New This Month

VibeVoice: Microsoft's Open Speech Models for Long Audio (GitHub, Scanned)

Microsoft's open speech models: hour-long transcription with speaker labels and a realtime voice.

nanochat: Train Your Own ChatGPT for About $100 (GitHub, Scanned)

Andrej Karpathy's minimal full-stack recipe to train a small ChatGPT-style model and chat with it.

exo: Run Big AI Models Across Several Macs (GitHub, Scanned)

Joins several Macs or PCs into one cluster to run models too big for any single machine.

Spec Kit: Make AI Coding Agents Work From a Spec (GitHub, Scanned)

GitHub's toolkit that has your coding agent write a spec, a plan and tasks before it writes code.

Anthropic Agent Skills: Ready-Made Skills for Claude (GitHub, Scanned)

Anthropic's public library of Agent Skills, including the document skills Claude itself uses.

ACE-Step 1.5: Make Full Songs With Vocals Locally (GitHub, Scanned)

An open music model that writes full songs with lyrics and vocals on your own GPU, in seconds.

Open Notebook: A Self-Hosted NotebookLM (GitHub, Scanned)

A self-hosted NotebookLM: chat with your PDFs, videos and web pages, and turn them into podcasts.

Handy: Free Offline Dictation for Any App (GitHub, Scanned)

Hold a shortcut, speak, and your words are typed into any app, transcribed offline on your machine.

Meetily: Private AI Meeting Notes With No Bot (GitHub, Scanned)

Records, transcribes and summarizes meetings on your own computer, with no bot joining the call.

Cherry Studio: One Desktop App for Every AI Model (GitHub, Scanned)

A desktop AI client for cloud and local models, with assistants, knowledge bases and MCP tools.

Krita AI Diffusion: Generative Fill Inside Krita (GitHub, Scanned)

A Krita plugin for AI inpainting, outpainting, live painting and upscaling on your own GPU.

Fabric: A Library of AI Prompts for the Terminal (GitHub, Scanned)

A CLI and about 260 ready-made AI prompts for summarizing, extracting and rewriting any text.

Wan2GP: AI Video Generation on a 6 GB GPU (GitHub, Scanned)

A web app that runs open video, image and audio models on consumer GPUs, some in 6 GB of VRAM.

Google AI Edge Gallery: Run AI Offline on Your Phone (GitHub, Scanned)

Google's app for running Gemma and other open models fully offline on Android and iPhone.

Dyad: Build Apps With AI on Your Own Machine (GitHub, Scanned)

A desktop AI app builder like Lovable or Bolt that runs locally with your own keys or local models.

Cap: An Open-Source Loom Alternative (GitHub, Scanned)

Record your screen, edit it locally and share a link, with the option to host it all yourself.

PDFMathTranslate: Translate PDFs, Keep the Layout (GitHub, Scanned)

Translate scientific PDFs into a bilingual copy that keeps formulas, charts and layout intact.

Nanobrowser: An AI Agent That Uses Your Browser (GitHub, Scanned)

A Chrome extension where AI agents browse, click and fill in pages for you, using your own API key.

PowerToys: Microsoft's Free Power-User Tools for Windows (GitHub, Scanned)

Over 30 free Windows utilities from Microsoft, from window layouts to an AI-assisted clipboard.

Karakeep: Self-Hosted Bookmarks With AI Tagging (GitHub, Scanned)

Save links, notes, images and PDFs to your own server, with AI tags, summaries and full-text search.

Paperless-ngx: Scan, OCR and Search Your Paperwork (GitHub, Scanned)

A self-hosted document archive that OCRs, tags and indexes every scan so you can find any paper again.

AFFiNE: Docs and Whiteboards in One Workspace (GitHub, Scanned)

A local-first Notion and Miro alternative where docs, whiteboards and databases share one canvas.

Frigate: Local AI Object Detection for Security Cameras (GitHub, Scanned)

A self-hosted camera recorder that spots people, cars and animals locally, built for Home Assistant.

Buzz: Transcribe Audio Offline With Whisper (GitHub, Scanned)

A desktop app that transcribes and translates audio and video offline with Whisper, no account needed.