Latest

Six months ago I started coordinating multiple AI coding agents (Claude Code, Codex CLI, Gemini CLI) across parallel terminals for a production project. The agents were productive, but I had no idea what they were actually deciding or why.The problem wasn't capability — it was accountability. An agent would make a choice buried in a 50-file commit, and I'd only find out weeks later when something broke. No trace of which agent did what, when, or based on what context.So I built a governance l...

URL: https://github.com/Preet3627/Comet-AITEXT: Hey HN, I'm Preet, 16 years old, and I've been building Comet AI Browser for the past 2 months while preparing for JEE. I want to be upfront about what this is and what it isn't. What it is: A cross-platform AI browser (Windows/macOS/Linux/Android/iOS) with a security architecture I couldn't find anywhere else. Most AI browsers trust LLM guardrails to prevent prompt injection. Comet doesn't — it enforces isolation at the system level:The agent p...

Anthropic's weekslong battle with the Department of Defense has played out over social media posts, admonishing public statements, and direct quotes from unnamed Pentagon officials to the news media. But the future of the $380 billion AI startup comes down to just three words: "any lawful use." The new terms, which OpenAI and xAI have […]

Anthropic claims DeepSeek and two other Chinese AI companies misused its Claude AI model in an attempt to improve their own products. In an announcement on Monday, Anthropic says the "industrial-scale campaigns" involved the creation of around 24,000 fraudulent accounts and more than 16 million exchanges with Claude, as reported earlier by The Wall Street […]

As 2025 drew to a close, Instagram head Adam Mosseri ended the year by doom-posting about AI. "Authenticity is becoming infinitely reproducible," Mosseri lamented. "Everything that made creators matter - the ability to be real, to connect, to have a voice that couldn't be faked - is now accessible to anyone with the right tools." […]

In addition to summoning Bixby or Gemini, Galaxy S26 users will be able to call on Perplexity by saying "hey, Plex." The integration of Perplexity into Galaxy AI is just one element of the company's embrace of a "multi-agent ecosystem." Often, people will use different AI agents for different tasks, depending on where their strengths […]

I started digging into OpenClaw, then found this: https://clawhub.ai/steipete/trello. They are literally telling people that it's okay to expose credentials, just as long as it's in an env var.If we’re building with AI, safety has to be a product principle, not an afterthought. AI makes coding more accessible, but it also strips away the guardrails you usually get from experienced mentors and hard-earned production lessons.So we built Earl: an AI-safe CLI for LLM agents. Instead of giving age...

I have a bit of phone anxiety, and have a ton of dread around making phone calls to restaurants, banks, doctors, and so on and on.I thought: AI could do this with a web form turned into a prompt.Stack started out simple -> using 11labs for voice + claude + twillio, but it actually got rather complex (even though I tried vibe coding most).First off, finding the phone numbers quickly is hard. This is done by scraping the web with some basic duckduckgo search and structure with openai calls.Seco...

Claude Code asks for permission before running tools (Bash, Write, Edit, etc.). If you're not at your terminal, it just waits. This tool hooks into Claude Code's PermissionRequest hook and sends each prompt as a push notification to your phone via ntfy.sh. Tap Approve or Deny, and Claude continues.Setup: npm install -g claude-remote-approver claude-remote-approver setup Then scan the QR code with the ntfy app on your phone and start a new Claude Code session.How it works: The hook POSTs t...

Finnish is morphologically complex — vowel harmony, six grammatical cases, free word order. AI models get it wrong in the same predictable ways every time. I built this after noticing that AI-generated Finnish triggers immediate pattern recognition in native speakers: overly formal register, SVO word order (Finnish allows much more variation), missing discourse particles (-han/-hän, -pa/-pä), and excessive nominalization. Before: "Tämä on erittäin merkittävä kehitysaskel, joka tule...

I built an open-source bot that turns Trello cards into working code using Claude Code.Drop a task card in a list → Sergio picks it up, explores your codebase, and posts an implementation plan as a comment. Add feedback, move the card back, and iterate. When you're happy, move it to the Development list → Sergio creates a worktree, writes the code, runs tests, and opens a draft PR on GitHub.It's a tool that can be used by teams of devs and product managers to cover the knowledge gaps between ...

