Show HN ranking for the past week
- boringBar – a taskbar-style dock replacement for macOS | 305
- Smol machines – subsecond coldstart, portable virtual machines | 93
- Oberon System 3 runs natively on Raspberry Pi 3 (with ready SD card) | 111
- I built a social media management tool in 3 weeks with Claude and Codex | 131
- Every CEO and CFO change at US public companies, live from SEC | 64
- PanicLock – Close your MacBook lid disable TouchID –> password unlock | 69
- Ithihāsas – a character explorer for Hindu epics, built in a few hours | 45
- MacMind – A transformer neural network in HyperCard on a 1989 Macintosh | 42
- LangAlpha – what if Claude Code was built for Wall Street? | 54
- Libretto – Making AI browser automations deterministic | 54
- Claudraband – Claude Code for the Power User | 44
- SPICE simulation → oscilloscope → verification with Claude Code | 30
- Stage – Putting humans back in control of code review | 96
- CodeBurn – Analyze Claude Code token usage by task | 24
- I made a calculator that works over disjoint sets of intervals | 8
- Plain – The full-stack Python framework designed for humans and agents | 51
- Marky – A lightweight Markdown viewer for agentic coding | 35
- Hormuz Havoc, a satirical game that got overrun by AI bots in 24 hours | 17
- Home Memory – A local DB of my house, down to cables and pipes | 12
- A memory database that forgets, consolidates, and detects contradiction | 33
- Kelet – Root Cause Analysis agent for your LLM apps | 24
- Waffle – Native macOS terminal that auto-tiles sessions into a grid | 23
- I rebuilt a 2000s browser strategy game on Cloudflare's edge | 33
- Hiraeth – AWS Emulator | 8
- Gave Claude a casino bankroll – it gambles till it's too broke to think | 9
- Fakecloud – Free, open-source AWS emulator | 9
- SmallDocs - Markdown without the frustrations | 20
- Continual Learning with .md | 34
- Ilha – a UI library that fits in an AI context window | 9
- Avec – iOS email app that lets you handle your Gmail inbox in seconds | 4
- Make sure your OpenClaw isn't doing things it's not supposed to | 3
- Omi – watches your screen, hears conversations, tells you what to do | 13
- Agent-cache – Multi-tier LLM/tool/session caching for Valkey and Redis | 6
- Revdiff – TUI diff reviewer with inline annotations for AI agents | 4
- A CLI that writes its own integration code | 10
- IceGate – Observability data lake engine | 5
- A stateful UI runtime for reactive web apps in Go | 4
- Equirect – a Rust VR video player | 1
- Object Storage Comparisons | 0
- Mcptube – Karpathy's LLM Wiki idea applied to YouTube videos | 2
- Editing 2000 photos made me build a macOS bulk photo editor | 25
- SmokedMeat, like Metasploit, but for CI/CD (open-source) | 9
- Host, share, promote and track release artifacts via your coding agent | 0
- Pushduck – S3 uploads that run on Cloudflare Workers, no AWS SDK | 7
- We built an AI Agent to reproduce bugs | 2
- Jeeves – TUI for browsing and resuming AI agent sessions | 3
- Git why – log your agent reasoning trace along your code | 1
- Compile English specs into 22 MB neural functions that run locally | 0
- Irl.rent – What renters pay, not what's listed in SF | 2
- A Better Internet | 3
- A social feed with no strangers | 5
- React Email 6.0 – An open-source email editor you can embed in your app | 0
- Xit – a Git-compatible VCS written in Zig | 1
- I built a Wikipedia based AI deduction game | 7
- ParseBench – Document parsing benchmark for AI agents | 5
- AI support chatbot with RAG and citations – one back end file, no infra | 0
- Rekal – Long-term memory for LLMs in a single SQLite file | 10
- Voiden – API Workflows as Markdown Files (Obsidian × Curl) | 5
- Deflect One – command line dashboard for managing Linux servers via SSH | 7
- I benchmarked Gemma 4 E2B – the 2B model beat the 12B on multi-turn | 1
- Lazyagent – a local TUI for watching what your coding agents are doing | 0
- OQP – A verification protocol for AI agents | 3
- Lazyagent – TUI for to watch all your AI coding agents | 0
- German Abitur: More good grades, fewer bad grades | 3
- Slack killed their OpenAPI spec, so we reverse engineered it | 1
- We built an MCP for Windows – ask Claude about CPU, temps, and privacy | 5
- Skillgrab – scan any project, auto-install matching AI skills | 1
- XitDB – an immutable single-file database | 0
- Dbg – One CLI debugger for every language (AI-agent ready) | 0
- We scanned uscis.gov for third-party trackers. The results are jarring | 0
- US keyboards don't have enough keys, so I switched to Japanese | 0
- Tsplat – Render Gaussian Splats directly in your terminal | 1
- I'm organizing a vibe coding game dev competition | 0
- CJIT, a single-binary C compiler that can self host | 1
- pg_grpc – Call gRPC services directly from PostgreSQL | 1
- Agent Armor, a Rust runtime for enforcing policies on AI agent actions | 5
- T4 – a versioned datastore with branching and time-travel (S3-backed) | 2
- Bloomberg Terminal for LLM ops – free and open source | 1
- One-command deploys from your terminal with CreateOS CLI | 1
- Keyboard First Email Client | 2
- Sudomake Friends, personalized AI personas in a Telegram group chat | 1
- OpenRig – agent harness that runs Claude Code and Codex as one system | 5
- StockFit API – structured SEC EDGAR data with a free tier | 1
- Noodlist – Letterboxd for Instant Ramen | 9
- Open-source Perplexity clone one file back end, streaming answers | 1
- Flint – A 30B model fine-tuned for less repetition | 2
- Agent Citizen – Your AI agents are sitting around doing nothing | 1
- Chrome extension that extracts styles and generates DESIGN.md files | 2
- Moxn – Git-like version control for collaborative docs | 7
- Turn your favorite YouTube channels into a streaming experience | 10
- Pyra – a Python toolchain experiment inspired by uv and Bun | 1
- Run AI coding agents in real, local sandboxes, not Git worktrees | 3
- Git-stage-batch – curate clean commit history before pushing | 1
- Terminal-Wrench, a dataset of 331 realistic hackable environments | 2
- Uninum – All elementary functions from a single operator, in Python | 2
- Dependicus, a dashboard for your monorepo's dependencies | 1
- Mercury – No-code orchestration for human and agent teams | 5
- BuilderPulse – Daily intelligence from 10 sources for indie hackers | 4
- Open KB: Open LLM Knowledge Base | 2
- MCP server gives your agent a budget (save tokens, get smarter results) | 5