PromptHMR adapts SAM’s promptable design to 3D human mesh recovery, integrating SLAM, pose detection, and SMPL models into a unified pipeline for monocular images and videos.
Explore the Python Data Science Handbook repo offering runnable Jupyter notebooks covering NumPy, Pandas, Matplotlib, and Scikit-Learn with no local setup required.
QuantaAlpha uses large language models with evolutionary strategies to automate quantitative alpha factor discovery, achieving strong backtest metrics on major indices.
RESTai exposes multi-project AI capabilities via a unified REST API, featuring an agentic browser with Dockerized Playwright, knowledge graph RAG, and a visual Blockly pipeline builder.
SceneMaker separates de-occlusion from 3D object generation to handle occluded open-set scenes. It uses FLUX Kontext and Step1X-3D, with code and checkpoints available.
SimRecon converts real-world videos into simulation-ready 3D scenes by combining geometry reconstruction, instance segmentation, viewpoint optimization, and semantic scene graph synthesis.
Home Information offers a spatial, local-first way to organize home manuals, warranties, and controls via a Django app integrating Home Assistant and ZoneMinder. Easy Docker quick start included.
web-design is a Claude Code SKILL that enforces a spec-first web design workflow via DESIGN.md, bridging AI code generation with consistent, testable design output.
Spoolman is a Python web service that tracks 3D printer filament inventory in real-time with multi-printer concurrency, supporting four databases and major 3D printing platforms.
Explore sanjay3290/ai-skills, a portable skill collection implementing the open Agent Skills Standard for cross-platform AI agent extensibility. Supports 40+ agents, 20+ skills, with OAuth security.
Stash captures coding agent session transcripts for teams and builds a shared knowledge base without server-side LLM calls, preserving privacy and cutting costs.
Tencent’s Hunyuan3D-Part offers a two-model pipeline for 3D mesh part segmentation with P3-SAM and high-fidelity part generation via X-Part, targeting semantic mesh decomposition.
TinyPilot transforms a Raspberry Pi into a browser-based KVM over IP device using uStreamer and Flask-SocketIO for low-latency remote keyboard, video, and mouse control.
Voice Clone Studio unifies multiple voice AI engines in a modular Gradio web UI. Supports voice cloning, multi-speaker dialogs, speech-to-speech, and LoRA fine-tuning with GPU or Apple Silicon.
Watchtower orchestrates 23 security tools via a LangGraph multi-agent system for automated pentesting. It uses a Planner-Worker-Analyst pattern, SQLite state, and supports multiple LLM providers.
WhyHow Knowledge Graph Studio builds RAG-native knowledge graphs using MongoDB and OpenAI embeddings, offering flexible triple-based graph construction for AI workflows.
Windrecorder captures screen activity on Windows, indexes it with multiple OCR engines locally, and offers a searchable rewind UI—all without cloud dependencies.
WorldGrow generates infinite 3D worlds via hierarchical block-wise synthesis with coarse-to-fine refinement, ensuring seamless, explorable environments for navigation and planning tasks.
Zero Password Manager is an open-source project combining Flutter/Dart frontend with a Python backend to offer a secure, cross-platform password management solution. The repo balances UI flexibility and backend performance with a clear setup path.
This Python MCP server wraps Meta’s Facebook Ads API into 20+ tools, letting AI agents query ad data conversationally. Setup is simple with a single server.py and token auth.
