Ideas Lab

AI memory with biological decay (52% recall)

Most RAG setups fail because they treat memory like a static filing cabinet. When every transient bug fix or abandoned rule is stored forever, the context window eventually chokes on noise, spiking token costs and degrading the agent's reasoning.This implementation experiments with a biological approach by using the Ebbinghaus forgetting curve to manage context as a living substrate. Memories are assigned a "strength" score where each recall reinforces the data and flattens its decay curve (spaced repetition), while unused data eventually hits a threshold and is pruned.To solve the "logical neighbor" problem where semantic search misses relevant but non-similar nodes, a graph layer is layered over the vector store. Benchmarked against the LoCoMo dataset, this reached 52% Recall@5, nearly double the accuracy of stateless vector stores, while cutting token waste by roughly 84%.Built as a local first MCP server using DuckDB, the hypothesis is that for agents handling long-running projects, "what to forget" is just as critical as "what to remember." I'd be interested to hear if others are exploring non-linear decay or similar biological constraints for context management.GitHub: https://github.com/sachitrafa/cognitive-ai-memory

Hacker News4mo agoToolAI

Utilyze – an open source GPU monitoring tool more accurate than nvtop

The standard GPU utilization metric reported by nvidia-smi, nvtop, Weights & Biases, Amazon CloudWatch, Google Cloud Monitoring, and Azure Monitor is highly misleading. It reports the fraction of time that any kernel is running on the GPU, which means a GPU can report 100% utilization even if only a small portion of its compute capacity is actually being used. In practice, we've seen workloads with ~1–10% real compute throughput while dashboards show 100%.This becomes a problem when teams rely on that metric for capacity planning or optimization decisions, it can make underutilized systems look saturated.We're releasing an open-source (Apache 2.0) tool, Utilyze, to measure GPU utilization differently. It samples hardware performance counters and reports compute and memory throughput relative to the hardware's theoretical limits. It also estimates an attainable utilization ceiling for a given workload.GitHub link: https://github.com/systalyze/utilyzeWe'd love to hear your thoughts!

Hacker News4mo agoToolAI

How I find a job where what is needed is solid code, not firefighting?

Today I saw that post about AI destroying the future of West software. I remembered I am having a similar struggle with my jobs.Right now my life is like this: some company lost their senior, they hire me to replace. They expect me to produce code with same speed and same quality in 2 months.Then they realize they are late actually (one company for example was 6 months late to deliver to clients) and want me to use AI to churn out code even faster.Meanwhile I find out they lost all people that knew how things actually worked, there is no documentation, or worse, the documentation is outright wrong ( one project I worked had thousands of Jira tickets generated from a requisites document. After some months of politicking I got permission to see the requisites document and learned it was from another project entirely, they wasted years coding with the wrong requisites outright! )Then as I get close to the end of probation period, the company tried some kind of hail Mary, one company thought maybe I would be more useful if they fired their DevOps and asked me to do the job of the senior engineer that had quit, the fired DevOps, and learn Go (I was hired as C dev, not even CPP) in 2 weeks. Then when the absurd hail mary fails I get fired.For a while I have been trying again and again with always same results, tried to see what I was doing wrong, and now I concluded I am looking for a job in the wrong places.Every time I got fired the same criticism happened: I spent too much time going into "rabbit holes" and figuring out details of legacy code or debugging or fixing things or refactoring, and not enough time just shipping code fast enough to appease clients. I keep trying to change this behavior and fail, maybe I should instead find a job where this behavior is something good instead of something bad, but I have no idea where to look.

Hacker News4mo agoToolAI

25FL score

iPhone photo organization & smart tagging

Built-in iOS Photos app has limited organization beyond albums. A tool offering AI-powered auto-tagging, smart collections by person/place/date, and batch editing would fill the gap for power users managing thousands of photos. [Google Search suggestion]

Google Trends4mo agoToolProductivityUS

42FL score

Unified multi-email account dashboard

Managing multiple Outlook accounts separately is fragmented. A unified inbox dashboard with smart filtering, unified search, and consolidated notifications across Gmail/Outlook accounts solves real friction. [Google Search suggestion]

Google Trends4mo agoToolProductivityUS

Multi-platform social media content scheduler

Creators manage Instagram, TikTok, LinkedIn posts separately with fragmented tools. A unified scheduler with bulk upload, best-time posting recommendations, and cross-platform analytics would streamline workflow. [Google Search suggestion]

Google Trends4mo agoToolMarketing & SalesUS

Life Automation Checklist & Workflow

Guide/template for automating personal life systems (finances, scheduling, tasks). People want to automate daily routines but lack a structured framework. [Google Search suggestion]

Google Trends4mo agoArticleProductivityUS

Word TOC Auto-Generator

Automate table of contents creation in Word documents. Users struggle with manual TOC updates; a tool could auto-generate and sync from heading structures. [Google Search suggestion]

Google Trends4mo agoToolProductivityUS

25FL score

Investment Automation Dashboard

Automate recurring investment setup and monitoring across brokerage accounts. Many users want rules-based investing but fear complexity with platform-specific workflows. [Google Search suggestion]

Google Trends4mo agoToolFinanceUS

Excel Task Automation Builder

No-code/low-code tool to automate repetitive Excel tasks (data entry, formatting, calculations). Users waste hours on manual Excel workflows. [Google Search suggestion]

Google Trends4mo agoToolProductivityUS

Personal finance management for Gen Z

Young people need better tools to understand and optimize their spending, savings, and financial decisions. Generic apps don't match their behavior or preferences.

