Ideas Lab
Real problems people complain about online, pulled every morning and scored out of 100. Build, validate, or skip. How scoring works
- Ideas
- 4,820
- BUILD
- 702
- Sources
- 8
- Last sync
- 5h ago
A context-aware permission guard for Claude Code
We needed something like --dangerously-skip-permissions that doesn’t nuke your untracked files, exfiltrate your keys, or install malware.Claude Code's permission system is allow-or-deny per tool, but that doesn’t really scale. Deleting some files is fine sometimes. And git checkout is sometimes not fine. Even when you curate permissions, 200 IQ Opus can find a way around it. Maintaining a deny list is a fool's errand.nah is a PreToolUse hook that classifies every tool call by what it actually does, using a deterministic classifier that runs in milliseconds. It maps commands to action types like filesystem_read, package_run, db_write, git_history_rewrite, and applies policies: allow, context (depends on the target), ask, or block.Not everything can be classified, so you can optionally escalate ambiguous stuff to an LLM, but that’s not required. Anything unresolved you can approve, and configure the taxonomy so you don’t get asked again.It works out of the box with sane defaults, no config needed. But you can customize it fully if you want to.No dependencies, stdlib Python, MIT.pip install nah && nah installhttps://github.com/manuelschipper/nah
Hacker News7mo agoToolAI
RunAnywhere (YC W26) – Faster AI Inference on Apple Silicon
Hi HN, we're Sanchit and Shubham (YC W26). We built a fast inference engine for Apple Silicon. LLMs, speech-to-text, text-to-speech – MetalRT beats llama.cpp, Apple's MLX, Ollama, and sherpa-onnx on every modality we tested. Custom Metal shaders, no framework overhead.Also, we've open-sourced RCLI, the fastest end-to-end voice AI pipeline on Apple Silicon. Mic to spoken response, entirely on-device. No cloud, no API keys.To get started: brew tap RunanywhereAI/rcli https://github.com/RunanywhereAI/RCLI.git brew install rcli rcli setup # downloads ~1 GB of models rcli # interactive mode with push-to-talk Or: curl -fsSL https://raw.githubusercontent.com/RunanywhereAI/RCLI/main/install.sh | bash The numbers (M4 Max, 64 GB, reproducible via `rcli bench`):LLM decode – 1.67x faster than llama.cpp, 1.19x faster than Apple MLX (same model files): - Qwen3-0.6B: 658 tok/s (vs mlx-lm 552, llama.cpp 295) - Qwen3-4B: 186 tok/s (vs mlx-lm 170, llama.cpp 87) - LFM2.5-1.2B: 570 tok/s (vs mlx-lm 509, llama.cpp 372) - Time-to-first-token: 6.6 msSTT – 70 seconds of audio transcribed in *101 ms*. That's 714x real-time. 4.6x faster than mlx-whisper.TTS – 178 ms synthesis. 2.8x faster than mlx-audio and sherpa-onnx.We built this because demoing on-device AI is easy but shipping it is brutal. Voice is the hardest test: you're chaining STT, LLM, and TTS sequentially, and if any stage is slow, the user feels it. Most teams fall back to cloud APIs not because local models are bad, but because local inference infrastructure is.The thing that's hard to solve is latency compounding. In a voice pipeline, you're stacking three models in sequence. If each adds 200ms, you're at 600ms before the user hears a word, and that feels broken. You can't optimize one stage and call it done. Every stage needs to be fast, on one device, with no network round-trip to hide behind
Hacker News7mo agoToolAI
Satellite imagery object detection using text prompts
I built a browser-based tool for detecting objects in satellite imagery using vision-language models (VLMs). You draw a polygon on the map and enter a text prompt such as "swimming pools", "oil tanks", or "buses". The system scans the selected area tile-by-tile and returns detections projected back onto the map as GeoJSON.Pipeline: select area and zoom level, split the region into mercantile tiles, run each tile with the prompt through a VLM, convert predicted bounding boxes to geographic coordinates (WGS84), and render the results back on the map.It works reasonably well for distinct structures in a zero-shot setting. occluded objects are still better handled by specialized detectors like YOLO models.There is a public demo and no login required. I am mainly interested in feedback on detection quality, performance tradeoffs between VLMs and specialized detectors, and potential real-world use cases.
