Best new launches of the week, 2-8 November 2026 (so far)

openideaOpen source

The IDE you know, rebuilt in Rust. IntelliJ IDEA–style keymap, tool windows and search-everywhere in a…

dsh-superagent-prototypeOpen source

Towards a More Autonomous Agent System

craft-anythingOpen source

Craft Anything: understand how any software works, and craft your own.

cleanyourtv

Your TV, minus the ads. No root, nothing uninstalled, one line restores it.

pixelfxOpen source

244 pixel art effects, every one a small piece of code. Plus a Claude Code skill to make your own.

MikaOpen source

An on-device AI agent for Android that operates apps and the web to get things done for you.

stack-diagramOpen source

Agent skill: describe your stack in a sentence, get an architecture diagram with official logos

floorplanOpen source

See how your app actually fits together. An interactive, plain-English map of your codebase, drawn by…

unslopOpen source

A Claude skill that turns vibecoded, AI-looking UI into a designed interface

TokenEconomizerOpen source

TokenEconomizer is a plugin for Claude Code, Codex, the GitHub Copilot CLI and Pi, with experimental support for opencode and Cursor Agent.

HackerBooks

A bookshelf of the books Hacker News readers mention most, 2007–2026.

OmniDiff

Opensource, super fast, content aware Git difftool, in Rust

BBRouter

Ben Eater's 8-bit computer, simulated on 3D breadboards

DeepSeek V4.1 Flash 1017Open source

DeepSeek-V4.1-Flash-1017 is a minor update to DeepSeek-V4.1-Flash, delivering substantial improvements…

LFM3 1.7BOpen source

LFM3-1.7B is a text model for local agents and specialized applications, based on our new tri-hybrid…

NVIDIA Nemotron 3.5 Transcribe 30B A4BOpen source

NVIDIA Nemotron-3.5-Transcribe is an offline speech and audio model that processes recordings, together…

Mistral Large 4 1T A52BOpen source

Mistral Large 4 is our largest and most capable model to date: a 1 trillion-parameter natively multimodal…

Unlimited OCR 2Open source

Image text to text model by baidu

Qwen3.5 4B 3D CoderOpen source

An experiment exploring the feasibility of small language models for general-purpose coding and…

Nanbeige4.3 33BOpen source

Text generation model by Nanbeige

Pika H3 FlexOpen source

Pika H3 Flex is a post-trained H3 model, designed to give professional creators the flexibility and speed…

IdolOpen source

Image to 3d model by speridlabs

Flux 3 Image Klein ComfyOpen source

Image to image model by black-forest-labs

Muse from MetaFree

Muse is your personal AI agent that gets things done, always working on what matters to you.

2AM CAMPaid

2AM is a point-and-shoot instant camera for after dark.

Chromagraph CameraPaid

Replace your phone camera’s default processing with bespoke, curated color and texture rendering designed…

Tiny ComputersPaid

A museum of tiny computers. Please touch the exhibits.

TypeDrawPaid

Imagine carrying a real notebook that opens with whatever you want to see first: a new note, your most…

DeckPaid

Deck-Man (formerly referred to as "duo-man") is a playful music player that brings the look, feel, and…

Play Music Theory GamesPaid

Play Music turns your drawings into looping music on iPhone and iPad.

play_music_theoryPaid

Listen to your drawings! play_music_theory is a visual instrument designed to help us explore the relationship between sound and shape.

ROLLIE'SPaid

Choose a camera. Pick a lens. Load a roll.

Duo Fold CounterPaid

How often do you really fold your phone?

dsh-superagent-prototypeOpen source

Towards a More Autonomous Agent System

Muse from MetaFree

Muse is your personal AI agent that gets things done, always working on what matters to you.

DeepSeek V4.1 Flash 1017Open source

DeepSeek-V4.1-Flash-1017 is a minor update to DeepSeek-V4.1-Flash, delivering substantial improvements…

LFM3 1.7BOpen source

LFM3-1.7B is a text model for local agents and specialized applications, based on our new tri-hybrid…

NVIDIA Nemotron 3.5 Transcribe 30B A4BOpen source

NVIDIA Nemotron-3.5-Transcribe is an offline speech and audio model that processes recordings, together…

Mistral Large 4 1T A52BOpen source

Mistral Large 4 is our largest and most capable model to date: a 1 trillion-parameter natively multimodal…

MikaOpen source

An on-device AI agent for Android that operates apps and the web to get things done for you.

Unlimited OCR 2Open source

Image text to text model by baidu

Qwen3.5 4B 3D CoderOpen source

An experiment exploring the feasibility of small language models for general-purpose coding and…

Nanbeige4.3 33BOpen source

Text generation model by Nanbeige