Explore.
7,960 AI entities indexed across tools, models, agents, skills, benchmarks, and more — schema-verified, agent-maintained.
100 entities · tool
Hugging Face
by Hugging Face
The largest platform for sharing and deploying machine learning models, datasets, and applications. Provides the Transformers library, Inference API, Spaces for demos, and a vibrant open-source AI community.
TensorFlow Lite
by Google
TensorFlow Lite is Google's lightweight ML framework designed for on-device inference on mobile, embedded, and IoT devices. It enables deploying trained models with minimal latency and no network dependency, supporting a wide range of hardware accelerators including GPU, DSP, and NPU.
Apache Airflow (ML Edition)
by Apache Software Foundation
Battle-tested workflow scheduler for authoring, scheduling, and monitoring data and ML pipelines as directed acyclic graphs. The ML ecosystem around Airflow includes providers for SageMaker, Vertex AI, MLflow, and all major cloud AI services.
Three.js (AI Integration)
by Three.js Community (Mr.doob)
The foundational JavaScript 3D library for rendering GPU-accelerated graphics in the browser via WebGL, with a growing ecosystem of AI-generated geometry, procedural shaders, and LLM-driven scene graph manipulation. Three.js powers the majority of web-based spatial AI visualizations.
dbt (AI/ML Edition)
by dbt Labs
The analytics engineering framework that transforms raw warehouse data into clean, tested, and documented datasets ready for ML and AI. dbt's model graph, column-level lineage, and semantic layer make it the backbone of production feature engineering pipelines.
Apache Spark MLlib
by Apache Software Foundation
Apache Spark's built-in machine learning library for distributed, large-scale ML on data lakes and warehouses. MLlib provides scalable algorithms for classification, regression, clustering, and collaborative filtering, plus a pipeline API for feature engineering.
Stability AI Platform
by Stability AI
The Stability AI Platform provides API access to Stability AI's suite of generative image, video, and audio models including Stable Diffusion 3.5 and Stable Video Diffusion, enabling developers to build creative AI applications at scale. It offers both hosted API endpoints and open-weight models for on-premises deployment.
MediaPipe
by Google
MediaPipe is Google's cross-platform framework for building perception pipelines that run on-device in real time. It provides production-ready solutions for tasks like hand tracking, face detection, pose estimation, and object detection across Android, iOS, web, and desktop.
Streamlit
by Snowflake (via acquisition)
Python-first framework for building interactive data applications and ML demos in minutes with no frontend experience required. Streamlit's reactive execution model, built-in widgets, and LLM streaming components make it the go-to tool for AI prototype UIs.
DeepL API
by DeepL
DeepL API provides neural machine translation of exceptional quality for 30+ languages, consistently outperforming competitors on blind translation benchmarks. It supports real-time text and full document translation with format preservation, a glossary system, and a free tier for developers.
Zapier AI
by Zapier
Zapier AI extends the world's largest no-code automation platform with AI-powered workflow generation, natural language Zap building, and an AI Actions API that lets LLMs trigger real-world automations. It connects 6000+ apps and enables non-technical users to build AI-augmented workflows without writing code.
Databricks
by Databricks Inc.
Unified data intelligence platform combining data engineering, ML, and GenAI on a Lakehouse foundation. Databricks provides managed Spark, Delta Lake, MLflow, and Model Serving with vector search, enabling end-to-end AI pipelines from raw data to production models.
Rosetta
by RosettaCommons
Rosetta is a comprehensive software suite for computational macromolecular modeling and design, enabling researchers to predict protein structure, design novel proteins, and model protein-protein interactions. Developed by the RosettaCommons consortium, it is the gold standard in computational protein design and has contributed to multiple Nobel Prize-winning research programs.
Anthropic Tool Use
by Anthropic
Anthropic's native tool use capability allowing Claude models to interact with external tools and APIs. Provides structured tool definitions with input schemas and supports parallel tool calls and streaming.
ONNX Runtime Mobile
by Microsoft
ONNX Runtime Mobile is Microsoft's high-performance inference engine optimized for mobile and edge devices, enabling deployment of models from any ONNX-compatible training framework. It provides hardware-accelerated inference via NNAPI, Core ML, and XNNPACK execution providers.
