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
- 3h ago
Jobs reduced to only prompting AI instead of real problem-solving
Most non-physical jobs are heading toward roles where the only task is prompting AI, which eliminates desired frequent problem-solving and feels like the worst outcome.
X10d agoOtherAI
Alter (YC S25) – Access control for multi-user agents
Hi HN! We’re Srikar and Kevan, founders of Alter – https://alterauth.com/. We’re building access control for agents that can take actions on behalf of multiple users.If you’ve built an internal agent people use through Slack, you may have experienced this scenario: everyone signs in with their own account, but the agent connects to the CRM or billing system with one shared API key, so the agent can do anything that the key can do. User-level authentication in Slack does nothing to control what the agent can do in an external system like the CRM or billing system.Here’s what Alter does:-It acts as a proxy and manages downstream credentials for every API request that an agent takes;-It takes identity into account for every action the agent does. Automatically take into account the end user identity of the person that the agent is taking actions on behalf of.-It enforces fine grained runtime policies and records compliance grade audit logs.Here’s a demo video: https://www.youtube.com/watch?v=9ZqPU14ipGEWe started this because we saw first hand how hard it is to build agents in regulated industries. To unlock the true benefits of agents we need to allow agents to take actions, sometimes actions on behalf of end users. I (Srikar) was working at Goldmans and I saw how prohibitively expensive it was for me as a developer to write my own custom auth to enable multi-tenancy in agents and to allow agents to have strict policy controls as they act on behalf of end users. My co-founder, Kevan, is a second time founder and was previously working on a database startup. He has experience building and selling deep tech into highly regulated environments. So this problem seemed like a natural fit for the both of us.Building and maintaining custom auth for multi tenant agents was challenging. But so was ensuring that the solution we developed was secure, scalable and keeping track of security grade audit logs. As a result we realized there needs to be a
Hacker News10d agoToolAI
Omnara – Open-source alternative to Claude Managed Agents
Hey all, Kartik from Omnara (https://omnara.com) here. We're building an open-source API for running durable agents. You create an agent with an API call, and Omnara runs the agent loop, gives the agent sandboxes to run commands in, and handles secrets, permissions, and RBAC. Each agent's state is stored in Postgres, so agents survive restarts and cost nothing while idle. You can message them and stream their events over the API.You may remember us from our early days, when we made a remote-control phone app for Claude Code and Codex. Since the harness ran on a laptop back then, we had to build a relay to reach it, it stopped when the laptop closed, and moving it to a cloud sandbox meant syncing code and agent state between machines. We didn't think remote-controlling a local agent was end-game for how people would run agents, so we built a new product where the agent runs in the cloud, any client can talk to it through an API, and it can still use your laptop as one of its machines.Anthropic and OpenAI are building hosted versions of this, like Claude Managed Agents and the OpenAI Agents API. Omnara is an open-source version you can run on your own servers and use your own models. It's basically a harness server like the opencode or codex servers, but durable, scalable, with the usual harness features like file and shell tools, subagents, compaction, permission prompts, MCP, skills, memory, yada yada yada.Here's some interesting architectural decisions we made while building this out:Most harnesses, like Claude Code, Codex, OpenCode, Pi, Goose, etc, run the agent loop in one long-lived process that keeps its log in a JSONL or SQLite file. In Omnara, the log is an append-only event log in Postgres, with inputs, model outputs and tool calls stored as typed rows in their own tables. The loop runs on stateless workers in the control plane. A worker runs one iteration of the loop, either a model call or the tool calls it produced, then
Hacker News9d agoToolAI
Death Plan Switch, a self-hosted dead man's switch for solo devs
Hi HN,I'm Peter Bishop and I've been working in graphics and web tech for over 25yrs.I've recently launched Death Plan Switch to solve a major problem in my succession plan. What if I go missing or die? The right people are told and my business can continue to operate for my clients.There's a backstory to this project, I was hospitalised in 2012 and lost my business back then and I couldn't get the data to my technical 2IC in time without frustrating my clients.Death Plan Switch solves this problem, it's free to download and use or study under the MIT license.I've been using it for the last few weeks. It was authored with the help of Claude Code after writing an extensive MD document and it passed 42 unit tests.I hope you get some use out of it, or it inspires your own succession plans. My clients are telling me this is a strong sales feature when they trust me with their hosting and technology accounts.Happy to answer any questions.Kind regards, Peter Bishop.
