7,242 results for Tool · 2.682s

News for “Tool”
18 results • 2678 ms server time
Moozonian News
github.com• Apr 1, 2026• 1 min read
Show HN: AirplaneMode – Simulate realistic airplane WiFi on macOSI needed to test how my app performed on airplane WiFi and found that existing tools (Network Link Conditioner, comcast, Chrome DevTools, etc) weren't sufficient.AirplaneMode is a macOS CLI and menu bar app that uses a local MASQUE relay to provide:1. Jitter. All of the mac os network simulators I tried apply a fixed constant delay with no jitter model. Real airplane satellite WiFi follows a log-normal distribution — most packets arrive near base RTT, but a few percent spike to 5-10x. AirplaneMode samples jitter from a log-normal distribution fit to real flight measurements.2. Userspace, with domain scoping and UDP support. No root required. A .mobileconfig profile routes only matched domains through the relay — the rest of your network is unaffected. The relay operates at the UDP packet level via MASQUE, so HTTP/3 and QUIC congestion control respond naturally to simulated conditions.3. Realistic Profiles. Airlines use performance-enhancing proxies that inflate speed test results. Pres
Moozonian News
news.ycombinator.com• Apr 1, 2026• 1 min read
Show HN: Agent Instructions and Bootstrap ComponentsHello,We started using AI tools intensively about 1.5 years ago. Initially, we used Gemini and Claude for creating specifications, generating concept mocks and UI mocks. That was an OK experience. Then we subscribed to Claude Code (Pro plan) and started building applications. Quite quickly, we realized that Claude (or Gemini or Codex) are quite adept at creating a lot of code quickly but they aren’t always consistent. They don’t seem to modularize well, nor do they always remember past decisions. Playing around with Claude and Gemini on a number of projects, we incrementally created instructions over time to address the shortcomings we observed. Every time, we ran into a situation where a coding agent didn’t output code, solve a problem or apply a common pattern in a way we expected, we added new instructions.These instructions are now in the repository:https://github.com/priyavijaikalyan2007/instructionsPlease fork, tune, modify, combine and use to your benefit. This repository is set
Moozonian News
unbubble.news• Apr 1, 2026• 1 min read
Show HN: Unbubble Shield – An Antivirus for MisinformationYou have an antivirus for your computer, a VPN for your internet connection, an ad blocker for your browser. What do you have to protect your critical thinking from misinformation?Fact-checking isn't enough (fake news travel 6x faster than truth) and the most effective misinformation is the one that doesn't even make you suspicious.That's why we built Unbubble Shield. It works like an antivirus: Shield runs in the background, monitoring hundreds of fact-checking organizations and verification databases, and alerts you when misinformation relevant to your feed is detected.The onboarding starts with a swipe-through test: we show you real fake news stories that went viral recently. You tell us which ones you've encountered. Then you go through a couple of additional questions to help us calibrate your Shield and only alert you when it's relevant, keeping the noise low.Check it out and let us know what you think!About us: We're a small team building tools to fight misinformation and social
Moozonian News
news.ycombinator.com• Apr 1, 2026• 1 min read
Show HN: Sally CLI Because "You're right" is probably wrongHi HN, I'm Thomas. I built Cynical Sally as a solo developer using AI assistants as my team. I've got no employees and no funding besides my own bank account that's getting emptier by the day, lol.https://github.com/w1ckedxt/cynicalsally-cliSally is an AI code reviewer with a consistent personality. She scores your code 0-10, finds real issues with evidence, and gives you actionable fixes. Her words, not mine:"Everyone has opinions. Mine just happen to be evidence-based."What makes her different from "paste into ChatGPT":- 6 specialised tools: code review, explain, refactor, PR review, brainstorm, frontend + marketing review - Works as CLI and MCP server (Claude Code, Cursor, Windsurf) - CI/CD ready with --fail-under flag for build gates - One consistent personality across all platformsTry it right now, no account needed!npm install -g @cynicalsally/cli90 free roasts/month. Every premium tool has one free trial so you can see if her feedback and Full Suite is worth paying for.She also
Moozonian News
bing.com• Apr 1, 2026• 1 min read
How Negasi Farms grew from loss into a mission of healingAdd Yahoo as a preferred source to see more of our stories on Google. In rural Delaware County, Indiana, Negasi Farms is using food as a tool for health, education and community connection, according ...
