Language
HomeLanguages
Sections
Voice Clone Studio combines Qwen3-TTS, Microsoft VibeVoice, Fish Speech, LuxTTS, Chatterbox, and MMAudio in one modular interface with voice cloning, dialogue generation, and custom model training.
How Memora gives Claude Code assistants long-term memory and a knowledge graph through MCP, turning scattered notes into a structured knowledge base.
A look at fast-plate-ocr, a lightweight library for license plate recognition that achieves up to 14,000 plates per second using compact CCT models and ONNX Runtime.
GigaAM is an open-source acoustic model family from SberDevices that outperforms Whisper on Russian speech recognition. Here's what it can do and how to use it.
Turn an old Android phone into a smart AI surveillance system with Sentinel. Captures video over LAN, records to PC, and uses multimodal neural networks for real-time event recognition.
Guide to integrating Tesla vehicles with Home Assistant using the community-built alandtse/tesla component, covering setup, vampire drain concerns, and Fleet API configuration.
httptap breaks down HTTP requests into phases and displays them as a waterfall chart in the terminal. Supports SLO checks and JSON export.
Open-source tool that overlays news events on candlestick charts and uses LLM + ML to explain market movements and predict price direction.
Tired of juggling scattered training scripts for multimodal models? lmms-engine is a modular engine that handles distributed training, sequence packing, and GPU optimizations so you can focus on config and data.
TetherIA's Aero Hand Open is a five-fingered tendon-driven robotic hand you can 3D print and assemble for about $314. Here's what's inside.
Researchers from TUM and Huawei released GenRecon, which combines generative 3D models with scene reconstruction to produce clean interior meshes from photos.
Turn any website into a ready-made API client without manually parsing DevTools. The reverse-api-engineer project automates the entire chain.
Transform arXiv papers into slides and diagrams with one command. paper-craft-skills generates academic diagrams, PPTX presentations, and detailed HTML breakdowns.
Open-source mcp-scanner audits MCP servers for hidden threats using YARA, LLM-as-judge, and Docker sandboxing.
WifiForge lets you practice Wi-Fi hacking in a virtual environment—no Alfa adapters or physical routers needed. Built on Mininet-WiFi with full Kali Linux tool support.
OpenOPC from HKU researchers reimagines multi-agent systems as an actual company with org structure, Kanban boards, and role-based memory—no more infinite loops of polite apologies.
UniFace consolidates face detection, alignment, embedding, segmentation, head pose, gaze tracking, and more under a single ONNX-powered Python interface.
MiroShark offers swarm-based agent simulations for under a dollar. Here's how it works and where it fits in your toolkit.
Learn how to find a router's physical location using its BSSID with geowifi—a tool that queries multiple Wi-Fi geolocation databases at once.
A $5,000 open-source humanoid robot built with 3D printing and Python. Includes CAD files, RL training pipeline, and sim-to-real transfer.
Anyone building AI agents in production knows the pain of duct-taping five different tools together. Future AGI aims to solve this with one open-source platform.
Open-source alternative to OpenAI Deep Research that runs locally with Docker, supports custom LLM providers, and costs nothing beyond your API usage.
A look at the neka-nat/freecad-mcp project that connects FreeCAD with Claude Desktop via MCP, allowing you to build 3D models from text descriptions or drawings.
PdfDing is a lightweight self-hosted PDF reader and catalog with cross-device sync, annotations, signatures, and Docker deployment.