Hacker News11d agoToolAI
VoidAccess – open-source dark web OSINT, from query to a graph
Hi HN! Im Katriel, and im a Security Researcher/Enthusiast and in the wave of AI, i wanted to build that next gen of security tooling that surpasses the current tools, and even the paid industries with an open source engine. I built MailAccess as well, which is going to be the best damn email osint tool out there, in another year. But just before building MailAccess i built VoidAccess, because i was delving a lot into DarkINT and the content inside the dark web is too difficult to navigate through for a human, so i automated that pipeline, made sure the noise was removed, and anything NSFW was filtered out, to give the analyst an overview of what is present in the dark web, without having to actually go through it manually.Very simple to run, you just run a few commands to install, and a couple to investigate. Then the engine takes over, and stops onyl when the job is done(or at a particular time limit, if set by the user).Do check it out, if that is something that interests you.Thanks to the community for giving it the love it has got till now.
Hacker News10d agoToolAI
Respan (YC W24) – Open-source Rust AI gateway built around plugins
Hey HN, this is Andy from Respan (https://www.respan.ai). We are building an open-source Rust AI gateway. It is a decoupled gateway, so everything is a plugin, including different providers, protocols (MCP, voice), modalities (images, videos), and gateway features (fallbacks, PII redaction, smart routing).Instead of packaging tons of providers and features into one gateway, Respan provides a small core and public interfaces that teams can use to assemble the AI infrastructure their application needs. That way, users can build their own features as additional plugins without having to change the gateway's core.Here’s a video demo: https://www.youtube.com/watch?v=pVv2ibXiTXMThere are countless LLM gateways and most of them solve a common problem: calling different providers from a single endpoint. However, adding new features can become prohibitively difficult. So developers can end up building another gateway to solve a specific problem.We've been building our gateway based on LiteLLM since 2024, and now it's providing services for thousands of orgs. Each org needs different API key settings, routes, and limits. To support that, we kept wrapping LiteLLM, adding more features to it, and at one stage, our wrapper code exceeded 100,000 lines.This January, a routine LiteLLM upgrade caused intermittent connection errors, and we had to roll back. We still haven't figured out the cause, but since then, we no longer upgrade LiteLLM directly and instead manually backport upstream fixes. These experiences made us realize that continuing to patch LiteLLM is not a sustainable long-term solution, and we had to redesign the gateway ourselves.While redesigning our gateway, we wanted to make it easier to add features without breaking existing ones. Inspired by Nginx, we think an AI gateway should have a really small core, only responsible for dispatching events.We believe that everything should be a plugin in our gateway, including provid
Hacker News10d agoToolAI
How to deal with shipping AI-written code you don't understand?
I saw this LinkedIn post from a Meta engineer and it resonated with me:https://www.linkedin.com/posts/ali-hamie_im-an-engineer-at-m...> I'm an engineer at Meta and I never felt this uncomfortable doing my job. I'm writing code these days and it all feels like a black box. This new standard of shipping with AI is moving so fast that if we're going to spend our time checking each line of code, it's going to take forever. That means you can end up with systems you've built where you don't truly understand how all the code works. You understand the high level, but not every detail. And maybe this is becoming the new standard. It goes against every instinct of being a software engineer. I'm used to understanding what I'm building. Now I'm trying to figure out how much I need to understand before I'm comfortable moving forward. Are other engineers feeling this too?How are you handling this?
Hacker News11d agoToolAI
How do you deal with AI output of your boss?
So, my boss goes on a rampage. You can clearly see the joy and at the same time the rage and impatience. AI is the tool he always wanted. We are too slow. Process is out of the window. No need for sprints anymore. No planning, just doing. All people downstream must somehow adapt.Whenever i see now his automated messages in slack, my natural reaction is: why do i even bother reading that? Thats for machines to read. He does not need me? Clearly i am not made for that. What is he expecting me to do? To confirm how great the AI did the job? Should i remember all these perfect presentations AI has created and integrate it into my doings into the coming weeks?I am torn. Should i really free my AI and deal with all this incoming text? Is this the way to react on this perfection?I am not mad at him, it clearly frees him of all the burder of dealing with people.I just dont know how to deal with this output personally. It is not for humans.I feel left alone. This is not a company anymore. Everyone is talking to AI now. This feels like chaos. Where everyone can do everything and stepping into each other's domain and it is perfect. The only way AI is stopped at are the ACLs.And because AI does everything for me, i don't remember things anymore, as i have no emotion connected with it. Feels like bad schooling and memoizing and get through it and you can't as it so dry and lifeless.So, how people deal with it in a company context? How have they setup their machines to react and still be up to date without reading the constant stream of changes coming from others?