I built Paragent because I kept context-switching between features.The idea: describe what you want in plain English, and an agent branches off, writes the code, and opens a PR. You can run 10 at once — each on its own branch.How it works: - Connect your repo via GitHub App (minimal permissions: contents + PRs) - Describe a feature ("Add Stripe checkout to the pricing page") - Agent plans, writes, runs your verification, opens a PR - You review on GitHub like any other PRYou bring your own AP...

Hey HN, I'm shipping my first open-source project and I'm pretty nervous about it. Aethene is an AI memory API – it gives your AI apps persistent memory. Store conversations, extract facts automatically, search semantically, handle contradictions gracefully. It works well thank most of the memory projects available on the market currently.Why I built this: I was building AI agents and kept running into the same problem – they forget everything. Every conversation starts from zero. I wanted ...

Your AI agent is burning 6x more tokens than it needs to just to browse the web. We built OpenBrowser MCP to fix that. Most browser MCPs give the LLM dozens of tools: click, scroll, type, extract, navigate. Each call dumps the entire page accessibility tree into the context window. One Wikipedia page? 124K+ tokens. Every. Single. Call. OpenBrowser works differently. It exposes one tool. Your agent writes Python code, and OpenBrowser executes it in a persistent runtime with full browser access...

"I built https://tokencost.is to solve a recurring headache: manually scraping dozens of provider pages just to estimate API spend for my agentic workflows.My goal was a neutral, minimalist utility in the vein of Time.is. We now track 44 models—including OpenAI, Anthropic, Google, DeepSeek, Mistral, and Cohere—with hourly updates.Key Features:Real-Time Latency: We track TTFT benchmarks (e.g., Llama 3.1 at 28ms) alongside pricing.Price Deltas: We track 24h market shifts; look for the ↑↓ indica...

I've been using Claude Code a lot recently and wanted visibility into security-relevant executions — the kind of thing you may not necessarily catch while the agent is running.CanaryAI is a macOS menu bar app that monitors Claude Code session logs and alerts on suspicious behaviour: reverse shells, credential file access, LaunchAgent/cron persistence, download-and-execute patterns, shell profile modification. It parses the JSON logs Claude Code writes locally — no interception, no proxying. A...

Put together a tool for quickly browsing and filtering the Openalex library of research papers. Would love to get some feedback on the system and it's utility for others, I've found myself using it almost like a social media in the past few days. Cheers!

The suspect in the mass shooting at Tumbler Ridge, British Columbia, Jesse Van Rootselaar, was raising alarms among employees at OpenAI months before the shooting took place. This past June, Jesse had conversations with ChatGPT involving descriptions of gun violence that triggered the chatbot's automated review system. Several employees raised concerns that her posts could […]

The Trump administration just tossed out Biden-era restrictions on mercury and other toxic pollutants from power plants. It's repealing Mercury and Air Toxics Standards (MATS) just as electricity demand in the US ticks up with the buildout of new AI data centers. Those standards are particularly impactful when it comes to pollution from coal plants […]

Amazon Web Services suffered a 13-hour outage to one system in December as a result of its AI coding assistant Kiro's actions, according to the Financial Times. Numerous unnamed Amazon employees told the FT that AI agent Kiro was responsible for the December incident affecting an AWS service in parts of mainland China. People familiar […]

OpenAI's first hardware release will be a smart speaker with a camera that will probably cost between $200 and $300, according to The Information. The device will be able to recognize things like "items on a nearby table or conversations people are having in the vicinity," The Information says, and it will have a Face […]

Each episode of HBO's The Pitt features some degree of medical trauma that almost makes the hospital drama feel like a horror series. Some patients are dealing with gnarly lacerations while others are fighting off vicious blood infections that could rob them of their limbs, and the chaos of working in an emergency room often […]

A hacker tricked a popular AI coding tool into installing OpenClaw - the viral, open-source AI agent OpenClaw that "actually does things" - absolutely everywhere. Funny as a stunt, but a sign of what to come as more and more people let autonomous software use their computers on their behalf. The hacker took advantage of […]