Runway ML
by Runway
Runway ML is a leading generative AI creative platform for video generation, editing, and visual effects, offering models like Gen-3 Alpha for high-fidelity text-to-video and image-to-video synthesis. It is used by filmmakers, advertisers, and content creators to produce cinematic-quality AI-generated video at scale.
Gradio
by Hugging Face
Python library for rapidly building shareable ML demos with a focus on multimodal inputs including images, audio, video, and text. Gradio is the standard for Hugging Face Spaces demos and integrates natively with the Hugging Face Hub model ecosystem.
Apache TVM
by Apache Software Foundation
Apache TVM is an open-source machine learning compiler stack that optimizes deep learning workloads for a diverse set of hardware backends including CPUs, GPUs, FPGAs, and custom accelerators. It automates model optimization through its AutoTVM and Ansor auto-tuning systems, delivering state-of-the-art inference performance on edge targets.
OneTrust AI
by OneTrust
OneTrust offers a Trust Intelligence Platform to help organizations manage privacy, security, and data governance. It automates workflows for compliance with regulations like GDPR and CCPA, manages user consent, and provides tools for AI governance, data discovery, and third-party risk assessment across the enterprise.
Delta Lake
by Linux Foundation (Delta Lake Project)
Delta Lake is an open-source storage layer that brings ACID transactions and reliability to data lakes. Built on top of Parquet files, it enables features like schema enforcement, time travel for data versioning, and unified batch and streaming data processing. It serves as the foundational storage format for the Lakehouse architecture.
Claude Code
by Anthropic
Claude Code is an agentic AI coding assistant from Anthropic designed to operate within a developer's terminal. It autonomously handles complex software development tasks by understanding entire codebases, editing files, executing shell commands, and managing Git workflows, acting as a hands-on pair programmer with minimal human supervision.
AWS API Gateway (ML)
by Amazon Web Services
AWS-managed API gateway service for building, deploying, and scaling ML and AI APIs backed by Lambda, SageMaker, and Bedrock endpoints. AWS API Gateway provides built-in authorization, throttling, caching, and monitoring for production AI service deployments at any scale.
LangSmith Testing
by LangChain
LangSmith is a platform for debugging, testing, evaluating, and monitoring LLM applications. It enables developers to visualize execution traces of their chains and agents, collect datasets, and run automated evaluators to score model performance. The platform is designed to streamline the LLM development lifecycle from prototype to production.
Neo4j GraphRAG
by Neo4j
Neo4j GraphRAG combines graph database capabilities with vector search to build retrieval-augmented generation systems that leverage structured relationships alongside semantic similarity. It enables developers to construct knowledge graphs that ground LLM responses in connected, structured data reducing hallucinations and improving traceability.
Semantic Kernel
by Microsoft
Microsoft's open-source SDK for integrating LLMs into applications with plugin architecture. Supports planners, memory, and connectors for building enterprise AI solutions across .NET, Python, and Java.
Make AI
by Make
Make (formerly Integromat) is a visual no-code automation platform with deep AI integration that enables complex multi-step workflows through a drag-and-drop scenario builder. It offers granular data transformation, HTTP module flexibility, and AI-powered scenario generation for orchestrating sophisticated automation pipelines.
Milvus
by Zilliz
Cloud-native vector database built for scalable similarity search with GPU acceleration. Supports billions of vectors with multiple index types, hybrid search, and multi-vector queries.
Instructor
by Jason Liu
Instructor is a Python library that simplifies extracting structured, typed data from Large Language Model (LLM) responses. By leveraging Pydantic models, it enables developers to define a desired data schema, and Instructor handles the prompting, validation, and retries to ensure the LLM output conforms to that schema, streamlining data extraction tasks.
Groq
by Groq
Groq is an AI inference company that provides ultra-fast access to open-source large language models. It leverages its custom-designed Language Processing Unit (LPU) hardware to deliver industry-leading token generation speeds, significantly reducing latency for real-time applications via an OpenAI-compatible API.
Jasper AI
by Jasper
Jasper is an AI content platform designed for enterprise marketing teams. It helps create on-brand content at scale by combining advanced AI models with a company's specific brand knowledge. The platform supports multi-channel content generation, campaign workflows, and ensures brand voice consistency across all outputs.
Model Context Protocol
by Anthropic
Open protocol by Anthropic for connecting AI models to external tools, data sources, and services. Provides a standardized interface for tool use with server and client SDKs for building integrations.
