HN RichAwo 6d ago

Yaps – AI Custom Keyboard on Android (Private and Offline)

Private offline AI keyboard for Android using on-device speech recognition without sending data to servers.

HN mefengl 6d ago

Zappa: An AI Powered Mitmproxy

Zappa: AI-powered mitmproxy for automated internet interaction. Tool for agent-based web automation and browsing.

HN RickJWagner 6d ago

Study: Become more optimistic by imagining a best possible self

Psychology study on increasing optimism through best possible self visualization technique.

HN matthieu_bl 6d ago

Snap lays off 16% of workers, citing 'rapid advancements' in AI

Snap lays off 1,000 employees citing AI advancements enabling team efficiency improvements.

HN yuribro 6d ago

AI Guided Hybrid Application Static Testing (Aghast)

Open-source SAST framework using AI guidance for automatable, scalable code security testing targeting specific concerns.

HN kamban 6d ago

How to Keep Your Data Safe When Using AI Tools

Analysis of LiteLLM supply chain attack and credential harvesting, recommending ephemeral secrets over stored credentials.

HN FailMore 6d ago

Show HN: SmallDocs – A Markdown-first CLI-native replacement for Word and GDocs

Open-source CLI and webapp for markdown preview, sharing, and styling with privacy

HN grums 6d ago

Nixquick – Search, install and uninstall nixpkgs across your Nix configurations

Tool for searching and managing nixpkgs across Nix configurations

HN ahmedktata 6d ago

A tool that turns development activity into automated daily and weekly reports

Tool converting development commits and PRs into automated daily/weekly team reports

HN seyz 6d ago

RootCX: A Supabase alternative for internal software

Supabase alternative providing database, SSO, permissions, and audit logs for AI app builders

HN aledevv 6d ago

The SM-2 Algorithm in Practice: Building a Spaced Repetition System in Laravel

SM-2 spaced repetition algorithm implemented in Laravel for an AI study platform

HN fredrikaverpil 6d ago

From Lazy.nvim to Vim.pack

Migration from lazy.nvim to Neovim's built-in vim.pack plugin manager

HN ddkingsley 6d ago

Show HN: Markplane – Project management in your repo, built for AI collaboration

Markplane: project management in repo as markdown files, designed for AI coding assistants

HN nour833 6d ago

Show HN: StegoForge – Open-source suite for steganography and ML forensics

StegoForge: Python framework for steganography, digital forensics, and covert communications with zero-dependency binaries.

HN 2Pacalypse- 6d ago

A 400 Word Prompt That Makes LLM Paragraphs More Bearable

Prompt engineering technique using rhetoric and narratology principles to improve LLM-generated paragraph quality.

HN jacob_rezi 6d ago

Show HN: Resume MCP

Resume MCP: Model Context Protocol server enabling AI tools to connect with Rezi resume platform for read/write access.

BL 6d ago

The next evolution of the Agents SDK

OpenAI's updated Agents SDK adds file inspection, command execution, code editing, and long-horizon task capabilities in sandboxed environments for developers building agents.

HN tamogotchi 6d ago

Claude Code: Widespread abnormal usage limit drain across all paid tiers

Bug report from Claude Code paying customer about abnormal usage limit drain across all paid tiers.

HN tamnd 6d ago

GitHub's Fake Star Economy

Investigation into GitHub star fraud ecosystem: $0.06 per fake star, VC-funded repos exploiting metrics for fundraising.

HN elye 6d ago

A VS Code Copilot Tool That Saves $$: Unlock Unlimited Free Follow-Up Prompts

Article about VS Code Copilot limitations and strategies for optimizing free follow-up prompts within token constraints.

HN jinqueeny 6d ago

Open Multi-Agent Interactive Classroom

OpenMAIC: open-source multi-agent platform converting topics into interactive classroom experiences with AI teachers

HN plcedoz 6d ago

HoloTab: A Chrome extension powered by Holo3, a SOTA computer-use model

HoloTab: Chrome extension using Holo3 computer-use model for browser automation with real-time reasoning display and voice commands.

HN teodorivanov624 6d ago

DotLLM – Building an LLM Inference Engine in C#

DotLLM: ground-up high-performance LLM inference engine written in C# for local .NET inference

HN edf13 6d ago

Prompt Injection Is Unfixable (So We Stopped Trying)

Security analysis: prompt injection is unfixable structural property of LLMs. OS-level security proxy for AI coding agents in development.

HN NomiJ 6d ago

Show HN: Helix – open-source self-healing back end for production crashes

Helix: multi-agent pipeline auto-fixes production crashes via Sentry integration with QA and dev agents

HN harijoe 6d ago

Lessons learned from building our CLI for agents

Technical writeup on building CLI for AI agents using MCP protocol. Design lessons on agent-human interfaces and tradeoffs.