Advertisement
Moozonian News
ccunpacked.dev• Apr 1, 2026• 1 min read
Claude Code Unpacked : A visual guideRelated ongoing threads:The Claude Code Source Leak: fake tools, frustration regexes, undercover mode - https://news.ycombinator.com/item?id=47586778 - March 2026 (406 comments)Claude Code's source code has been leaked via a map file in their NPM registry - https://news.ycombinator.com/item?id=47584540 - March 2026 (956 comments)Also related: https://www.ccleaks.com
Moozonian News
news.ycombinator.com• Mar 31, 2026• 1 min read
Nexus – Agent-native ops platform for ecommerce MCP, self-registration, no demosHi HN,I'm Karim, based in Cairo. I run an ecommerce operations company and built Nexus to solve my own problem: 6 disconnected tools that never talked to each other.Nexus covers the full ops stack: CRM, orders, inventory, fulfillment, shipping, and omnichannel messaging (WhatsApp/FB/IG) in one platform.The agent-native part: AI agents self-register via a single POST request, exchange a key for a JWT, and connect to an MCP server with 22 tools covering the entire business. No human approval. No demo. No sales call.Free tier = read-only. Write access = paid plan. The agent proves value first.This isn't MENA-specific — fully remote and self-maintained. An operator in Jakarta runs the same workflows as one in Cairo.2 paying customers. Happy to answer questions on: architecture (Supabase + Deno Edge Functions), multi-tenant RLS, or the agent-native business model.MCP discovery: https://nexus.aiforstartups.io/.well-known/mcp.json Agent docs: https://nexus-docs.aiforstartups.io/api/ai-agents-
Moozonian News
github.com• Mar 31, 2026• 1 min read
Show HN: Dograh – voice agents that pick Recordings over TTS using LLMTL;DR: Dograh is an open-source platform to build voice AI agents with drag-and-drop workflows. New in v1.20: Gemini 3.1 live support, Pre-recorded audio support for lower latency and more natural responses. Fully self-hostable, no vendor lock-in.Hi HN,We’re the Dograh team (YC alumni). While building voice bots, we found that wiring WebRTC/ Telephony + STT + LLM + TTS took more time than the bots themselves. Teams are spending weeks on plumbing - handling call flows, extracting variables, dealing with telephony edge cases, and redeploying for small changes. Tools like Vapi/Retell are easy to start with but come with lock-in and platform fees. So we built Dograh: a 100% open-source platform that handles the full stack, with a visual workflow builder and self-hosting by default.Dograh v1.20 introduces two major additions: 1. Gemini 3.1 Live support Run fully real-time voice agents using Gemini’s streaming APIs, without stitching together separate STT + LLM + TTS components. 2. Pre-recor
Moozonian News
shardsofstone.com• Mar 31, 2026• 1 min read
Show HN: Shards of Stone – A Warcraft 2-inspired RTS that runs in the browserA browser-based RTS inspired by Warcraft 2, Age of Empires & Starcraft. 9 factions, 200+ units, fog of war, tech trees, naval combat, multiplayer, and AI opponents. Runs on desktop and mobile with no install.You can play it here: https://www.shardsofstone.comI built this over ~10 hours of spare time using Claude as my primary development tool. I'm not a game dev - I described what I wanted in big brain dumps and iterated across multiple threads. Each thread made heavy use of plan mode and specifically asking for sub agent teams to build systems in parallel. I only hit the Claude max plan limits twice.The whole engine is HTML5 Canvas + Next.js with an ECS architecture. Running on Vercel and using Cloudflare R2 for assets. Using Suno for music, Elevenlabs for dialog and Gemini 2.5 Flash Preview Image (Nano Banana) for image generation. Claude handled everything else. Also looking at Tauri to build desktop apps for Mac, Windows & Linux.Some things I think are interesting:1. LLM-powered AI
Advertisement
Moozonian News
cosmicjs.com• Mar 31, 2026• 1 min read