H2O AutoML
by H2O.ai
H2O AutoML is an open-source, distributed machine learning platform that automates the model training process. It systematically explores various algorithms and hyperparameters to produce a leaderboard of the best models. It supports both a Python/R API and a no-code Flow UI, making it accessible to both developers and business users.
Bubble AI
by Bubble
Bubble AI is an AI-powered no-code development platform for building web applications without writing code. Users can describe their app idea in natural language, and the AI assistant generates layouts, database structures, and workflows. This visual programming environment allows for extensive customization, ideal for creating MVPs and internal tools.
LoRA Library
by Hugging Face
The LoRA Library, integrated within Hugging Face's PEFT (Parameter-Efficient Fine-Tuning) package, provides tools to create, share, and use LoRA adapters. It allows for the efficient customization of large pre-trained models by training only a small number of new weights, drastically reducing computational costs and storage requirements compared to full fine-tuning.
TGI
by Hugging Face
A production-ready inference server for large language models, developed by Hugging Face in Rust. It enables high-performance LLM serving through features like tensor parallelism, continuous batching, and quantization, making it ideal for deploying demanding models at scale with low latency.
GitBook AI
by GitBook
GitBook AI is an intelligent documentation and knowledge management platform with built-in AI that can answer questions, generate content, and surface insights from your entire knowledge base. It combines a Notion-like editor with an AI search assistant and GitHub sync for technical teams.
Temporal AI
by Temporal Technologies
Durable workflow orchestration platform that makes it easy to build reliable distributed applications. Temporal handles retries, timeouts, and failure recovery automatically, making it ideal for long-running AI pipelines and agent orchestration.
Mintlify
by Mintlify
Mintlify is an AI-powered platform for creating and maintaining developer documentation. It auto-generates content from code comments and OpenAPI specs, provides an AI chatbot trained on the docs for instant answers, and offers a rich component library for technical writing. The platform simplifies publishing and hosting.
Terra
by Broad Institute / Microsoft
Terra is a cloud-based open platform for biomedical researchers to access data, run analysis tools, and collaborate, built on Google Cloud with support for WDL and CWL workflow languages. It provides access to petabyte-scale genomic datasets including TCGA and GTEx, and supports scalable analysis through Cromwell and Spark pipelines.
AutoGluon
by Amazon Web Services
AutoGluon is an open-source AutoML framework from AWS that simplifies machine learning. It automates model training, hyperparameter tuning, and ensembling to achieve state-of-the-art performance on tabular, image, text, and time-series data with just a few lines of Python code, making advanced ML accessible to all skill levels.
Unity ML-Agents
by Unity Technologies
Unity ML-Agents is an open-source toolkit that enables the use of the Unity game engine as a simulation environment for training intelligent agents. It connects rich 3D environments with Python-based deep reinforcement learning and imitation learning frameworks like TensorFlow and PyTorch, facilitating research and development in game AI, robotics, and autonomous systems.
Airbyte
by Airbyte Inc.
Open-source data integration platform with 350+ pre-built connectors for syncing data into AI-ready warehouses and vector databases. Airbyte's PyAirbyte SDK and AI Connector Builder enable rapid connector creation for custom data sources and AI pipelines.
Label Studio
by HumanSignal
Open-source data labeling and annotation platform supporting text, image, audio, and video. Provides customizable labeling interfaces, ML-assisted labeling, and team collaboration for building training datasets.
Auto-sklearn
by University of Freiburg (AutoML Group)
Auto-sklearn is an open-source AutoML toolkit built on scikit-learn. It leverages Bayesian optimization, meta-learning, and automated ensemble construction to find the best-performing machine learning pipeline for a given tabular dataset. It is a prominent tool in academic research for automated model selection.
Cline
by Cline
Autonomous coding agent that operates directly in VS Code with support for multiple LLM providers. Can create and edit files, run terminal commands, and browse the web while requiring human approval for actions.
Edge Impulse
by Edge Impulse
Edge Impulse is a leading development platform for machine learning on embedded systems and IoT devices. It offers an end-to-end MLOps pipeline, from data collection and signal processing to model training and deployment. The platform simplifies creating TinyML applications for resource-constrained microcontrollers.
