Packages
4946 resultsAserto
Cloud-native fine-grained authorization service for applications and APIs. Aserto provides a hosted Open Policy Agent (OPA) service with user/group management, role-based access control (RBAC), and relationship-based access control (ReBAC / Google Zanzibar model). Decision logs, policy versioning, and middleware SDKs for Express, FastAPI, Rails, and more. Agents call Aserto's authorization API to answer 'can user X perform action Y on resource Z?' without building custom authorization logic.
Azure Cosmos DB API
Fully managed, globally distributed NoSQL and relational database service from Microsoft Azure. Supports multiple APIs (NoSQL/Core, MongoDB, Cassandra, Gremlin, Table) over the same underlying engine. Offers single-digit millisecond reads, configurable consistency levels (5 levels from eventual to strong), and turnkey multi-region writes with automatic failover.
Cloudflare Hyperdrive API
Accelerates connections from Cloudflare Workers to remote PostgreSQL databases by maintaining persistent regional connection pools and caching query results at the edge.
Couchbase REST API
Couchbase REST API enables agents to perform distributed NoSQL document operations, N1QL/SQL++ queries, full-text search, and mobile data sync against a high-performance multi-service cluster.
Finance Trading AI Agents MCP
Finance Trading AI Agents MCP server enabling AI agents to access financial market data and trading tools — fetching stock prices and market data, analyzing financial instruments, and integrating market data into agent-driven investment research and trading analysis workflows.
Hugging Face Inference API
Hugging Face Inference API — run inference on 200,000+ open-source models (LLMs, NLP, CV, audio) via a unified REST API without managing GPU infrastructure.
HuggingFace Datasets
HuggingFace Datasets library — fast, efficient loading and processing of ML datasets. Datasets features: load_dataset() for 100,000+ public datasets from Hub, local file loading (CSV, JSON, Parquet, text), Dataset.map() for preprocessing, Dataset.filter(), streaming mode (streaming=True for infinite datasets), Arrow-backed memory mapping (no RAM limits), multi-GPU/CPU parallelism, push_to_hub() for sharing, DatasetDict for train/validation/test splits, dataset caching, and Sequence/ClassLabel/Value feature types. Core library for agent LLM training data, evaluation benchmarks, and RAG document ingestion.
Mojo
Systems programming language designed as a superset of Python, created by Modular (Chris Lattner). Mojo extends Python with manual memory management, SIMD vectorization, GPU programming, and MLIR compiler infrastructure for ML workloads. Goal: Python syntax with C++/CUDA performance for ML code without leaving the Python ecosystem. Mojo compiles to native code and can call Python libraries. Powers Modular's MAX engine for ML inference acceleration.
OpenAI Swarm
Experimental lightweight multi-agent framework from OpenAI exploring ergonomic interfaces for multi-agent orchestration. Swarm introduces two core primitives: Agents (LLM + tools + instructions) and Handoffs (agents transferring control to other agents). Minimal abstraction over OpenAI Chat Completions API. Educational reference implementation for exploring agent handoff patterns. NOT production-ready — OpenAI recommends Agents SDK for production use.
Oracle MCP Servers
Collection of reference MCP server implementations for Oracle products including database tools and OCI API servers. Supports polyglot runtimes (Python, Node.js, Java) with stdio and HTTP streaming transports. Explicitly positioned as proof-of-concept/reference implementations, not production-ready.
Ragas
Open-source Python framework that evaluates RAG pipelines across metrics like faithfulness, answer relevancy, context precision, and context recall using LLM-as-judge and statistical methods.
Rev.ai API
Rev.ai provides a speech recognition API with async job-based transcription, real-time streaming, speaker diarization, and custom vocabulary, built on Rev's human-transcription heritage.
Sci-Hub MCP Server
Sci-Hub MCP server enabling AI agents to retrieve academic papers via Sci-Hub — fetching full-text PDFs of research papers by DOI, PMID, or URL, bypassing academic publisher paywalls. Primarily used by researchers in institutions without journal subscriptions for accessing scientific literature.
Twitch API (Helix)
Twitch's Helix REST API provides access to stream data, channel information, clips, subscriptions, chat, and EventSub webhooks — enabling agent-driven Twitch bots, analytics, and streaming tools.
Twitch Helix API
Twitch Helix is the current Twitch REST API (v2) providing access to stream data, users, clips, games, channel points, subscriptions, and EventSub webhooks — enabling agents to monitor live events, manage channels, and automate Twitch platform interactions.
Unstructured.io
Document parsing library and API that converts PDFs, Word docs, HTML, and emails into structured elements (Title, NarrativeText, Table) ready for LLM ingestion and RAG pipelines.
Windmill
Open-source developer platform for building and running scripts, flows, and internal apps in Python, TypeScript, Go, SQL, and Bash, with a visual flow editor and built-in UI builder.
kombu
Messaging library for Python — provides a unified high-level interface over AMQP and other message transports (Redis, SQS, MongoDB, SQLite, in-memory). kombu features: Connection for transport-agnostic broker connections, Producer/Consumer for publish-subscribe, Exchange (direct/fanout/topic/headers), Queue with routing keys, SimpleQueue for Redis/memory queues, kombu.serialization for JSON/pickle/msgpack, retry policies, drain_events() loop, acks/nacks for reliability, dead letter queues, task routing for Celery, connection pooling, heartbeats, and failover URLs. Celery's transport layer — usable standalone without Celery.
Azure SDK for Python
Official Azure SDK for Python. Modular packages per Azure service: azure-storage-blob, azure-cosmos, azure-servicebus, azure-ai-openai, azure-identity, azure-keyvault-secrets, and 200+ others. Follows Azure SDK design guidelines with consistent patterns across all services — same credential types, same retry policies, same paging patterns. Supports both sync and async (asyncio) variants for each service client.
Checkly
Checkly is a programmable synthetic monitoring platform that runs scheduled API checks and Playwright-based browser tests from global locations, with a REST API and CLI for managing checks, groups, alert channels, and retrieving check results.