Packages
OpenDataLab Python SDK provides programmatic and CLI access to datasets hosted on the OpenDataLab platform, with login, search, listing, and download capabilities.
However, be aware that the last release was over a year ago, the maintainers flag ongoing compatibility concerns with the platform API, and you may need to stay on…
Extracts structured data (Markdown, JSON, HTML) from PDFs with bounding boxes and semantic tagging, and auto-tags untagged PDFs into Tagged PDF format for accessibility compliance.
Provides event definitions and tooling for the Open edX Hooks Extension Framework (OEP-50), enabling event-driven architecture within Open edX services.
OpenEnv provides a Gymnasium-style framework for creating and deploying isolated execution environments that agents can interact with via standard `reset()`, `step()`, and `state()` APIs over HTTP and WebSocket.
Not recommended for production systems requiring API stability.
OpenEvals provides a framework for writing and running evaluators to assess LLM application outputs, including LLM-as-judge evaluators, code evaluators, and prebuilt prompts for common evaluation scenarios.
Read and write OpenEXR image files with support for scanline, tiled, deep, multi-part, and multi-view formats, exposing pixel data through numpy arrays.
However, verify the actual license terms before use—the metadata does not declare an SPDX identifier or include raw license text, so you must confirm compatibility…
Defines the Python Protocol contract for flagd evaluators, allowing custom implementations to integrate with the OpenFeature SDK.
Install only if you need to implement the Evaluator protocol; it is not a standalone tool but a dependency for evaluator development.
Evaluates feature flags using JSON logic and custom operators (fractional, semantic versioning, string matching) as a reference implementation for the OpenFeature flagd evaluator.
Install only if you are already adopting OpenFeature; it is a specialized component, not a general-purpose library.
Automatically captures feature flag evaluations as span events in OpenTelemetry traces, enabling observability of how feature flags affect runtime behavior.
Install it if you use both OpenFeature and OpenTelemetry and want to understand how feature flags affect your system's behavior.
Integrates flagd flag evaluation into Python applications via the OpenFeature SDK, supporting both remote gRPC-based evaluation and local in-process flag resolution.
Connects the OpenFeature SDK to Flagsmith for server-side feature flag evaluation, supporting flag resolution, multivariate experiments, and event tracking.
However, verify the license before use in proprietary contexts, and confirm that your flagsmith client version meets the tracking requirements.
Integrates OpenFeature SDK with remote flag evaluation servers via the OpenFeature Remote Evaluation Protocol (OFREP), enabling centralized feature flag management over HTTP.
Integrates Unleash feature flags with OpenFeature SDK, enabling standardized flag evaluation and context-aware feature toggling in Python applications.
Install it if you are already using OpenFeature SDK and want Unleash as your flag provider, or if you want to standardize flag evaluation across multiple vendors.
OpenFeature Python SDK provides a vendor-agnostic API for feature flagging that abstracts away the underlying flag management tool, letting you evaluate flags with a consistent interface regardless of provider.
Install it if you need a vendor-agnostic abstraction for feature flagging or are evaluating the OpenFeature ecosystem.
OpenFermion compiles and analyzes quantum algorithms to simulate fermionic systems, providing data structures and tools for manipulating fermionic and qubit Hamiltonians for quantum chemistry applications.
Install it if you are developing quantum algorithms for chemistry or fermionic systems.
Bridges OpenFermion quantum algorithm library with PySCF electronic structure package, enabling fermionic system simulation through PySCF's computational backend.
Python SDK for OpenFGA that wraps the OpenFGA API, enabling fine-grained authorization checks, relationship tuple management, and authorization model operations through an async client.
A Python client library for interacting with Openfire's REST API Plugin, enabling programmatic management of users, groups, chat rooms, sessions, messages, and system configuration.
Query and manage product data from the Open Food Facts database via its official Python API, supporting product lookup, text search, and data creation or updates.
Install it if you need to integrate product lookup or food data into your application.
OpenHands is a CLI tool that runs an AI agent in your terminal, IDE, browser, or CI pipeline to automate development tasks like writing code, fixing bugs, and running tests.