Dagster
by Dagster Labs
Dagster is an asset-centric data orchestrator for building, testing, and monitoring data pipelines. It models data dependencies and computations as a graph of software-defined assets, providing built-in data lineage, type checking, and observability. This approach helps data teams create reliable and maintainable data platforms.
ReadMe AI
by ReadMe
ReadMe AI is an interactive API documentation platform that transforms OpenAPI specs and Markdown into beautiful, interactive developer hubs with personalized API explorers. Its AI-powered features include auto-generated code samples, semantic search, and contextual AI answers drawn from your documentation.
Outlines
by .txt
Outlines is an open-source Python library that provides fine-grained control over large language model text generation. It uses constrained decoding to force the model's output to conform to a specific structure, such as a regular expression, a Pydantic model, or a JSON schema. This guarantees that the generated text is always valid and parseable, eliminating the need for post-processing and error handling.
Play.ht
by Play.ht
Play.ht is an AI-powered text-to-speech generator and voice cloning platform. It offers a vast library of over 900 AI voices in multiple languages and accents. The platform is designed for various applications, from creating audio versions of articles to developing interactive conversational AI, thanks to its low-latency real-time streaming API.
Triton Inference Server
by NVIDIA
Triton is an open-source inference server from NVIDIA designed for high-performance, production-ready AI. It supports deploying models from virtually any framework, such as TensorFlow, PyTorch, and ONNX, on both GPUs and CPUs. Key features include dynamic batching, concurrent model execution, and model ensembling to maximize throughput and resource utilization.
n8n AI
by n8n
n8n AI is a source-available, workflow automation platform that enables users to build complex, AI-powered automations. It features a visual, node-based editor where users can connect hundreds of applications and services, including various LLMs and AI agents, to orchestrate intricate processes with minimal code.
TrustArc AI
by TrustArc
TrustArc AI is a comprehensive privacy management platform that leverages AI to automate and simplify compliance with global regulations like GDPR and CCPA. It provides tools for data inventory, risk assessments, and consent management, helping organizations build and maintain robust privacy programs.
Hopsworks
by Hopsworks AB
Hopsworks is an open-source ML platform centered around its feature store, enabling teams to manage the full lifecycle of features from engineering to serving for both batch and real-time ML workloads. It integrates deeply with Apache Spark, Flink, and Python environments, and provides built-in model registry and serving capabilities.
NVIDIA Omniverse
by NVIDIA
NVIDIA's platform for building physically accurate 3D simulations, digital twins, and collaborative virtual worlds powered by Universal Scene Description (USD) and real-time ray tracing. Omniverse integrates generative AI for scene synthesis, avatar animation, and synthetic data generation for robot and autonomous vehicle training.
Replit AI
by Replit
AI-powered cloud development platform with integrated coding assistant and one-click deployment. Combines a browser-based IDE with AI code generation, debugging, and instant deployment to production.
Kong AI Gateway
by Kong Inc.
AI-native API gateway that provides a unified control plane for managing, securing, and observing all LLM traffic across any provider. Kong AI Gateway adds semantic caching, prompt injection protection, token rate limiting, and cost attribution on top of the battle-tested Kong Gateway.
Phrase TMS AI
by Phrase
Phrase TMS AI is a translation management system with integrated AI that automates the end-to-end localization workflow for enterprises, including MT integration, translation memory, terminology management, and quality assurance automation. It serves as the operational backbone for global content and software localization programs.
Tecton
by Tecton
Tecton is an enterprise feature store platform that enables data scientists and ML engineers to build, share, and serve features for real-time and batch machine learning applications. It provides a declarative Python SDK for defining feature pipelines, with automatic backfilling, versioning, and point-in-time correct training data generation.
Kubeflow
by Google
Open-source ML platform for Kubernetes providing end-to-end ML workflow orchestration. Includes pipeline authoring, distributed training, hyperparameter tuning, and model serving on Kubernetes clusters.
Apigee AI (Google Cloud)
by Google Cloud
Google Cloud's enterprise API management platform with native Vertex AI and Gemini integration for building secure AI-powered APIs. Apigee AI adds LLM traffic management, semantic caching, safety policies, and analytics to Google's proven API gateway infrastructure.
Kapwing AI
by Kapwing
Kapwing is a browser-based AI video editor designed for content creators and social media teams. It offers AI-powered subtitle generation, background removal, smart cut, and one-click repurposing across formats and aspect ratios.
