Procedural game-sound CLI for AI agents: synths, drums, sfx, car engines, formant speech (robot/evil robot/monster…), effects, loops. Includes a Claude Code skill. - ogomez92/genny

New AI Models Just Dropped.

The first 508 audit that actually listens. Drives real screen readers across your mobile app, captures what they speak, and emits evidence transcripts plus a draft OpenACR. - IRS-Public/aloud

Fill out PDFs independently using only your keyboard and screen reader.

Free video magnifier apps for Android phones and tablets that don’t have advertisements, perfect for low vision users and visually impaired students

I recently built a Python library for the first time in a while, and to make it available in PyPI I followed the official Python packaging guide. But it turns out there’s some rough edges in the suggested tools.
Namely, the build backend hatch puts all the files in the project directory into the built sdist, except from some files it chooses to exclude, which led to a gitignored file as well as VCS metadata getting packaged and uploaded to PyPI. This really surprised me, and I think most Python users new to packaging would be better served by choosing a conservative build backend like uv_build, which puts only the Python source modules and some specific project-level files into the sdist.

Open, Jev-compatible System One decision server on DiffusionGemma - razorback16/openjev

An Archive of Our Own, a project of the Organization for Transformative Works

Thirty years of voluntary funding schemes haven't paid open source maintainers because asking doesn't scale. The real money already flows — to JFrog, Docker, Sonatype — at the registry layer. The fix: registries charge companies for supply (they already do), then route a slice automatically to the maintainers who make that supply worth having.

TG Drop Deck is free accessible broadcast software for radio, podcasting, DJing and live streaming, currently in open beta. Eighty sounds on the number row, a running order with crossfades, a processed microphone, audio streaming to Icecast or SHOUTcast and video streaming to YouTube, Facebook and Restream. Windows and Mac, keyboard first, screen reader first, forty sounds included.

How Bradford and Bryan Manning use ChatGPT to navigate vision loss, grow Two Blind Brothers, and support the blind community.

sanoTTS (सानो = 'small' in Nepali): a ~1.4M-param neural TTS that runs on a $3 chip or in the browser. Leads SCOREQ/UTMOS in the sub-15M class. - Ampixa/sanoTTS

Football Manager meets D&D: a guild-management sim that writes its own history.

Large language model (LLM) agents that interact with graphical user interfaces increasingly rely on either raw screenshots or platform-specific accessibility application programming interfaces (APIs) to perceive interface state. Both approaches have limitations for assistive applications: screenshot-based perception lacks the semantic roles and relationships required by screen readers, while platform-specific APIs such as Windows UI Automation, macOS Accessibility, Android AccessibilityService, and web ARIA require separate integrations for each platform. This paper proposes an architecture that uses the Model Context Protocol (MCP) as a unified transport and schema layer between heterogeneous accessibility frameworks and LLM-based assistive agents. An MCP accessibility server exposes ARIA-aligned roles, labels, states, and focusable-element hierarchies through a platform-independent representation, enabling consistent interaction across operating systems and applications. The framework also introduces an MCP resource model for persisting user accessibility preferences across sessions. The architecture is analyzed with respect to three research questions: protocol extensibility for accessibility-tree representation, latency and semantic fidelity trade-offs between accessibility trees and screenshot-based perception, and support for persistent accessibility profiles through MCP resources. Rather than presenting an empirical implementation, this work contributes a conceptual framework supported by comparative analysis of accessibility APIs, GUI agent architectures, and the MCP specification. The analysis suggests that a standardized MCP accessibility layer can reduce platform-specific integration complexity while preserving the semantic information required for accessible AI agents, providing a foundation for future implementation and evaluation.