Tag

Provides a collaborative API development platform for designing, testing, documenting, and monitoring APIs — with sharable Collections, mock servers, CLI, and AI-driven features (Agent Mode, AI Agent Builder, MCP Server) to automate API workflows.

Programmatically author, schedule, and monitor data workflows using Python-defined DAGs. Features modular executors, rich provider/operator ecosystem (Kubernetes, AWS, GCP), and built-in scheduling/monitoring for batch and ML pipelines.

Tracks and visualizes ML experiments, dataset/model versioning, and team collaboration through SDKs and dashboards; integrates with major frameworks and supports hosted or self‑hosted deployments. ([wandb.ai](https://wandb.ai/?utm_source=openai))

Simplifies training and scaling PyTorch models by providing a lightweight, opinionated wrapper for training loops, distributed strategies, and experiment orchestration. Modular components and integrations let you prototype on one GPU and scale to multi-node setups with minimal code changes.

Visual workflow automation platform that connects apps, APIs and services to automate tasks and orchestrate processes. Offers many built-in connectors, self‑hosting and cloud options, Node.js extensibility, and community workflow templates — good for integrations and API orchestration.

Manages OAuth, credential storage, API proxying, and deployable TypeScript integration functions so products and AI agents can access 800+ external APIs. Includes AI-assisted function generation, a production runtime with scaling and observability, and cloud or self-hosted deployment options.

Qlib is an open-source, AI-oriented quantitative investment platform from Microsoft that provides a full pipeline for quant research — data processing, feature engineering, model training, backtesting and serving. It supports supervised learning, market-dynamics modeling and reinforcement learning, and integrates tools (e.g., RD-Agent) for automated factor mining and model optimization.

Embed configurable AI “employees” into a data-model driven no-code app builder — plugin-based, decouples UI from data models, supports external databases and APIs, and can be deployed via Docker for building internal business apps and workflows.

Unified metadata platform for data discovery, observability, and governance — central metadata repository, column-level lineage, and a pluggable ingestion framework with 84+ connectors. Suited for teams that need searchable data catalogs, automated lineage, and collaborative data governance.

SkyPilot is an open-source MLOps / AI infrastructure project that provides a unified control plane and CLI to run, manage, and scale AI workloads on any compute — Kubernetes, Slurm, 20+ clouds, or on-prem clusters. It supports job-as-code (YAML/Python), intelligent scheduling and cost optimization (spot instances, autostop), automatic setup/sync of environments, auto-recovery, and integrations for training, serving and inference workflows.

Provides reproducible MLOps pipelines for training, evaluation, and deployment — with stack abstractions, end-to-end versioning, and integrations across orchestrators, artifact stores, trackers, and cloud/Kubernetes environments.

Turns the developer terminal into an agentic development environment that accepts natural-language prompts to write code, run multi-step terminal workflows, and debug. Key features include interactive Agent Mode, session sharing, and a cloud orchestration platform (Oz) for scaling agents.