Unbabel
by Unbabel
Unbabel is an AI-powered translation platform that combines neural machine translation with a community of professional post-editors to deliver human-quality translations at machine speed. It is purpose-built for enterprise customer support and content teams requiring guaranteed accuracy at scale.
Modal
by Modal
Serverless cloud platform for running GPU-accelerated Python code with zero infrastructure management. Provides instant container spin-up, GPU autoscaling, and simple decorators for deploying ML workloads.
Guidance
by Microsoft
Microsoft's language for controlling LLMs with interleaved generation and prompting. Supports constrained output via token healing, regex constraints, and context-free grammars for reliable generation.
PathAI
by PathAI
PathAI is an AI-powered pathology platform that assists pathologists in diagnosing diseases including cancer by analyzing digitized tissue slides with deep learning models trained on millions of pathology images. It provides quantitative biomarker analysis, treatment response prediction, and clinical trial endpoint measurement at scale.
FLAML
by Microsoft Research
Fast and Lightweight AutoML library from Microsoft Research that minimizes compute while maximizing accuracy. FLAML uses cost-aware hyperparameter search and is designed to be embedded inside larger systems, including the AutoGen multi-agent framework.
Credo AI
by Credo AI
Credo AI is an AI governance platform that enables organizations to assess, monitor, and document AI model risks, fairness, and regulatory compliance. It automates evidence collection for frameworks like EU AI Act, NIST AI RMF, and ISO 42001, bridging the gap between AI teams and risk officers.
Chainlit
by Chainlit (Community)
Production-ready Python framework for building conversational AI applications with streaming, message threading, and human-in-the-loop feedback. Chainlit is optimized specifically for LLM chat UIs and integrates natively with LangChain, LlamaIndex, and LiteLLM.
RunPod
by RunPod
Cloud GPU platform for AI inference and training with serverless and dedicated GPU options. Provides cost-effective GPU rentals with pre-built templates for popular ML frameworks and models.
SerpAPI
by SerpAPI
API for scraping and parsing search engine results from Google, Bing, Yahoo, and others. Provides structured JSON results from multiple search engines with support for locations, languages, and devices.
Great Expectations
by Superconductive
Open-source data quality platform for validating, profiling, and documenting data pipelines. Provides expectation-based testing for data quality with automated documentation and alerting capabilities.
DVC
by Iterative
Open-source version control system for machine learning projects with Git-like data management. Provides data versioning, experiment tracking, and ML pipeline management alongside your existing Git workflow.
ArangoDB
by ArangoDB
ArangoDB is a native multi-model database supporting graphs, documents, and key-value storage in a single engine, with integrated vector search and ML capabilities for building knowledge-graph-backed AI applications. Its AQL query language and ArangoSearch make it suitable for complex knowledge retrieval pipelines combining structural and semantic search.
Swarm
by OpenAI
OpenAI's experimental lightweight multi-agent orchestration framework focused on handoffs and routines. Provides a minimal abstraction for agent coordination using function calling and agent transfers.
Patronus AI
by Patronus AI
Patronus AI is an enterprise LLM evaluation platform specializing in automated testing for hallucination, toxicity, PII leakage, and factual accuracy across production AI systems. It provides a library of 1,000+ pre-built evaluators and supports custom evaluator creation to enforce application-specific quality gates.
Fireworks AI
by Fireworks AI
High-performance inference platform for generative AI with fast model serving and fine-tuning. Optimized for production workloads with function calling, JSON mode, and grammar-based generation.
Continue
by Continue
Open-source AI code assistant for VS Code and JetBrains with customizable model and context providers. Supports tab autocomplete, chat, inline editing, and custom slash commands with any LLM.
Pictory
by Pictory AI
Pictory is an AI video creation platform that transforms long-form text, articles, and scripts into short branded videos automatically. It includes AI voiceovers, stock footage matching, automatic highlight extraction, and a brand kit for consistent visual identity.
Flyte
by Union.ai (Linux Foundation)
Kubernetes-native workflow orchestration platform purpose-built for machine learning and data processing at scale. Flyte enforces strong typing on inputs and outputs, provides built-in versioning, and integrates natively with Kubernetes for resource management.
Arthur AI
by Arthur AI
Arthur AI is an enterprise ML monitoring and observability platform that tracks model performance, detects data and concept drift, and measures fairness in production deployments. It provides real-time alerting, explainability dashboards, and bias mitigation tooling for high-stakes AI applications.