Show HN: Team agents that manage your CMS from Slack, WhatsApp, and TelegramHey HN,We're Cosmic (YC W19), a headless CMS. Today we're launching Team Agents and the Cosmic Agent.Team Agents are AI-powered team members that live in Slack, WhatsApp, and Telegram. They have names, roles, persistent memory, and real capabilities. Not chatbots. Not one-off prompts. Persistent agents that work alongside your team.Here's what they can do:CONTENT AGENTS write blog posts, landing pages, and marketing copy. They generate images, add SEO metadata, and publish directly to the CMS. Message them in Slack, get a finished post back.CODE AGENTS read your codebase, create branches, write components, and open PRs on GitHub. Need a new page? Message the agent. Review the PR. Merge and deploy.COMPUTER USE AGENTS browse the web like a human. They log into Vercel Analytics, Google Search Console, Ahrefs, or any web tool. They take screenshots, extract data, and build reports. No API integrations needed. If you can see it in a browser, they can.TEAM AGENTS tie it all together. They li
Moozonian News
github.com• Mar 31, 2026• 1 min read
Show HN: Postgres extension for BM25 relevance-ranked full-text searchLast summer we faced a conundrum at my company, Tiger Data, a Postgres cloud vendor whose main business is in timeseries data. We were trying to grow our business towards emerging AI-centric workloads and wanted to provide a state-of-the-art hybrid search stack in Postgres. We'd already built pgvectorscale in house with the goal of scaling semantic search beyond pgvector's main memory limitations. We just needed a scalable ranked keyword search solution too.The problem: core Postgres doesn't provide this; the leading Postgres BM25 extension, ParadeDB, is guarded behind AGPL; developing our own extension appeared daunting. We'd need a small team of sharp engineers and 6-12 months, I figured. And we'd probably still fall short of the performance of a mature system like Parade/Tantivy.Or would we? I'd be experimenting long enough with AI-boosted development at that point to realize that with the latest tools (Claude Code + Opus) and an experienced hand (I've been working in database syste
Moozonian News
news.ycombinator.com• Mar 30, 2026• 1 min read
I replaced Firecrawl with 2,700 lines of ElixirI was paying about $190/month for Firecrawl. It worked, but it was expensive and felt half baked. The CLI was awkward to use. Maybe I wasn't using it right, but the whole thing felt like it was in flux. I figured if they vibe coded it I might as well do it myself.So I vibed my own. 3k lines of Elixir, custom readability engine, no external services. It even manages, for some sites at least, to evade bot protection.It saves a lot of cash and helps pay the Claude Code Max subscription.I guess my realization is that you shouldn't just take tooling aimed at AI agents for granted. Code is a commodity now, so a price tag for an MCP tool nearly as much as the most expensive subscription tiers for Claude Code/Codex makes no sense to me.Just ask your agent to code 80% of the tool for yourself.
Moozonian News
news.ycombinator.com• Mar 30, 2026• 1 min read
Ask HN: Is it actually possible to run multiple coding sessions in parallel?I’ve been trying to make sense of how people really use tools like Claude Code, especially after seeing some of the workflows shared on Twitter.I started using terminal coding agents around June last year. I used Claude Code for a few months, then switched to Opencode because the experience was rough. My terminal would constantly flicker, formatting was messy, and a single session could drag my whole machine down. Then after a month or two I moved to Pi and have been using it ever since.What’s strange is that after going through all these coding agents, my workflow hasn’t really changed. It’s still very primitive. I ask a question or show agent some ideas, discuss the approach, let the agent write code, then I review and verify. I did try to adopt some of the “high-efficiency” workflows people talk about, but none of them work for me.Around the end of last year I saw Boris, the Claude Code Author, share how he uses Claude Code. I was shocked. He runs multiple sessions in parallel. I tr
Advertisement