Packages

MCP server that provides AI agents with access to Xiaohongshu (Little Red Book / RedNote) content, enabling keyword-based note search and note retrieval via URL through browser-based cookie authentication.

Provides a managed in-app chat and messaging platform via SDKs and a REST API, enabling agents to send messages, manage channels and users, retrieve chat history, and moderate conversations within product applications.

Serpstat REST API for comprehensive SEO data including keyword research, rank tracking, SERP analysis, and competitor intelligence. Enables AI agents to manage keyword research and search volume data for content strategy automation, handle rank tracking and SERP position monitoring for SEO performance, access competitor analysis and domain analytics for competitive intelligence, retrieve backlink data and referring domain analysis for link building automation, manage site audit and technical SEO data for on-page optimization, handle PPC and paid search data for cross-channel keyword strategy, access search trend data for editorial calendar planning, retrieve local SERP data for local SEO automation, manage bulk keyword clustering for content architecture, and integrate Serpstat with SEO platforms, CMS, and marketing analytics systems.

SonarCloud — cloud-based static code analysis and code quality platform that detects bugs, vulnerabilities, and code smells across 30+ languages, with a REST API for querying analysis results.

Open-source infrastructure for building search and RAG pipelines combining dense vector search, sparse vector search (SPLADE), BM25 full-text, and cross-encoder reranking. Trieve provides a REST API for chunk management (ingest, update, delete) and search (semantic, fulltext, hybrid), plus recommendations and RAG with citations. Self-hostable with Trieve Cloud managed option. Strong focus on search quality via multi-stage retrieval.

An open-source platform for building and deploying fully-managed AI agents and long-running workflows in TypeScript, with durable task execution, automatic retries, queues, human-in-the-loop pauses, and full observability.

Customer Data Platform that collects user events from sources via a unified tracking API and routes them to hundreds of analytics, marketing, and data warehouse destinations.

Parses and preprocesses unstructured documents (PDFs, Word, PowerPoint, HTML, images) into clean, structured text chunks optimized for LLM and RAG pipelines.

Delivers historical weather data going back decades plus multi-day forecasts via a unified Timeline API, supporting both JSON and CSV output for any global location.

A Python/Java/Vue backend server for the Xiaozhi ESP32 open-source smart hardware project, providing voice interaction, speaker recognition, multi-LLM dialogue, visual perception, and IoT device control for ESP32-based AI assistants.

High-performance CRDT (Conflict-free Replicated Data Type) implementation for building real-time collaborative applications. Yjs provides shared data structures (Y.Map, Y.Array, Y.Text, Y.XmlFragment) that sync automatically across clients with conflict-free merging. Used by major collaborative editors (Notion, Linear, Liveblocks are built on similar patterns). Agent use: shared state management for multi-agent systems where multiple agents need to write to shared documents or data structures without conflicts.

Async AWS SDK for Python — wraps boto3 with asyncio support for non-blocking AWS service calls. aioboto3 features: async context manager pattern (async with aioboto3.Session() as session), async S3 operations (await s3.put_object, await s3.get_object, transfer.upload_file), async DynamoDB operations, async SQS (await sqs.send_message, receive_message), async SNS, async Secrets Manager, aiobotocore underneath (wraps botocore with aiohttp), paginator async iteration (async for page in paginator.paginate()), and transfer manager for multipart upload/download. Required for async Python web services that need non-blocking AWS access in FastAPI/aiohttp handlers.

Native Rust implementation of the Delta Lake protocol with Python bindings (deltalake package). Enables reading and writing Delta Lake tables without Spark — works in Python, Rust, and through Arrow/Pandas integration. Used to interact with Delta Lake from Python data pipelines, ML workflows, and agent backends. The Python deltalake package wraps the Rust implementation for high performance.

iDenfy identity verification and biometric KYC REST API for banks, fintech, gaming, and regulated businesses across Europe and globally to perform document verification, facial biometric recognition, liveness detection, and AML screening — enabling automated customer identity verification with 98% automation rate through iDenfy's AI-powered KYC platform built in Lithuania with strong GDPR compliance. Enables AI agents to manage identity session for automated KYC verification flow automation, handle document verification for ID document capture and OCR automation, access face match for selfie-to-document biometric comparison automation, retrieve liveness for anti-spoofing real user detection automation, manage AML screening for sanctions and PEP watchlist check automation, handle NFC verification for chip-based document authentication automation, access video call for agent-supervised identity verification automation, retrieve database check for name and DOB identity corroboration automation, manage e-signature for KYC-integrated document signing automation, and integrate iDenfy with onboarding flows and compliance platforms for EU-compliant identity verification automation.

Open-source data lakehouse table format providing ACID transactions, record-level updates/deletes, and incremental processing on cloud object stores (S3, GCS, Azure). Hudi enables streaming upserts, efficient incremental queries ('give me records changed since timestamp X'), and time-travel on data lakes built on Spark, Flink, or Presto. Originated at Uber for streaming CDC to data lakes at scale. Competes directly with Delta Lake and Apache Iceberg.

ML model deployment platform for serving custom ML models and open-source models (Llama, Whisper, SDXL, etc.) via a REST API. Uses 'Truss' — an open-source model packaging format — to containerize models with their dependencies. Baseten handles GPU provisioning, auto-scaling, and serving infrastructure. Faster to deploy models than custom Kubernetes setups.

Beyond Identity passwordless authentication REST API for enterprises to implement phishing-resistant, passwordless MFA — replacing passwords and legacy OTP with cryptographic device-bound authentication and real-time device security posture checks — enabling AI agents to manage user enrollment, device binding, authentication policies, risk assessment, and SIEM integration through Beyond Identity's zero trust authentication platform. Enables AI agents to manage identity management for passwordless user identity provisioning and management automation, handle authenticator binding for device credential binding and management automation, access policy management for risk-based authentication policy creation and enforcement automation, retrieve event management for authentication event and risk signal retrieval automation, manage tenant management for enterprise tenant configuration and administrative automation, handle integration management for SSO, IdP, and SIEM integration configuration automation, access device trust for real-time device security posture assessment automation, retrieve risk management for adaptive risk scoring and step-up authentication trigger automation, manage application management for protected application and authentication configuration automation, and integrate Beyond Identity with Okta, Azure AD, Ping Identity, and SIEM platforms for zero trust authentication automation.

Open-source computer vision annotation platform originally developed by Intel. Supports image and video annotation for object detection, segmentation, classification, and keypoint tasks. Provides collaborative annotation with multiple annotators, quality control workflows, and semi-automatic annotation using AI models (SAM, YOLOv8, etc.). REST API enables programmatic task creation, annotation export, and integration with ML pipelines. Hosted as CVAT.ai SaaS or self-hosted.

Comprehensive process automation platform combining BPMN workflow orchestration and DMN decision management with visual modeling tools, human task management, and analytics for end-to-end business process automation.

Distributed Evolutionary Algorithms in Python — toolkit for implementing genetic algorithms, genetic programming, evolution strategies, and swarm intelligence. DEAP features: creator for custom individual/fitness classes, toolbox for operator registration, algorithms.eaSimple/eaMuPlusLambda for full EA loops, genetic operators (crossover, mutation, selection), Pareto front multi-objective optimization (NSGA-II), genetic programming tree evaluation, Hall of Fame for best individuals, Statistics tracking, pickle-based parallelism with scoop, and flexible fitness design. Used for feature selection, hyperparameter optimization, NAS, game playing, and prompt evolution.