Provides tools and interfaces for AI agents to interact with computer systems for software development tasks, including code editing, linting, and utility functions for file manipulation and analysis.
However, do not start new projects with it—the package is archived and its functionality has moved to the OpenHands Agent SDK.
Provides a REST and WebSocket API server for running OpenHands AI agents that can work with code, either locally or in ephemeral containerized workspaces.
OpenHands is a self-hosted developer control center that runs coding agents (OpenHands, Claude Code, Codex, Gemini, or any ACP-compatible agent) across local, remote, and cloud backends, with built-in support for automations and integrations.
OpenHands SDK provides Python and REST APIs for building software agents that can work with code, execute tasks locally or in ephemeral workspaces, and integrate with LLMs to perform development workflows.
However, the unclear license status requires verification before production use.
Provides Python and REST APIs for building AI agents that work with code, enabling tasks from one-off code generation to multi-agent refactors with local or ephemeral workspace execution.
The main gotchas are the Python 3.12 requirement and the unclear license status—verify the license terms before using in proprietary contexts.
Provides Python and REST APIs for building software agents that can work with code, execute tasks locally or in ephemeral containers, and integrate with LLMs.
However, verify the license terms first—the metadata does not specify one—and ensure your LLM API and Python 3.12+ environment are in place before starting.
OpenImageIO reads, writes, and processes images in nearly any file format via a format-agnostic API, with support for VFX-production image types including EXR, TIFF, JPEG, PNG, and many others through a plugin architecture.
Provides utility functions to convert typed annotation and evaluation objects into OpenInference span attributes, and context managers to attach session, user, metadata, and prompt template information to traced spans.
Auto-instruments Agno Agent applications to emit OpenTelemetry-compatible traces for monitoring and observability, exportable to collectors like Arize Phoenix or Langfuse.
Install it if you are building Agno agents and need observability; it adds minimal friction and works with existing monitoring infrastructure.
Automatically captures and exports traces from Anthropic API calls to OpenTelemetry-compatible collectors like Arize Phoenix, enabling observability of LLM interactions.
Automatically instruments AWS Bedrock API calls (invoke_model, converse, invoke_agent) made via boto3 and aioboto3 to emit OpenTelemetry traces for observability and debugging.
Auto-instruments Claude Agent SDK calls to emit OpenTelemetry-compatible traces capturing prompts, results, token counts, and tool execution as OpenInference AGENT spans.
Install it if you run Claude agents and need traces for debugging, monitoring, or cost analysis.
Automatically instruments CrewAI agent applications with OpenTelemetry tracing, sending execution traces to monitoring backends like Arize Phoenix or Arize AX for observability.
Install it if you have an OpenTelemetry collector available; skip it only if your crews are purely local experiments with no observability requirement.
Auto-instruments DSPy applications to generate OpenTelemetry-compatible traces for observability and debugging, sending them to collectors like Arize Phoenix or Arize AX.
Auto-instruments Google ADK applications to emit OpenTelemetry-compatible traces for observing agent behavior, tool calls, and LLM interactions.
Automatically instruments Google GenAI SDK calls to emit OpenTelemetry-compatible traces for observability and debugging.
Auto-instruments Haystack LLM pipelines and components to emit OpenTelemetry traces for monitoring and observability in tools like Arize Phoenix.
Install it if you need to monitor or debug Haystack LLM pipelines; skip it only if you have no observability requirements or use a different instrumentation approach.
Auto-instruments LangChain applications to generate OpenTelemetry-compatible traces for observability and debugging, compatible with both LangChain 1.x and LangChain Classic.
Auto-instruments LiteLLM function calls (completion, embedding, image generation, and Anthropic API methods) to emit OpenTelemetry-compatible traces for observability in tools like Arize Phoenix.
Auto-instruments LlamaIndex applications to generate OpenTelemetry-compatible traces for observability and debugging, sending them to collectors like Arize Phoenix or Arize AX.
Install it if you're building production LlamaIndex applications or debugging retrieval quality; skip it if you don't need tracing.