Real problems people complain about online, pulled every morning and scored out of 100. Build, validate, or skip. How scoring works
AI teams need better tools to collaboratively label, version, and manage visual datasets like GitHub does for code. Current solutions are fragmented and expensive.
YC Graveyard8y agoToolAI
Companies want to automate phone interactions with customers but need natural-sounding voice AI that can handle complex conversations. Traditional phone trees and chatbots create poor user experiences.
YC Graveyard11y agoToolAI
Many businesses need NLP capabilities for local languages in emerging markets, but existing tools are primarily built for English and major languages. This creates barriers for local business automation and customer service.
YC Graveyard10y agoToolAI
### Discord username (optional) _No response_ ### Describe the solution you'd like? Due to safety concerns, many users are getting paranoid about Warp's forced login and online AI assistance. Since terminals are used to access critical data on local machines and servers, adding the ability to use local language models like Llama 2 using Ollama instead of online AI engines would be a great plus to Warp terminal emulator. ### Is your feature request related to a problem? Please describe. Mostly safety concerns when using Warp for accessing password protected systems and documents. ### Additional context _No response_ ### How important is this feature to you? 4 ### Warp Internal (ignore) - linear-label:39cc6478-1249-4ee7-950b-c428edfeecd1 None
GitHub2y agoToolAI
Linux users lack a dedicated desktop application for ChatGPT, relying on web versions which are suboptimal.
X6mo agoToolAI
Professionals want one-on-one teaching to learn building AI tools, as self-learning resources are insufficient.
X6mo agoOtherAI
Hi everybody, I really want to ask sorry to everyone and say that maybe I failed with the community, but has an explanation. In the last year, I can't give any support here. I really know that there a lot of people using Docz as a dependency on a lot of projects and this was choking me a lot, every day that I spent without being able to work here was a painful moment for me. But unfortunately was hard times and I want to explain this to you. When I had the idea to work on Docz I was working for a company here in Brazil and in order to develop it, I need to wake up every day 3 hours earlier and go to bed 3 hours later. So I worked a lot with full energy to create this project and was awesome, really awesome. I could have a lot of opportunities because of it, could change my work, start to work to other companies and was pretty good times. But as the project grew, a lot of demand was appearing as well and that's the bad part of the journey. Without victimism, I need to be honest here: maintaining an open-source is something very hard, really hard. When the project starts to have a lot of people using it, it's more complicated yet. People want a lot of things from you and your project, big companies are using the project and need a lot of things as well from it in order to keep their projects healthy, but in most of the cases this is a talk in just one way. _There are more people interest in have things from you, than help!_ **And this crashed me 😕** So, after a time working a lot here and on my business, I was with my healthy compromised and **needed to choose between "keep my open source project" or "keep my mental and physical health"**. And for me the choice was very clear, I choose me. This gave a very bad way to the project that stays without people to maintain it. For a long @rakannimer helped me a lot with this (thanks a lot for this), but unfortunately, after few months he couldn't help anymore and the projects stay on stand-by since this. But
GitHub5y agoToolAI
Hi everyone, I am Kumar, co-founder of Dench (https://denchclaw.com). We were part of YC S24, an agentic workflow company that previously worked with sales floors automating niche enterprise tasks such as outbound calling, legal intake, etc.Building consumer / power-user software always gave me more joy than FDEing into an enterprise. It did not give me joy to manually add AI tools to a cloud harness for every small new thing, at least not as much as completely local software that is open source and has all the powers of OpenClaw (I can now talk to my CRM on Telegram!).A week ago, we launched Ironclaw, an Open Source OpenClaw CRM Framework (https://x.com/garrytan/status/2023518514120937672?s=20) but people confused us with NearAI’s Ironclaw, so we changed our name to DenchClaw (https://denchclaw.com).OpenClaw today feels like early React: the primitive is incredibly powerful, but the patterns are still forming, and everyone is piecing together their own way to actually use it. What made React explode was the emergence of frameworks like Gatsby and Next.js that turned raw capability into something opinionated, repeatable, and easy to adopt.That is how we think about DenchClaw. We are trying to make it one of the clearest, most practical, and most complete ways to use OpenClaw in the real world.Demo: https://www.youtube.com/watch?v=pfACTbc3Bh4#t=43 npx denchclaw I use DenchClaw daily for almost everything I do. It also works as a coding agent like Cursor - DenchClaw built DenchClaw. I am addicted now that I can ask it, “hey in the companies table only show me the ones who have more than 5 employees” and it updates it live than me having to manually add a filter.On Dench, everything sits in a file system, the table filters, views, column toggles, calendar/gantt views, etc, so OpenClaw can directly work with it using Dench’s CRM skill.The CRM is built on top of DuckDB, the smallest, most performant
Hacker News6mo agoToolAI
Title: Show HN: PageAgent, A GUI agent that lives inside your web appHi HN,I'm building PageAgent, an open-source (MIT) library that embeds an AI agent directly into your frontend.I built this because I believe there's a massive design space for deploying general agents natively inside the web apps we already use, rather than treating the web merely as a dumb target for isolated bots.Currently, most AI agents operate from external clients or server-side programs, effectively leaving web development out of the AI ecosystem. I'm experimenting with an "inside-out" paradigm instead. By dropping the library into a page, you get a client-side agent that interacts natively with the live DOM tree and inherits the user's active session out of the box, which works perfectly for SPAs.To handle cross-page tasks, I built an optional browser extension that acts as a "bridge". This allows the web-page agent to control the entire browser with explicit user authorization. Instead of a desktop app controlling your browser, your web app is empowered to act as a general agent that can navigate the broader web.I'd love to start a conversation about the viability of this architecture, and what you all think about the future of in-app general agents. Happy to answer any questions!
