a library for background removal models

💖🧸 Self hosted, you-owned Grok Companion, a container of souls of waifu, cyber livings to bring them into our worlds, wishing to achieve Neuro-sama's altitude. Capable of realtime voice chat, Minec…

A lightweight, cloud-native GIS platform for visualizing, exploring, and analyzing geospatial data. It runs in the web browser, on the desktop, on mobile, and inside Jupyter notebooks.

Speech recognition

Ultra fast and easy duplicate file finder. Awesome TUI/GUI to manage results.

Verified Rust for low-level systems code

CLI to control iOS and Android devices for AI agents

Animate portrait photos with your voice - presently implements FLOAT

Ghidra is a software reverse engineering (SRE) framework

[NeurIPS 2025] MemEIC: A Step Toward Continual and Compositional Knowledge Editing

Voice based multi-agent architecture to schedule patient Appointment

The record/bell split for agent-to-agent comms: durable file mailboxes as the one record, pluggable push notifications (console, file, Discord) as the many bells.

nRF54 Arduino core for XIAO nRF54L15 and other nRF54 boards using a register-level runtime

A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls.

Intercept any app, then call it from Python like a library

🎁 Physical computing system.

Foundation model for tiny devices; 14mb, 26m params, 1-6k toks/sec on mobiles, wearables smart home and robots.

This is a real-time conversation project powered by a VoxCPM-based streaming TTS model.

Run GLM-5.2 (744B MoE) on a 25GB-RAM consumer machine — pure C, zero deps, experts streamed from disk. Tiny engine, immense model. 🐦

The `npx serve` of Apple Simulators.

MOSS-Transcribe-Diarize 0.9B is an open-source SOTA end-to-end audio understanding model for long-form multi-speaker transcription, diarization, timestamps, and acoustic event awareness.

Self-hosted transactional email platform — send through your own AWS SES account, keep the dashboard, API keys, delivery logs, and webhooks on your own infrastructure.

Leading free and open-source face recognition system

LightTact: A Visual-Tactile Fingertip Sensor for Deformation-Independent Contact Sensing (RSS'26)

Flash Vision-Language-Action Inference for Autonomous Driving

Implementation of "MoonSplat: Monocular Online Gaussian Splatting with Sim(3) Global Optimization" for SIGGRAPH 2026.

A from-scratch C++17/ggml port of Depth Anything 3 (ByteDance)

[ICLR 2026] StreamSplat: Towards Online Dynamic 3D Reconstruction from Uncalibrated Video Streams