Hacker News13d agoArticleAI
Laminar (YC S24) – RL-trained model that finds errors in agent traces
Hi HN, we’re Robert and Din from Laminar (https://laminar.sh). We’ve been building open-source observability for AI agents since 2024. Recently, we released flow-1, a model trained with RL to find errors in agent traces. On our benchmark (https://laminar.sh/blog/flow-1), it matches GPT-6-sol in detection quality while being 23x cheaper. This makes it affordable to analyze every production agent trace, without sampling.Here’s a one-minute walkthrough: https://youtu.be/KJa3h6ZJNLQWe also put together a post with example traces and analyses from flow-1 and other models: https://laminar.sh/blog/flow-1-in-actionAgent observability is crowded, so instead of a bullet list of how Laminar differs from X, we’ll explain how we’re solving agent observability from first principles.Agents now run for many steps and fail implicitly. An agent can click the wrong button or cite the wrong document while every call completes successfully. These errors are the most useful ones to catch and understand. To find them, you need to understand what the agent was trying to do and inspect its LLM calls and tool results. Simply looking at the final agent output is not enough.Collecting traces alone doesn’t solve this. A lot of agent observability platforms are still data collectors at their core. You can end up paying to store traces that nobody has time to read or extract value from.Using another LLM to inspect traces is THE solution, but capable models are expensive at scale and cheaper ones often miss errors or flag unrelated things.So we built our model to solve exactly this problem. We finetuned a small OSS model and then post trained it with RL on thousands of synthetic investigations of realistic agent workflows in software, legal, customer support, etc. We got a model that is both good at agent trace analysis and very cheap to run.flow-1 runs inside a harness we call Signals. It acts as a coding agent, treating an agent tr
Hacker News11d agoToolAI
KiviDB, a faster Redis-compatible memory database and vector cache
Hi all,So I have been working on this project KiviDB from February 2026. It started as a project for me to understand rust, having a product with no GC pauses, memory blow up after snapshots and getting OOM on running pods, and that was actually an issue I faced with Dragonfly. I wanted to have something picking the best of Rust, but also picking the best parts of other alternatives like Garnet and Dragonfly. I used AI a lot, but I was the one making the design decisions based on the tests that claude picked from my history of troubleshooting sessions as part of my job. KiviDB supports both RESP2 and RESP3 protocol. I had some founders credits on my AWS account which helped me with the infra, and running instances I could perform benchmark on.Its keyspace is sharded across threads, it is multi-threaded in nature, and performs best on Linux due to io_uring, I used the tokio_uring crate for this. It also has tokio fallback for other OS's. I hadn't open sourced it until recently as I felt it was not ready yet, the best way to learn it was to build a cloud managed service for it across all three widely used cloud providers i.e AWS, GCP and azure. Since I used to mainly work with cloud, I had some insights on what would be the best ways for the deployments, how to conduct failovers, manage SLAs, etc. And that's what I took help from claude to fast pace it. The website does look like AI slop but it works for now, given my limited resources, that's all I had. You may check it out at : https://kividb.io, I open sourced the core engine under AGPLv3, didn't want to have just source available, because that is available with other tools too. It supports apprx 98-99% of the redis 8.10 commands, few have issues and you can find them at https://github.com/kividbio/kividb/issues, contributors are welcome.Now the numbers, for the final benchmark, I used 2 c7gn.metal servers, in the same placement group in us-east1, and I us
Hacker News11d agoToolAI
I built a task system to handle the drudgery so I could focus on tasks
I'm a software engineer from the east coast (who has lived in Boston, NY, the bay area, UK, France), and I built a task system called 3 & Done. It's the place you trust to store everything you need to do. It accepts voice input for rapid entry, as well as text (it stores the audio locally so you can listen to jog your memory) and emails you every morning with the three most important things for you to do that day, and why, based on what you've said about the task: deadlines, urgency, sitting too long.I've been at software engineering for about 44 years now... Grew up with it, which was unusual when I started, and I was always good about getting into the zone and doing things. The career started small, small company, then back office, the dot com startups, then smaller companies again after the bust, a non-profit, and eventually YouTube (Google at the time, but just barely) and Meta (just Facebook when I was there).When I hit the startups, and later big tech, it was no longer enough to just be an engineer, to have drive, to be good, you had to be organized, you had to follow through, get stuff done, and that's where the task systems started. Twenty-five over the years (and yes, I've actually counted), from Moleskine notebooks with Getting Things Done, evernote (remember evernote?), bug trackers, todoist, asana, google keep, among others.When I managed on the Facebook News Feed, I got into gantt charts (for me and my team), spreadsheets, OmniPlan... I remember apologizing to my director for being so disorganized (because I felt I was making a mess of it), and he told me that I was the most organized engineer he knew.That was because I was doing all of the work in the background, the trimming, the sorting, the reviews, but it was just so much work. Which was why I changed from system to system. Each time it built up, and I had to spend more time looking at things I couldn't or didn't get done, when I was rushed and could
Hacker News11d agoToolAI
Creating complex AI-generated virtual experiences without significant effort
Users want zero-effort, one-click setups for AI virtual libraries instead of step-by-step guides, as inbound requests persist despite free resources.
