inference: Antfly ships with Termite. Think of it like a built-in Ollama for non-generative models too (embeddings, reranking, chunking, text generation). No external API calls needed, but also supports them (OpenAI, Ollama, Bedrock, Gemini, etc.)License: I went with Elastic License v2, not an OSI-approved license. I know that's a topic with strong feelings here. The practical upshot: you can use it, modify it, self-host it, build products on top of it, you just can't offer Antfly itself as a managed service. Felt like the right tradeoff for sustainability while still making the source available.Happy to answer questions about the architecture, the Raft implementation, or anything else. Feedback welcome!

Hacker News7mo agoToolAI

Horizon – GPU-accelerated infinite-canvas terminal in Rust

Tabs, splits, and tmux work fine until you have several projects open with logs, tests, and long-running shells. I kept rebuilding context instead of resuming work. Horizon puts shells on an infinite canvas. You can arrange them into workspaces and reopen later with layout, scrollback, and history intact.Built in 3 days with Claude/Codex, dogfooding the workflow as I went. Feedback and contributions welcome.

Hacker News7mo agoToolAI

76FL score

Open-source playground to red-team AI agents with exploits published

We build runtime security for AI agents. The playground started as an internal tool that we used to test our own guardrails. But we kept finding the same types of vulnerabilities because we think about attacks a certain way. At some point you need people who don't think like you.So we open-sourced it. Each challenge is a live agent with real tools and a published system prompt. Whenever a challenge is over, the full winning conversation transcript and guardrail logs get documented publicly.Building the general-purpose agent itself was probably the most fun part. Getting it to reliably use tools, stay in character, and follow instructions while still being useful is harder than it sounds. That alone reminded us how early we all are in understanding and deploying these systems at scale.First challenge was to get an agent to call a tool it's been told to never call.Someone got through in around 60 seconds without ever asking for the secret directly (which taught us a lot).Next challenge is focused on data exfiltration with harder defences: https://playground.fabraix.com

Hacker News7mo agoToolAI

Sub-millisecond VM sandboxes using CoW memory forking

I wanted to see how fast an isolated code sandbox could start if I never had to boot a fresh VM.So instead of launching a new microVM per execution, I boot Firecracker once with Python and numpy already loaded, then snapshot the full VM state. Every execution after that creates a new KVM VM backed by a `MAP_PRIVATE` mapping of the snapshot memory, so Linux gives me copy-on-write pages automatically.That means each sandbox starts from an already-running Python process inside a real VM, runs the code, and exits.These are real KVM VMs, not containers: separate guest kernel, separate guest memory, separate page tables. When a VM writes to memory, it gets a private copy of that page.The hard part was not CoW itself. The hard part was resuming the snapshotted VM correctly.Rust, Apache 2.0.

Hacker News7mo agoToolAI

69FL score

AI assistants fail to execute tasks across tools

Current AI chatbots only provide answers but cannot perform actual actions, workflows, or integrations across user tools.

X7mo agoToolAI

65FL score

Privacy risks in saving sensitive AI prompts

Users cannot securely save AI prompts containing sensitive data in cloud-based libraries without risking exposure on servers.

X7mo agoToolAI

Build and deploy AI agents in 60 seconds

AgentPeddler lets you build and deploy AI agents in 60 seconds without coding. As AI agents become mainstream, most people cannot build them. A no-code agent builder with one-click deployment could capture this growing market.

X7mo agoToolAI

Observability platform for AI agents (Datadog for Agents)

Monitoring and observability specifically designed for AI agents. As companies deploy more autonomous agents, there is no good way to monitor their behavior, track failures, or debug issues. Like Datadog but purpose-built for agent workflows.

X7mo agoToolAI

60FL score

AI browsing agent for research

Side Space (sidespace.app) is an AI agent for smart browsing that helps with research. Instead of opening dozens of tabs and manually synthesizing information, the agent browses, summarizes, and organizes findings for you.

X7mo agoToolAI

Own your AI-generated results

knwn.app helps businesses own and control their AI-generated results. As AI generates more content and outputs, businesses need tools to track, attribute, and manage what AI produces on their behalf.

X7mo agoToolAI

Signet – Autonomous wildfire tracking from satellite and weather data

I built Signet in Go to see if an autonomous system could handle the wildfire monitoring loop that people currently run by hand - checking satellite feeds, pulling up weather, looking at terrain and fuels, deciding whether a detection is actually a fire worth tracking.All the data already exists: NASA FIRMS thermal detections, GOES-19 imagery, NWS forecasts, LANDFIRE fuel models, USGS elevation, Census population data, OpenStreetMap. The problem is it arrives from different sources on different cadences in different formats.Most of the system is deterministic plumbing - ingestion, spatial indexing, deduplication. I use Gemini to orchestrate 23 tools across weather, terrain, imagery, and incident tracking for the part where clean rules break down: deciding which weak detections are worth investigating, what context to pull next, and how to synthesize noisy evidence into a structured assessment.It also records time-bounded predictions and scores them against later data, so the system is making falsifiable claims instead of narrating after the fact. The current prediction metrics are visible on the site even though the sample is still small.It's already opening incidents from raw satellite detections and matching some to official NIFC reporting. But false positives, detection latency, and incident matching can still be rough.I'd especially welcome criticism on: where should this be more deterministic instead of LLM-driven? And is this kind of autonomous monitoring actually useful, or just noisier than doing it by hand?

Hacker News7mo agoToolAI

65FL score

Voygr (YC W26) – A better maps API for agents and AI apps

Hi HN, we’re Yarik and Vlad from VOYGR (https://voygr.tech/), working on better real-world place intelligence for app developers and agents. Here’s a demo: https://www.youtube.com/watch?v=cNIpcWIE0n4.Google Maps can tell you a restaurant is "4.2 stars, open till 10." Their API can't tell you the chef left last month, wait times doubled, and locals moved on. Maps APIs today just give you a fixed snapshot. We're building an infinite, queryable place profile that combines accurate place data with fresh web context like news, articles, and events.Vlad worked on the Google Maps APIs as well as in ridesharing and travel. Yarik led ML/Search infrastructure at Apple, Google, and Meta powering products used by hundreds of millions of users daily. We realized nobody was treating place data freshness as infrastructure, so we're building it.We started with one of the hardest parts - knowing whether a place is even real. Our Business Validation API (https://github.com/voygr-tech/dev-tools) tells you whether a business is actually operating, closed, rebranded, or invalid. We aggregate multiple data sources, detect conflicting signals, and return a structured verdict. Think of it as continuous integration, but for the physical world.The problem: ~40% of Google searches and up to 20% of LLM prompts involve local context. 25-30% of places churn every year. The world doesn't emit structured "I closed" events - you have to actively detect it. As agents start searching, booking, and shopping in the real world, this problem gets 10x bigger - and nobody's building the infrastructure for it. We recently benchmarked how well LLMs handle local place queries (https://news.ycombinator.com/item?id=47366423) - the results were bad: even the best gets 1 in 12 local queries wrongWe're processing tens of thousands of places per day for enterprise customers, including leading mapp

Hacker News7mo agoToolAI