Stars
Switch games running natively on iPhone, iPad and Mac: an NSP folder becomes an unsigned IPA (NSO rewriter, Horizon HLE host, NVN→Metal)
A humanizer for work writing: takes the AI tone out without changing what your text says or commits to. Agent Skill + evidence: blind judges, hand-checked meaning changes, Pangram.
Pangram AI detector alternatives compared: Pangram's own modes, the no-detector approach, and a writing tool.
CVE-2026-109618/109619 — 5 RCE chains + detection rules (Suricata, Sigma, ModSecurity). PHP session.upload_progress pre-auth exploit research.
High fidelity scanner for php2shell (CVE-2026-109618 and CVE-2026-109619)
Conversational AI plush toy — a laptop "brain" (STT · vision · TTS · LangGraph · dual memory) streams over WebSocket to a Raspberry Pi Zero "body". Face/emotion aware, multi-personality, runs 100% …
your fitbit air, but it finally tells you why you feel like garbage. recovery, strain, sleep and a Pulse Age that judges you, all free and self-hosted.
Whoop-style readiness tracker for the Fitbit Air, built on the new Google Health API. iOS, on-device, no subscription.
A python library to build parameterized gridfinity compatible objects such a baseplates and boxes.
Debloat any Android or Google TV over Wi-Fi and get an Apple TV-style home.
DeepSeek-V4-Flash-0731 284B inference in ~25 GB of RAM / Qwen3.8-Next-Flash inference in ~15 GB of RAM on any M-series MacBook
Turn off Apple Intelligence and delete its models on your Mac. Optional tweaks for analytics, ads and pop-ups. A native app and CLI, and every change can be undone.
AI agent toolkit: unified LLM API, agent loop, TUI, coding agent CLI
Deterministic guardrails that don't break agents
A local inference engine for Apple silicon, built around the model.
Jev-compatible API server for open decision models. Ollama for decision models: pull and serve 29 model families (Laya, pplx-decider, Clef, Winnow, coba...) locally or self-hosted behind /v1/system…
How Python does AI. Agents, realtime voice, image generation, embeddings. Every model, every interface, typed end to end.
mutonby / openshorts
Forked from kamilstanuch/Autocrop-verticalOpen source AI clip generator: turns long videos into viral 9:16 shorts with AI moment detection, face tracking, subtitles and dubbing. Self-host free with Docker (MIT), or use the cloud with GPU s…
FreeToken brings datacenter-scale model serving to your desktop. Run massive models locally, fast and efficiently.
MCP Server for Huawei Health Kit — Connect your Huawei Watch health data to AI agents via Model Context Protocol
Qwen 3.8 27B at 48-65 tok/s on a Mac Studio M4 Max — measured oMLX native-MTP recipe, same-day A/B vs mlx-vlm+MTP sidecar, raw benchmark JSON included
1.0 Beta · oMLX 0.6.3rc2 Dual-ANE+CPU · Qwen3.8-27B abliterated oQ4e · Mac Studio M3 Ultra
Hundreds of models & providers. One command to find what runs on your hardware.
Terminal-based Signal messenger client with vim keybindings
Turn an Android tablet into a wired second monitor for Linux/Wayland over USB - zero-copy, hardware-encoded.
A hand-picked collection of the finest of resources for the most awesome of agents, Claude Code, the undisputed champion of coding companions, from the unstoppable team at Anthropic PBC (no affilia…