Hacker News6mo agoToolAI
Sup HN,So I got tired of bouncing between Flightradar, MarineTraffic, and Twitter every time something kicked off globally, so I wrote a dashboard to aggregate it all locally. It’s called Shadowbroker.I’ll admit I leaned way too hard into the "movie hacker" aesthetic for the UI, but the actual pipeline underneath is real. It pulls commercial/military ADS-B, the AIS WebSocket stream (about 25,000+ ships), N2YO satellite telemetry, and GDELT conflict data into a single MapLibre instance.Getting this to run without melting my browser was the hardest part. I'm running this on a laptop with an i5 and an RTX 3050, and initially, dumping 30k+ moving GeoJSON features onto the map just crashed everything. I ended up having to write pretty aggressive viewport culling, debounce the state updates, and compress the FastAPI payloads by like 90% just to make it usable.My favorite part is the signal layer—it actually calculates live GPS jamming zones by aggregating the real-time navigation degradation (NAC-P) of commercial flights overhead.It’s Next.js and Python. I threw a quick-start script in the releases if you just want to spin it up, but the repo is open if you want to dig into the backend.Let me know if my MapLibre implementation is terrible, I'm always looking for ways to optimize the rendering.
Hacker News6mo agoToolAI
Agent Kanban has 4 main features:GitOps & team friendly kanban board integration inside VS Code Structured plan / todo / implement via @kanban commands Leverages your existing agent harness rather than trying to bundle a built in one .md task format provides a permanent (editable) source of truth including considerations, decisions and actions, that is resistant to context rot
Hacker News6mo agoToolAI
Every MCP server injects its full tool schemas into context on every turn — 30 tools costs ~3,600 tokens/turn whether the model uses them or not. Over 25 turns with 120 tools, that's 362,000 tokens just for schemas.mcp2cli turns any MCP server or OpenAPI spec into a CLI at runtime. The LLM discovers tools on demand: mcp2cli --mcp https://mcp.example.com/sse --list # ~16 tokens/tool mcp2cli --mcp https://mcp.example.com/sse create-task --help # ~120 tokens, once mcp2cli --mcp https://mcp.example.com/sse create-task --title "Fix bug" No codegen, no rebuild when the server changes. Works with any LLM — it's just a CLI the model shells out to. Also handles OpenAPI specs (JSON/YAML, local or remote) with the same interface.Token savings are real, measured with cl100k_base: 96% for 30 tools over 15 turns, 99% for 120 tools over 25 turns.It also ships as an installable skill for AI coding agents (Claude Code, Cursor, Codex): `npx skills add knowsuchagency/mcp2cli --skill mcp2cli`Inspired by Kagan Yilmaz's CLI vs MCP analysis and CLIHub.https://github.com/knowsuchagency/mcp2cli
Hacker News6mo agoToolAI
Hello Hacker News! We're Filip, Stavros, and Vivek from Terminal Use (https://www.terminaluse.com/). We built Terminal Use to make it easier to deploy agents that work in a sandboxed environment and need filesystems to do work. This includes coding agents, research agents, document processing agents, and internal tools that read and write files.Here's a demo: https://www.youtube.com/watch?v=ttMl96l9xPA.Our biggest pain point with hosting agents was that you'd need to stitch together multiple pieces: packaging your agent, running it in a sandbox, streaming messages back to users, persisting state across turns, and managing getting files to and from the agent workspace.We wanted something like Cog from Replicate, but for agents: a simple way to package agent code from a repo and serve it behind a clean API/SDK. We wanted to provide a protocol to communicate with your agent, but not constraint the agent logic or harness itself.On Terminal Use, you package your agent from a repo with a config.yaml and Dockerfile, then deploy it with our CLI. You define the logic of three endpoints (on_create, on_event, and on_cancel) which track the lifecycle of a task (conversation). The config.yaml contains details about resources, build context, etc.Out of the box, we support Claude Agent SDK and Codex SDK agents. By support, we mean that we have an adapter that converts from the SDK message types to ours. If you'd like to use your own custom harness, you can convert and send messages with our types (Vercel AI SDK v6 compatible). For the frontend, we have a Vercel AI SDK provider that lets you use your agent with Vercel's AI SDK, and have a messages module so that you don't have to manage streaming and persistence yourself.The part we think is most different is storage.We treat filesystems as first-class primitives, separate from the lifecycle of a task. That means you can persist a workspace across turns, share it betw
Hacker News6mo agoToolAI
LLM models like Claude Sonnet experience sudden drops (e.g., 9%+) in performance, impacting developers who lack real-time tracking tools.
