Show HN ranking for the past week
- Honker – Postgres NOTIFY/LISTEN Semantics for SQLite | 75
- VidStudio, a browser based video editor that doesn't upload your files | 107
- Tolaria – Open-source macOS app to manage Markdown knowledge bases | 129
- How LLMs Work – Interactive visual guide based on Karpathy's lecture | 53
- GoModel – an open-source AI gateway in Go | 75
- Run TRELLIS.2 Image-to-3D generation natively on Apple Silicon | 39
- Prompt-to-Excalidraw demo with Gemma 4 E2B in the browser (3.1GB) | 62
- Mediator.ai – Using Nash bargaining and LLMs to systematize fairness | 74
- MDV – a Markdown superset for docs, dashboards, and slides with data | 55
- Agent Vault – Open-source credential proxy and vault for agents | 52
- Faceoff – A terminal UI for following NHL games | 47
- Gova – The declarative GUI framework for Go | 26
- Alien – Self-hosting with remote management (written in Rust) | 48
- I've built a nice home server OS | 42
- Browser Harness – Gives LLM freedom to complete any browser task | 50
- Broccoli, one shot coding agent on the cloud | 49
- Ctx – a /resume that works across Claude Code and Codex | 28
- Daemons – we pivoted from building agents to cleaning up after them | 33
- Built a daily game where you sort historical events chronologically | 59
- Run coding agents in microVM sandboxes instead of your host machine | 1
- Atomic – Local-first, AI-augmented personal knowledge base | 41
- A lightweight way to make agents talk without paying for API usage | 12
- Holos – QEMU/KVM with a compose-style YAML, GPUs and health checks | 23
- leaf – a terminal Markdown previewer with a GUI-like experience | 19
- Ghost Pepper Meet local meeting transcription and diarization | 4
- Backlit Keyboard API for Python | 5
- WeTransfer Alternative for Developers | 8
- Runner – A Better Claude Cowork | 19
- Nyx – multi-turn, adaptive, offensive testing harness for AI agents | 8
- Newsmaps.io a map of how news topics are covered by different countries | 6
- Solyto – a free, open-source all-in-one personal management app | 18
- Git Push No-Mistakes | 6
- CyberWriter – a .md editor built on Apple's (barely-used) on-device AI | 6
- Pvm – A TUI to browse and run commands across multiple Python venvs | 2
- Cartoon Studio – an open-source desktop app for making 2D cartoon shows | 5
- Graph Compose – Temporal workflows with visual builder, SDK, and AI | 18
- Endo Familiar, an O-cap based JavaScript agent sandbox | 3
- Netlify for Agents | 4
- Sostactic – polynomial inequalities using sums-of-squares in Lean | 1
- Almanac MCP, turn Claude Code into a Deep Research agent | 1
- XTrace – Encrypted vector DB (search embeddings without exposing them) | 3
- HNswered – watches for replies to your Hacker News posts and comments | 20
- Algorithmic String Art, accessible to all | 4
- LocalLLM – Recipes for Running the Local LLM (Need Contributors) | 2
- Everest Drive – a multiplayer spaceship crew simulator in the browser | 4
- OCI MicroVMs for Proxmox VE | 2
- Clone, a small Rust VMM, forks VMs in under 20ms via CoW | 3
- Gemini Plugin for Claude Code | 7
- Open Passkey – open-source passkey auth with free "backendless" host | 3
- We built a way for Claude Code to join meetings like a real teammate | 2
- AWS's Kiro just got an Open source Codex | 0
- I can't write Python. It works anyway | 8
- Nimbus – Browser with Claude Code UX | 1
- I built a toy that plays grandma's stories when my daughter hugs it | 3
- ShellTalk brings deterministic text-to-bash | 0
- Rapid-MLX – Run local LLMs on Mac, 2-3x faster than alternatives | 1
- Real-Real-Time Chat | 10
- AthleteData – AI coach for endurance athletes that messages you first | 0
- I Built SwiftUI but for macOS MDM | 0
- Stash – CLI to search over your team's coding agent sessions | 1
- Should – Expressive Assertions for Go | 0
- MemFactory: Unified Inference and Training Framework for Agent Memory | 0
- MCPfinder – An MCP server that finds and installs other MCP servers | 1
- Physics-accurate 3D assets for robotics simulations from any input | 6
- AgentBox – SDK to Run Claude Code, Codex, or OpenCode in Any Sandbox | 0
- We built an OCR server that can process 270 dense images/s on a 5090 | 2
- No JavaScript Club | 3
- Spectrum – Deploy AI Agents to iMessage, WhatsApp, Telegram, and More | 0
- Hydra – Never stop coding when your AI CLI hits a rate limit | 2
- A collaborative SSH copilot for on-calls/DevOps/MLOps | 2
- CLI-use – turn any MCP server into a CLI in one command | 1
- A visual CI/CD system | 2
- Chestnut – The antidote to AI-induced skill atrophy | 4
- Palmier – bridge your AI agents and your phone | 8
- OpenClawdex – Open-Source Orchestrator UI for Claude Code and Codex | 7
- FMQL – graph query and bulk-edit CLI for Markdown and YAML frontmatter | 1
- CatchAll – slowest web search API that outperforms everything on recall | 1
- Brygga – A modern, fast, feature-rich IRC client for macOS | 0
- Aide – A customizable Android assistant (voice, choose your provider) | 9
- macOS VMs to let you agents run wild | 4
- Self-hosted Raspberry Pi wall display (no cloud, no subscription) | 9
- We built a <60ms, open-source alternative to E2B using RustVMM and KVM | 2
- Clawemon, A Pokemon-style MMO for your agents | 0
- gcx – The Official Grafana Cloud CLI | 0
- Themeable HN | 1
- Modular – drop AI features into your app with two function calls | 1
- Claude-codex-proxy – Use Claude Code with ChatGPT subscription | 0
- Medievalizer, an extension that rewrites pages into Old English scripts | 3
- Four years of my CS degree, typeset in LaTeX (850 pages) | 2
- Libredesk – self-hosted, single binary Intercom/Zendesk alternative | 4
- AgentGrade – agent-readiness guide for your site | 1
- A fake small claims court for petty complaints | 5
- DecisionBox – Autonomous AI agent runs data discovery on your warehouse | 0
- Llm.sql – Run a 640MB LLM on SQLite, with 210MB peak RSS and 7.4 tok/s | 2
- PrivateClaw – AI agents running in confidential VMs you can verify | 0
- I Recreated Encarta's MindMaze | 8
- Turning a Gaussian Splat into a videogame | 2
- #1 On This Day | 1
- Irregular German Verbs – a simple app, no ads or tracking | 3
- Trainly – Free 72-hour audit of your AI agent's production traces | 1