Explore AI, agents, blockchain and crypto through official sources, concrete tasks and practical guides.
Browse by purpose and evidence; use an exact name, ticker or addressable project domain to narrow the search.
Atrophy is a command-line coding practice tool that presents exercises to solve without AI, grades or scores the results, and tracks skill ratings over time.
Guide: Install Atrophy and establish a baselineAts is an Apache-2.0 implementation of Adaptive Token Sampling, a differentiable, parameter-free module for vision transformers.
Guide: Evaluate the documented DeiT-S ImageNet configurationAttackGen is an open-source Python and Streamlit application that generates cybersecurity incident-response scenarios and tabletop exercise materials using large language models, MITRE ATT&CK and ATLAS data, threat selections, and organization details.
Guide: Install AttackGen from its repositoryAttention Sinks is an open-source Python library that adapts pretrained language models to use modified sliding-window attention, retaining initial attention-sink tokens and a recent-token window to support extended text generation with constant memory use and without retraining.
Guide: Set up Attention Sinks for a pretrained modelAttentiongan is a Python research implementation of attention-guided generative adversarial networks for unpaired and multi-domain image-to-image translation.
Guide: Generate translations with a pretrained modelAn open-source TypeScript project described as a unified trust framework for blockchain-based attestation infrastructure. Its documented implementation centers on on-chain claims, authorities, schemas, subjects and resolvers.
Guide: Set up the documented Stellar SDK and CLI packagesAttestation is a Java library and set of command-line utilities for implementing blockchain attestations, including identity links to internet identifiers, signed cheque messages that can enable Ether withdrawals, and attestations usable as non-fungible tokens.
Guide: Build the project and create the demo JARAttestix is an open-source Python toolkit for creating cryptographically verifiable AI agent identities and credentials, recording governance evidence and supporting delegated authority.
Guide: Create an agent identity and issue a credential in PythonAtto is an open-source command-line Nano wallet written in Go.
Guide: Build Atto from sourceAttrPrompt is an open-source Python framework and dataset repository for developing and evaluating large-language-model training-data generation pipelines, with code for generating data and training classifiers and published datasets for text-classification tasks.
Guide: Load an AttrPrompt dataset splitAttu is a graphical management application for Milvus vector databases, available as a web app, standalone server or desktop app.
Guide: Start Attu with Docker and connect to MilvusAuctionGym is an open-source simulation framework for reproducible offline evaluation of bandit and reinforcement-learning approaches to ad allocation and bidding in online advertising auctions.
Guide: Reproduce the truthful-bid second-price exampleAudar-ASR-V1 is a family of generative speech-recognition models that converts audio into text, with a focus on Arabic and its dialects.
Guide: Transcribe a short clip with Transformers and FlashAudio AI Field Guide is a bilingual English–Persian educational reference to speech and audio machine learning, from dataset preparation and preprocessing to Transformer architectures, ASR, audio classification, TTS, fine-tuning and voice-system pipelines.
Guide: Load and inspect an audio example from MINDS-14Audio Diffusion Pytorch is a Python library built on PyTorch that provides customizable diffusion-model components for waveform audio generation.
Guide: Set up the library for a text-conditioned audio workflowAudio Webui is a Python application that provides a web interface for interacting with different audio-related neural networks.
Guide: Install and start Audio Webui locallyAudio.cpp Webui is a C++ audio-model inference application built on ggml, distributed with a task-oriented WebUI and local launcher scripts.
Guide: Generate speech with the documented PocketTTS CLI exampleAudiobench is a Python research benchmark for evaluating audio large language models across more than 50 datasets covering speech, audio-scene and voice-understanding tasks.
Guide: Run the documented model-as-judge example