2D And 3D Face Alignment
A Torch7 demo implementation of neural networks that predict 2D and 3D facial landmarks, with pretrained model files and access to associated landmark annotations.
Guide: Set up and launch the landmark demoExplore AI, agents, blockchain and crypto through official sources, concrete tasks and practical guides.
Find the components, requirements and official instructions for a concrete next step.
Plan a read-only tool that returns a documented RPC result to an agent.
View requirements and sources →Prepare a local model and an API clientChoose the installation, model and client route for LocalAI before adopting local inference.
View requirements and sources →Choose stable asset IDs before reading market dataPrepare a CoinGecko market-data lookup using the provider’s own identifiers.
View requirements and sources →Selected profiles with a clear purpose, supported use cases and source-based guides. Selection is not an execution test or a ranking of project quality.
An open-source, self-hosted AI engine and API layer for running models locally across language, vision, voice, image, and video tasks.
Builder toolsOpenAI Agents SDKAn open-source, MIT-licensed Python framework for building and coordinating multi-agent LLM workflows. It supports configurable agents, tool use, handoffs and tracing.
InfrastructureLight ProtocolAn open-source Rust protocol for ZK compression on Solana. Its stated purpose is to reduce the cost or footprint of Solana state using zero-knowledge compression.
Builder toolsVelora SDKAn open-source TypeScript SDK for calling the Velora API and accessing aggregated decentralized-exchange liquidity and rates.
Selected for a documented reader task. Source review does not claim an execution test.
A Torch7 demo implementation of neural networks that predict 2D and 3D facial landmarks, with pretrained model files and access to associated landmark annotations.
Guide: Set up and launch the landmark demoAdaptsegnet is a PyTorch research implementation of a method for adapting semantic segmentation from synthetic source-domain images to real target-domain images.
Guide: Evaluate a pretrained GTA5-to-Cityscapes modelAgents-SDK is a portable C++ framework for building on-device AI agent systems that reason, plan and take actions.
Guide: Build the SDK and configure provider keysAI Chatbot — Ashot72 is a TypeScript and Next.js multi-user chatbot that crawls websites and uses LangChain and Pinecone to support responses grounded in their content.
Guide: Set up the chatbot locallyAI LLM Playground is a Python repository of experimental chatbot web applications using OpenAI Assistant APIs, LangChain, embeddings, vector databases and agent patterns.
Guide: Set up the Python project environmentAI Youtube Video Chat is a JavaScript Next.js application for asking questions about a YouTube video and receiving answers grounded in its content.
Guide: Prepare a local development setupAlphagen is a Python research codebase for reinforcement-learning-based generation and evaluation of formulaic predictive stock factors.
Guide: Prepare stock data for AlphaGen’s built-in Qlib pipelineAnchor Comp is a Rust library that provides Anchor-compatible account types and cross-program invocation helpers for integrating non-Anchor Solana programs into Anchor-based Solana programs.
Guide: Add anchor-comp to a Rust Solana programAnime Inpainting is a Python desktop application for repairing and drawing on anime images, with an OpenCV-based interface and an Edge-Connect inpainting backend.
Guide: Install and prepare Anime InpaintingAquila DB is a self-hosted neural search database that indexes machine-learning-generated latent vectors alongside JSON metadata and performs k-nearest-neighbor retrieval.
Guide: Build and run Aquila DB with DockerBELT is a Python model implementation that processes text longer than BERT’s 512-token limit by splitting it into chunks, running them through a BERT-style model and pooling intermediate results.
Guide: Install BELT NLP with CPU-only PyTorchBert Faiss Qa System is a Python application for asking questions about a document collection.
Guide: Set up and open the local document Q&A interfaceBert Nli is an open-source Python project that provides fine-tuned BERT and ALBERT models and code for natural-language inference: classifying a sentence pair as contradiction, entailment or neutral.
Guide: Set up the project and download its datasets and modelBert Squeeze is a Python library of code for reducing the size or inference latency of Transformer-based models, with implementations for distillation, pruning and quantization and early exiting listed among its techniques.
Guide: Set up the Bert Squeeze repository
Bitcoin is a peer-to-peer payment network and protocol. Its developer documentation explains transactions, wallets, payment processing and node operation.
Guide: Choose the Bitcoin integration documentationBitcoin Broker is a self-hosted Go application that provides a Thrift service for BTC brokerage, combines order-book depth from multiple exchanges, matches offsetting orders, routes and splits large orders, and retries failed orders.
Guide: Set up the broker locallyBitcoin Elixir is an Elixir library for Bitcoin protocol and script operations, accompanied by a work-in-progress full-node implementation.
Guide: Configure node startup and a local peerBlaGPT is a Python Transformer implementation and experimental playground for benchmarking language-model architectures, layers and techniques on smaller datasets.
Guide: Start a FineWeb10B architecture benchmark