X6mo agoToolAI
Developers, researchers, and knowledge workers face limitations when using AI for sophisticated problem-solving that requires nuanced reasoning, multi-step analysis, or handling complex scenarios. Current AI models often provide oversimplified answers or break down when tasks require deeper cognitive processing. This forces users to either accept inadequate solutions or spend significant time manually breaking down complex problems into simpler components.
Product Hunt6mo agoToolAI
**Describe the enhancement** Current set of input types doesn't cover some use-cases for manual workflows We use a single gh-action as an entrypoint of deploying packages from our monorepo, and sometimes we need to manually deploy several packages simultaneously. Up until now we just went with a set of Booleans, so we could tick all the packages we needed to run our CI/CD against via UI. However, we speedily reached a [limit of 10 input values](https://github.com/actions/runner/issues/1928) Introducing an input type that would store a, say, json array could help: ```yaml on: workflow_dispatch: inputs: name: type: multi-choice description: select packages options: - go-service1 - go-service2 - py-service1 ``` ...and in fact would be more logical with less copy-paste overhead for our use-case
GitHub4y agoToolAI
Hi HN! We're Gobhanu and Saatvik (brothers), building Vela (https://tryvela.ai) - AI agents that handle multi-party, multi-channel scheduling.Scheduling is a constraint satisfaction problem disguised as email! It’s easy when it’s two people, one timezone, one channel. But it becomes a constraint satisfaction problem when inputs are unstructured natural language across multiple communication channels, constraints change mid-solve, and the objective function includes social dynamics that don't exist formally anywhere.What if scheduling just happened? For example: a recruiter sends one message, and every interview across five candidates, three hiring managers, and two time zones gets booked, confirmed, and updated automatically. No links, no back-and-forth, no one spending hours with 20 emails. Everyone just gets the right invite at the right time, on whatever channel they actually use. That's what we built Vela to do.You loop in Vela into your emails, SMS, WhatsApp, Slack, phone or integrate into an ATS etc and it takes over: reads context, checks calendars, proposes times, follows up when people ghost, and rebooks when things shift.One of our first customers is a staffing firm that searched for a scheduling solution for almost eight years. Their coordinators manage hundreds of candidate-client interviews where each side needs separate email threads, separate Zoom accounts to avoid double-booking links, and calendar invites connecting parties who never directly communicate. A client reschedules one interview and it cascades into four others. A candidate responds on SMS to a thread that started on email. Vela solved this in just 10 minutes of onboarding.The hardest part has been the data problem. Scheduling behavior varies enormously across populations. C-suite folks respond to email within hours and expect formal 3-option proposals. Truck drivers applying for logistics roles respond to SMS at odd hours from shared devices with "y tm wrks.
Hacker News6mo agoToolAI
I got tired of sharing AI demos with terminal screenshots or screen recordings.Claude Code already stores full session transcripts locally as JSONL files. Those logs contain everything: prompts, tool calls, thinking blocks, and timestamps.I built a small CLI tool that converts those logs into an interactive HTML replay.You can step through the session, jump through the timeline, expand tool calls, and inspect the full conversation.The output is a single self-contained HTML file — no dependencies. You can email it, host it anywhere, embed it in a blog post, and it works on mobile.Repo: https://github.com/es617/claude-replayExample replay: https://es617.github.io/assets/demos/peripheral-uart-demo.ht...
Hacker News6mo agoToolAI
Hi HN! We’re Sam and Michael from Palus Finance (https://palus.finance). We’re building a treasury management platform for startups and SMBs to earn higher yields with a high-yield bond portfolio.We were funded by YC for a consumer-focused product for higher-yield savings. But when we joined YC and got our funding, we realized we needed the product for our own startup’s cash reserves, and other startups in the batch started telling us they wanted this too.We realized that traditional startup treasury products do much the same thing: open a brokerage account, sweep your cash into a money market fund (MMF), and charge a management fee. No strategy involved. (There is actually one widely-advertised treasury product that differentiates on yield, but instead of an MMF it uses a mutual fund where your principal is at considerable risk – it had a 9% loss in 2022 that took years to recover.)I come from a finance background, so this norm felt weird to me. The typical startup cashflow pattern is a large infusion from a raise covering 18–24 months of burn, drawn down gradually. That's a lot of capital sitting idle for a long time, where even a modest yield improvement compounds into real money.MMFs are the lowest rung of what's available in fixed income. Yes, they’re very safe and liquid, but when you leave your whole treasury in one, you’re giving up yield to get same-day liquidity on cash you won’t touch for six months or more. Big companies have treasury teams that actively manage their holdings and invest in a range of safe assets to maximize yield. But those sophisticated bond portfolios were just never made accessible to startups. That’s what we’re building.Our bond portfolio holds short-duration floating-rate agency mortgage-backed securities (MBS), which are an ideal, safe, high-yielding asset for long-term startup cash reserves under most circumstances.[1]The bond portfolio is managed by Regan Capital, which runs MBSF, the largest floating-rate ag
Hacker News6mo agoToolAI