Hacker News7mo agoToolAI
Prism (YC X25) – Workspace and API to generate and edit videos
Hey HN — we’re Rajit, Land, and Alex. We’re building Prism (https://www.prismvideos.com), an AI video creation platform and API.Here’s a quick demo of how you can remix any video with Prism: https://youtu.be/0eez_2DnayIHere’s a quick demo of how you can automate UGC-style ads with Openclaw + Prism: https://www.youtube.com/watch?v=5dWaD23qnroAccompanying skill.md file: https://docs.google.com/document/d/1lIskVljW1OqbkXFyXeLHRsfM...Making an AI video today usually means stitching together a dozen tools (image generation, image-to-video, upscalers, lip-sync, voiceover, and an editor). Every step turns into export/import and file juggling, so assets end up scattered across tabs and local storage, and iterating on a multi-scene video is slow.Prism keeps the workflow in one place: you generate assets (images/video clips) and assemble them directly in a timeline editor without downloading files between tools. Practically, that means you can try different models (Kling, Veo, Sora, Hailuo, etc) and settings for a single clip, swap it on the timeline, and keep iterating without re-exporting and rebuilding the edit elsewhere.We also support templates and one-click asset recreation, so you can reuse workflows from us or the community instead of rebuilding each asset from scratch. Those templates are exposed through our API, letting your AI agents discover templates in our catalog, supply the required inputs, and generate videos in a repeatable way without manually stitching the workflow together.We built Prism because we were making AI videos ourselves and were unsatisfied with the available tools. We kept losing time to repetitive “glue work” such as constantly downloading files, keeping track of prompts/versions, and stitching clips in a separate video editing software. We’re trying to make the boring parts of multi-step AI video creation less manual so users can generate → review → edit → assembl
Hacker News7mo agoToolAI
FR: Support custom records in MagicDNS
Also, for DNS, the Customer would really like to make DNS aliases such as **example.ourdomain.beta.tailscale.net** always point to a machine name **staging-1** or something like that. This way, they can easily access the machines.
GitHub5y agoToolAI
The Mog Programming Language
Hi, Ted here, creator of Mog.- Mog is a statically typed, compiled, embedded language (think statically typed Lua) designed to be written by LLMs -- the full spec fits in 3,200 tokens. - An AI agent writes a Mog program, compiles it, and dynamically loads it as a plugin, script, or hook. - The host controls exactly which functions a Mog program can call (capability-based permissions), so permissions propagate from agent to agent-written code. - Compiled to native code for low-latency plugin execution -- no interpreter overhead, no JIT, no process startup cost. - The compiler is written in safe Rust so the entire toolchain can be audited for security. Even without a full security audit, Mog is already useful for agents extending themselves with their own code. - MIT licensed, contributions welcome.Motivations for Mog:1. Syntax Only an AI Could Love: Mog is written for AIs to write, so the spec fits easily in context (~3200 tokens), and it's intended to minimize foot-guns to lower the error rate when generating Mog code. This is why Mog has no operator precedence: non-associative operations have to use parentheses, e.g. (a + b) * c. It's also why there's no implicit type coercion, which I've found over the decades to be an annoying source of runtime bugs. There's also less support in Mog for generics, and there's absolutely no support for metaprogramming, macros, or syntactic abstraction.When asking people to write code in a language, these restrictions could be onerous. But LLMs don't care, and the less expressivity you trust them with, the better.2. Capabilities-Based Permissionsl: There's a paradox with existing security models for AI agents. If you give an agent like OpenClaw unfettered access to your data, that's insecure and you'll get pwned. But if you sandbox it, it can't do most of what you want. Worse, if you run scripts the agent wrote, those scripts don't inherit the permissions that constrain th
Hacker News7mo agoToolAI
Painful iteration on AI agents
Iterating and improving AI agents is a painful, manual process requiring multiple updates and testing, hindering development speed.
X7mo agoToolAI
How are people doing AI evals these days?
With the buzz that's happening with all the new AI models that get released (what feels like every other week), how are companies running internal AI evals to determine which model is best for their use case?
Hacker News7mo agoToolAI
Computer vision model improvement requires complex development workflows
Developers struggle with the complex process of training, testing, and improving visual AI models. Current tools are fragmented and technical.
YC Graveyard3y agoToolAI
Businesses need AI models to follow specific rules and constraints
Companies want to deploy AI but need models to adhere to specific business rules, compliance requirements, or output formats. Ensuring AI reliability and constraint adherence is a growing concern.
YC Graveyard1y agoToolAI
AI engineers need better development infrastructure and tooling
As AI development becomes mainstream, engineers struggle with managing model training, deployment, and monitoring with traditional DevOps tools. Specialized AI development infrastructure is needed.
YC Graveyard2y agoToolAI
Companies want AI benefits but can't use cloud AI due to data privacy concerns
Enterprises need AI capabilities but can't send sensitive data to external AI services due to compliance and privacy requirements.