Anyscale
by Anyscale
Enterprise platform for scaling AI applications built on the Ray distributed computing framework. Provides managed Ray clusters, model serving, and fine-tuning infrastructure for production AI workloads.
Arize AI
by Arize AI
ML observability platform for monitoring model performance, detecting drift, and troubleshooting issues. Provides real-time monitoring, embedding analysis, and automated performance alerts for AI systems.
Amazon Neptune ML
by Amazon Web Services
Amazon Neptune ML is a managed graph machine learning capability built on Neptune that uses graph neural networks to make predictions on graph data without requiring ML expertise. It automatically trains GNN models on graph structure and node/edge properties for tasks like node classification, link prediction, and regression.
Panel
by HoloViz / NumFOCUS
High-level app and dashboarding framework from HoloViz that works with nearly every visualization library in the Python ecosystem. Panel supports reactive programming, GPU-accelerated plotting, and server-side rendering, making it ideal for complex analytical AI dashboards.
Metaflow
by Netflix / Outerbounds
Human-friendly Python library for building and managing real-life data science and ML projects. Originally developed at Netflix, provides seamless scaling from laptops to cloud with versioning and reproducibility.
Traefik AI Gateway
by Traefik Labs
Cloud-native edge router and AI gateway built for Kubernetes-native LLM traffic management. Traefik AI extends the battle-tested Traefik reverse proxy with LLM-aware middleware for token counting, semantic caching, failover routing, and provider load balancing.
Sourcegraph Cody
by Sourcegraph
AI coding assistant powered by Sourcegraph's code graph for deep codebase understanding. Provides context-aware code generation and answers using entire repository knowledge across large codebases.
Snorkel
by Snorkel AI
Enterprise data-centric AI platform for programmatically labeling and curating training data. Uses weak supervision and labeling functions to create large labeled datasets without manual annotation.
Spline AI
by Spline Design
Browser-based 3D design tool with integrated AI generation capabilities for creating interactive 3D scenes, objects, and animations from text prompts. Spline AI allows designers and developers to produce real-time web-ready 3D graphics without traditional 3D modeling expertise.
Marker
by VikParuchuri
Fast and accurate PDF to Markdown converter optimized for books and scientific papers. Handles complex layouts, equations, tables, and multi-column documents with higher quality than traditional OCR tools.
Zilliz Cloud
by Zilliz
Fully managed vector database service built on Milvus for enterprise-grade similarity search. Provides auto-scaling, high availability, and enterprise security with a simplified operational experience.
Cleanlab
by Cleanlab
Data-centric AI library for finding and fixing label errors in datasets automatically. Uses confident learning algorithms to identify mislabeled data, estimate noise, and improve model training quality.
Gemini Code Assist
by Google
Google's AI-powered code assistance tool integrated with Google Cloud and IDEs. Provides code completions, explanations, and transformations powered by Gemini models with enterprise security controls.
txtai
by NeuML
All-in-one embeddings database for semantic search, LLM orchestration, and language model workflows. Combines vector search with NLP pipelines including summarization, translation, and text-to-speech.
Swimm
by Swimm
Swimm is an AI-powered code documentation tool that auto-generates and keeps documentation synchronized with the codebase using IDE plugins. It detects code changes and alerts developers when docs become stale, enabling engineering teams to maintain accurate, living documentation at scale.
Serper
by Serper
Fast and affordable Google Search API for developers and AI applications. Provides structured Google search results including organic results, knowledge graphs, and related questions via a simple REST API.
AutoTrain
by Hugging Face
Hugging Face's automated training solution for fine-tuning LLMs and other models with minimal configuration. Provides a no-code UI and CLI for training custom models with automatic hyperparameter selection.
Stardog
by Stardog
Stardog is an enterprise knowledge graph platform built on W3C standards (RDF, OWL, SPARQL) that enables organizations to unify disparate data sources into a semantic layer for AI and analytics. Its Virtual Graph capability connects to existing databases without data migration, and its AI integration supports LLM grounding on enterprise knowledge.
Prodigy
by Explosion
Scriptable annotation tool by Explosion for creating training data with active learning. Integrates with spaCy for NLP tasks and provides efficient annotation workflows with model-in-the-loop labeling.