YC Graveyard4y agoToolFintech

Kloak, A secret manager that keeps K8s workload away from secrets

Hacker News4mo agoToolOther

Scaling a targeted web crawler beyond 500M pages/day

I've been reading up on crawler architecture. The two most useful sources I've found are the blog post "Crawling a billion web pages in just over 24 hours, in 2025" and the Mercator paper ("Mercator: A Scalable, Extensible Web Crawler").Both of these, and most other material I've come across, focus on crawling the broad open web rather than a targeted set of domains. For product prices it's the latter. Mercator calls out DNS resolution as a major bottleneck, for example, but when you're only hitting a few hundred domains that isn't really a concern.The other gap is that both assume static HTML. For our use case we need a headless browser, and we also have to deal with Cloudflare and similar anti-bot systems.For product prices specifically, a lot of sites publish price feeds which simplifies things, but plenty don't, and getting good coverage still requires scraping. Our current system does about 500M pages/day and we're looking to improve its performance.Does anyone here have experience in this space, or know of articles/blog posts on scaling targeted (rather than broad) crawlers with headless browsers? Any pointers appreciated.

Hacker News4mo agoToolAI

35FL score

Marathon Training & Race Planning Hub

Runners struggle to find centralized, personalized marathon training plans, pace group matching, race logistics, and tracking tools. Current solutions are fragmented across apps, forums, and official sites. [Trending: "london marathon 2026" with 5000+ searches in GB]

Google Trends4mo agoToolSport & FitnessGB

Fitness Coaching & Gamification

Making fitness engaging through game mechanics and personalized coaching. People struggle with consistency in fitness routines and need motivation systems.

YC Graveyard15y agoToolHealth & Fitness

Community Chat & Discussions

Self-hosted or easy-to-manage group chat for communities. Need for organized, threaded conversations beyond IRC and Slack.

YC Graveyard15y agoToolCollaboration

42FL score

Browser Harness – Gives LLM freedom to complete any browser task

Hey HN,We got tired of browser frameworks restricting the LLM, so we removed the framework and gave the LLM maximum freedom to do whatever it's trained on. We gave the harness the ability to self correct and add new tools if the LLM wants (is pre-trained on) that.Our Browser Use library is tens of thousands of lines of deterministic heuristics wrapping Chrome (CDP websocket). Element extractors, click helpers, target managemenet (SUPER painful), watchdogs (crash handling, file downloads, alerts), cross origin iframes (if you want to click on an element you have to switch the target first, very anoying), etc.Watchdogs specifically are extremely painful but required. If Chrome triggers for example a native file popup the agent is just completely stuck. So the two solutions are to: 1. code those heuristics and edge cases away 1 by 1 and prevent them 2. give LLM a tool to handle the edge caseAs you can imagine - there are crazy amounts of heuristics like this so you eventually end up with A LOT of tools if you try to go for #2. So you have to make compromises and just code those heuristics away.BUT if the LLM just "knows" CDP well enough to switch the targets when it encounters a cross origin iframe, dismiss the alert when it appears, write its own click helpers, or upload function, you suddenly don't have to worry about any of those edge cases.Turns out LLMs know CDP pretty well these days. So we bitter pilled the harness. The concepts that should survive are: - something that holds and keeps CDP websocket alive (deamon) - extremely basic tools (helpers.py) - skill.md that explains how to use itThe new paradigm? SKILL.md + a few python helpers that need to have the ability to change on the fly.One cool example: We forgot to implement upload_file function. Then mid-task the agent wants to upload a file so it grepped helpers.py, saw nothing, wrote the function itself using raw DOM.setFileInputFiles (which we only noticed that later in a git diff). Thi

Hacker News4mo agoToolAI

Atomic – Local-first, AI-augmented personal knowledge base

Hey HN - I first posted about my knowledge base product, Atomic, here around a month ago; since then, a viral tweet by Karpathy has produced a torrent of AI powered knowledge base projects. meanwhile I've been shipping like crazy, here are some of the new features shipped in the last month:- Rebuilt the iOS app with an Android app on the way- expanded both the MCP and internal agent chat toolkit immensely- A custom, CodeMirror6-based markdown editor with obsidian-style rendering- A dashboard view that provides a daily summary of atoms created or updated in the last dayAnd many bug fixes and improvements across the board. Atomic is MIT licensed. You can download the desktop app, but the true power is unlocked by self hosting an atomic server, which any client (web, mobile, or desktop) can connect to from anywhere. You can add content to your knowledge base directly, or via RSS feed, web clipper, mobile share capture, obsidian sync, or REST api.

Hacker News4mo agoToolAI

Tolaria – Open-source macOS app to manage Markdown knowledge bases

Hey there! I am Luca, I write https://refactoring.fm/ and I built Tolaria for myself to manage my own knowledge base (10K notes, 300+ articles written in over 6 years of newslettering) and work well with AI.Tolaria is offline-first, file-based, has first-class support for git, and has strong opinions about how you should organize notes (types, relationships, etc).Let me know your thoughts!

Hacker News4mo agoToolAI