Anycrawl
A public TypeScript/Node.js web-crawling project that extracts website content and structured search-engine results into LLM-ready data.
Guide: Set up an authenticated self-hosted Anycrawl APIExplore 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.
A public TypeScript/Node.js web-crawling project that extracts website content and structured search-engine results into LLM-ready data.
Guide: Set up an authenticated self-hosted Anycrawl APIAnyJev is a Python library for turning language-model outputs into typed decisions with associated option probabilities, using training-free inference or documented self-distilled models.
Guide: Make a decision with a Tacit model in PythonAnyLabeling is an open-source Python application for annotating images with geometric shapes and using supported YOLO and Segment Anything models for AI-assisted labeling.
Guide: Install AnyLabeling from PyPIAnyLoom is a self-hosted AI assistant stack that connects a Qwen3 model served by llama.cpp, BGE-M3 embeddings, Qdrant hybrid retrieval, AnythingLLM chat and document management, and a Python DyTopo multi-agent orchestrator.
Guide: Set up the local assistant stackAnymd is a Rust-based local command-line tool and MCP server that converts documents, web pages, images, audio and video into Markdown or associated text and metadata for AI-agent workflows.
Guide: Set up Anymd as an MCP server with npxAnythingLLM is an open-source, local-first AI application and agent-orchestration framework for document chat and configurable AI-agent workflows.
Guide: Prepare AnythingLLM for local developmentAnythingLLM Embedded Chat Widget is a JavaScript submodule that exposes an AnythingLLM workspace and its embedded knowledge base through a chat widget embedded in a website or HTML page.
Guide: Set up and build the custom embed scriptAnythingmcp is an open-source MCP gateway that converts REST/OpenAPI, SOAP, GraphQL, OData and SQL systems into tools for AI clients including Claude, ChatGPT and Copilot.
Guide: Start a local Anythingmcp instanceAnyTool is an open-source Python library that adds a tool-use layer to AI agents. It documents MCP server discovery and orchestration, with shell and GUI backends that can run locally or through a server.
Guide: Set up AnyTool and register an MCP serverAnyV2V is an open-source research framework for tuning-free video-to-video editing that uses a single edited image to guide changes across a video.
Guide: Set up the i2vgen-xl environmentApache HAWQ is an open-source, Hadoop-native MPP database and SQL analytics engine for interactive queries over large datasets stored in HDFS.
Guide: Explore HAWQ tables and external HDFS data
Apache MXNet is an open-source deep-learning library with APIs for developing and training neural-network models, including the Python-first Gluon API and bindings for other languages.
Guide: Explore the Apache MXNet Python API and Gluon documentation
Apache PredictionIO is an open-source machine-learning server and stack for developers and data scientists to build predictive engines, deploy them as web services, and evaluate competing engine variants.
Guide: Install Apache PredictionIO as a bundled machine-learning stack
Apache SystemDS is an open-source machine-learning system for data preparation, model training and other data-science workflows.
Guide: Set up and run SystemDS from sourceApache UIMA is a framework for assembling unstructured-content analysis applications from modular components, with framework-managed data flow and support for Java and C++ components.
Guide: Find Apache UIMA installation and example-running instructionsApdrawinggan is a self-hosted Python and PyTorch implementation of a hierarchical GAN that generates artistic portrait drawings from face photographs.
Guide: Generate drawings with the pretrained modelApe is an open-source Python-based Web3 development framework for compiling, testing and interacting with smart contracts from a command-line session.
Guide: Install Ape and confirm the command-line setupApe Etherscan is a Python plugin for the Ape Framework that connects smart-contract development workflows to Etherscan-compatible blockchain explorers.
Guide: Install Ape Etherscan and configure an explorer key