X12d agoToolAI
Wonderhop – A daily game: guess what most people say, or what none do
Hello HN!Wonderhop is a small browser game with no account needed to play, everyday there are 4 rounds of 7 quesitons like "Name a food that a lot of people hate" The goal depends on the mode: Either gives the answer most people would give, the one no one would give, the oldest answer or the most recent one and there's a leaderboard for the day.The most interesting part of the project was understanding answers that are typed freely and in 10 languages, there was some typos, plurals, nickname, or even duplicate way of sayign the same thing. We needed AI judge that checks it really existes conencted to some API like wikipedia to judge the veracity of each answer really quickly (less than 1s on average)The percentage starts from an estimate but move really fast with the answers of real players. If the list missed a good answer, it gets added as soon as a few different players give it.(There are also a lot of secrets and pop culture references added in the game :) )A large part of the code was written with AI tools, but the artistic direction the concept and every choice design are human-madeWe'd love to know if the goal is clear from the very first question while playing and were any good answers rejected unfairlyWe are a couple of developers from Montreal that like guessing games so we built this in about two month.Thanks a lot!
Hacker News17d agoToolAI
Are you hesitant to install vibe-coded apps?
The thing is in the past there can be supply chain attacks but when its an actual programmer creating the software there is at least a chance for them to notice if something is up.But if the app is not even created by a programmer whats stopping prompt injection from including some virus in the app?Aren't we completely blind to security issues at that point?
Hacker News16d agoOtherAI
WhatsApp MCP running free on Cloudflare
I wanted my humble Claude on mobile to access my WhatsApp messages but the only options I could find either required WhatsApp Business or an actual server to run Baileys on.I wanted to run it for free on ClaudeFlare and with my personal WhatsApp account, so I built this.Important feature - it connects to your Google account as well as WhatsApp to grab the names of all your WhatsApp contacts, otherwise you get only phone numbers for many of them and search doesn't work properly.This is a single user install because it's both gray area and very private - so point your agent at the repo and let it set things up.
Hacker News12d agoToolAI
[Feature]: Add TurboQuant Support for KV Cache Quantization
# [Feature]: Add TurboQuant Support for KV Cache Quantization ## 🚀 The feature, motivation and pitch **TurboQuant** is a novel online vector quantization method that achieves near-optimal distortion rates for both MSE and inner product preservation, specifically designed for KV cache compression in LLMs. As described in the paper [TurboQuant: Online Vector Quantization with Near-optimal Distortion Rate](https://arxiv.org/pdf/2504.19874), this method provides: - **Provably optimal distortion bounds** within a factor of ~2.7 of information-theoretic limits - **Unbiased inner product estimation** - critical for attention mechanisms - **Online application** - no data-dependent preprocessing required - **Accelerator-friendly design** - suitable for real-time AI workloads - **Significant memory savings** - 4-5× compression while maintaining model performance The paper demonstrates TurboQuant achieving perfect recall on Needle-in-a-Haystack tests at 4× compression and competitive performance on LongBench with just 2.5-3.5 bits per dimension. This would be a valuable addition to vLLM's quantization portfolio, complementing existing scalar methods (FP8, INT4, etc.) with a vector quantization approach specifically optimized for attention KV caches. ## Alternatives Current vLLM KV cache quantization options include: - **FP8 quantization** (`fp8_e4m3`, `fp8_e5m2`) - scalar quantization with element-wise MSE optimization - **Compressed-tensors KV cache** - supports various schemes but primarily scalar-based - **ModelOpt FP8** - NVIDIA's FP8 implementation TurboQuant differs by: 1. Using **vector quantization** with learned codebooks instead of scalar quantization 2. Optimizing for **inner product preservation** rather than just MSE 3. Providing **theoretical guarantees** on distortion bounds 4. Supporting **variable bit-widths** (2.5-bit, 3.5-bit) through outlier handling ## Additional context ### Technical Integration Approach Based on vLLM's existing quantization f
GitHub7mo agoToolAI
Fakeipedia – Wikipedia for worlds that don't exist
Hi HN!Fakeipedia is an automatic world-building platform which takes an imagined world and makes a whole wiki that you can endlessly explore by clicking red links.I came up with this idea a few months ago after playing around with worldbuilding in Gemini, but I didn't want to release it until a powerful enough model could do it justice, and I decided that Argon is creative enough to write articles that are worth reading. I was surprised how well it turned out and how engaging some of the writing actually is.If you want to generate an article there is a nominal charge attached ($0.90), which helps cover AI/Stripe costs, and I think I just about break even. You can also steer the generation ala choose-your-own-adventure books when generating a new article. Everything generated is free and public for everyone to see.I hope you like it and I'm very much open to hearing about new world ideas/features that would make this project better.
Hacker News14d agoToolAI