HN abcde666777 6d ago

We never knew this until LLMs came along

Stub article title without content

HN beardyw 6d ago

Agents hooked into GitHub can steal creds – but users haven't been warned

Security researchers demonstrate prompt injection attacks stealing credentials from GitHub-integrated AI agents

HN 0dd 6d ago

Comment and Control: Prompt Injection in Claude Code, Gemini CLI, and Copilot

Security research: prompt injection vulnerability in Claude Code, Gemini CLI, Copilot GitHub Actions agents allows stealing API keys via GitHub comments.

HN nixys_nxs 6d ago

Nxs-universal-chart – open-source tool to install applications into Kubernetes

Nxs-universal-chart is a Kubernetes Helm chart tool for deploying applications. DevOps/MLOps consulting company background.

HN dahlia 6d ago

Optique 1.0.0: environment variables, interactive prompts, and 1.0 API cleanup

Optique 1.0.0 TypeScript CLI parser with type-safe combinators, environment variables, and interactive prompts.

HN nikhilol 6d ago

Ask HN: Robotics engineers – how painful was setting up GPU sim infra?

Query from robotics engineers about GPU simulation infrastructure setup, proposing CI/CD service for physics simulators.

HN the_data_nerd 6d ago

I track GitHub engineering acceleration to help investors spot breakout startups

Analysis of GitHub commit velocity metrics across 38 startups in 18 sectors, used to predict funding announcements.

HN WolfOliver 6d ago

What if you didn't need to write back end code for your app?

LinkedRecords tutorial: Backend-less app framework with authentication, authorization, and data persistence via Docker.

HN angst 6d ago

Qwen OAuth Free tier will be discontinued on 2026-04-15

Announcement: Qwen OAuth free tier discontinuation on 2026-04-15 with reduced daily quota.

HN Reebz 6d ago

Show HN: My favorite local-feeling remotely accessible Claude Code setup

Setup tutorial for running Claude Code sessions on Mac with remote access via iPhone/iPad using tmux and Tailscale.

HN energy123 7d ago

GPT-5.4 Pro solved Erdos problem #1196

Unsubstantiated claim about GPT-5.4 Pro solving mathematical problem. No details or evidence provided.

HN gmays 7d ago

CoreWeave, Anthropic Form AI Cloud Agreement

Business announcement: CoreWeave and Anthropic form cloud partnership. Corporate news, limited technical depth.

HN opiniateddev 7d ago

Late-Bound Sagas: Why Your Agent Is Not an LLM in a Loop

Technical deep-dive on agent architecture patterns, contrasting loop-based approaches with saga-based runtimes for production systems.

HN suprnurd 7d ago

Show HN: We built an MCP for Windows – ask Claude about CPU, temps, and privacy

MCP server providing AI agents and IDEs read-only access to Windows system resource usage, security data, and monitoring through natural language queries.

HN cspinetta 7d ago

Running AI agents in microVMs instead of containers

Technical discussion on running AI agents in microVMs versus containers. Infrastructure patterns for agent execution.

HN zc2610 7d ago

Show HN: LangAlpha – what if Claude Code was built for Wall Street?

LangAlpha: Claude Code variant for financial domain. LLM application for specialized use case.

HN cjarchivist 7d ago

Show HN: Fleet Watch – preflight guard for local AI inference on Apple Silicon

Fleet Watch: preflight guard tool for local AI inference on Apple Silicon. Developer tool for ML inference optimization.

HN hunvreus 7d ago

Show HN: Clonecn – Agent skill for generating Shadcn/UI themes

Agent skill for generating shadcn/ui themes from screenshots, URLs, or style prompts with live preview and customization.

HN mooreds 7d ago

Vibe coded menu bar app which watches for posts about vibe coding menu bar apps

Humorous MacOS menu bar app that monitors BlueSky posts about vibe-coded menu bar apps, itself built with Claude.

HN frankterpo 7d ago

KillBench: Every frontier LLM is biased about who deserves to live

Benchmark study measuring bias in frontier LLMs regarding ethical decision-making scenarios.

HN Brajeshwar 7d ago

AI agents replicate human social dynamics in days

Research on AI agents exhibiting social dynamics. Limited details in headline format.

HN joladev 7d ago

How to hit your Claude weekly limit so you can go outside and touch grass

Humorous essay about excessive Claude usage. Opinion piece with no technical content or practical information.

HN ahmedktata 7d ago

Gitmore: Automated daily/weekly reports from Git activity

Tool that converts Git commits and pull requests into automated daily or weekly team reports delivered to Slack or email.

HN smalltorch 7d ago

Show HN: I made a specialized tool for construction professionals

Mobile app for construction professionals to create punch lists, takeoffs, and reports from PDF plans with offline functionality.