YC Graveyard3y agoToolAI
Businesses need to convert unstructured data into searchable, usable formats
Companies have massive amounts of high-dimensional data like images, text, and audio that they can't easily search or analyze. Converting this to structured, queryable formats is technically challenging.
YC Graveyard7y agoToolAI
Businesses need easy-to-embed machine learning models without ML expertise
Companies want to add ML capabilities to their applications but lack the expertise to build, train, and deploy models themselves. This problem has grown as AI becomes more essential for competitive advantage.
YC Graveyard14y agoToolAI
Kula – Lightweight, self-contained Linux server monitoring tool
Zero dependencies. No external databases. Single binary. Just deploy and go. I needed something that would allow for real-time monitoring, and installation is as simple as dropping a single file and running it. That's exactly what Kula is. Kula is the Polish word for "ball," as in "crystal ball." The project is in constant development, but I'm already using it on multiple servers in production. It still has some rough edges and needs to mature, but I wanted to share it with the world now—perhaps someone else will find it useful and be willing to help me develop it by testing or providing feedback. Cheers! Github: https://github.com/c0m4r/kula
Hacker News7mo agoToolAI
Didit (YC W26) – Stripe for Identity Verification
Hi HN, I’m Alberto. I co-founded Didit (https://didit.me) with my identical twin brother Alejandro. We are building a unified identity layer—a single integration that handles KYC, AML, biometrics, authentication, and fraud prevention globally. Here’s a demo: https://www.youtube.com/watch?v=eTdcg7JCc4M&t=7s.Being identical twins, we’ve spent our whole lives dealing with identity confusion, so it is a bit of irony that we ended up building a company to solve it for the internet.Growing up in Barcelona, we spent years working on products where identity issues were a massive pain. We eventually realized that for most engineering teams, "global identity" is a fiction—in reality it is a fragmented mess. You end up stitching together one provider for US driver's licenses, another for NFC chip extraction in Europe, a third for AML screening, a fourth for government database validation in Brazil, a fifth for liveness detection on low-end Android devices, and yet another for biometric authentication and age estimation. Orchestrating these into a cohesive flow while adapting to localized regulations like GDPR or CCPA is a nightmare that makes no sense for most teams to be working on.When we looked at the existing "enterprise" solutions, we were baffled. Most require a three-week sales cycle just to see a single page of documentation. Pricing is hidden behind "Contact Us" buttons, and the products themselves are often bloated legacy systems with high latency and abysmal accuracy.We also noticed a recurring pattern: these tools are frequently optimized only for the latest iOS hardware, performing poorly on the mid-range or older Android devices that make up a huge percentage of the market. This results in a "leaky" funnel where legitimate users drop off due to technical friction and fraud goes undetected because data points are spread across disparate systems. Also, these systems are expensive, often requi
Hacker News7mo agoToolAI
DD Photos – open-source photo album site generator (Go and SvelteKit)
I was frustrated with photo sharing sites. Apple's iCloud shared albums take 20+ seconds to load, and everything else comes with ads, cumbersome UIs, or social media distractions. I just want to share photos with friends and family: fast, mobile-friendly, distraction-free.So I built DD Photos. You export photos from whatever you already use (Lightroom, Apple Photos, etc.) into folders, run `photogen` (a Go CLI) to resize them to WebP and generate JSON indexes, then deploy the SvelteKit static site anywhere that serves files. Apache, S3, whatever. No server-side code, no database.Built over several weeks with heavy use of Claude Code, which I found genuinely useful for this kind of full-stack project spanning Go, SvelteKit/TypeScript, Apache config, Docker, and Playwright tests. Happy to discuss that experience too.Live example: https://photos.donohoe.info Repo: https://github.com/dougdonohoe/ddphotos
Hacker News7mo agoToolAI
Can I repurpose a Bluetooth voice remote as input device for a PC?
I am exploring ways to work with my PC that doesnt involve always sitting at a desk and typing with hands like a cave man.Testing out using Wispr Flow and similar voice inputs -- seems to work fine for some use cases.I also place the laptop on a treadmill sometimes and try to to get some research / browsing / work done. Mouse (trackball) and typing are the current weakest link.are there decent handheld input gadgets that allow simple trackpad / click / scroll up&down / next&previous type of navigation and a push-to-talk voice input? I am looking at cheap remotes for FireTV stick and other streaming boxes that seem to have voice input -- anyway one could hack one of those to do our bidding and pair with a PC?
Hacker News7mo agoToolAI