The anthropic-sdk-python repository is the official Python client library for interacting with the Anthropic (Claude) REST API. It is designed to provide a user-friendly, type-safe, and asynchronous/synchronous capable interface for making chat/completion requests to models like Claude. The library includes definitions for all request and response parameters using Python typed objects, automatically handles serialization and deserialization, and wraps HTTP logic (timeouts, retries, error mapping) so that developers can call the API in a clean, high-level way. The SDK supports both synchronous and asynchronous usage (via async/await) depending on context. Importantly, it also supports streaming responses via Server-Sent Events (SSE) so that large outputs can be consumed incrementally rather than waiting for the full response. The client offers helper abstractions for tools (function-style “tools”) and streaming utilities for building interactive agents.

Features

  • Typed Python client for Anthropic Claude REST API with request/response models
  • Support for both synchronous and asynchronous (async/await) API usage
  • Streaming (SSE) response support for incremental output consumption
  • Token counting utilities to forecast usage without executing full request
  • Tool / function-calling helpers to integrate with “tool” infrastructure
  • Built-in retry logic, error mapping, and HTTP configuration (timeouts, custom clients)

Project Samples

Anthropic SDK Python Screenshot 1

Project Activity

See All Activity >

Categories

AI Models

License

MIT License

Follow Anthropic SDK Python

Anthropic SDK Python Web Site

Other Useful Business Software
Attack Surface Management | Criminal IP ASM Icon
Attack Surface Management | Criminal IP ASM

For security operations, threat-intelligence and risk teams wanting a tool to get access to auto-monitored assets exposed to attack surfaces

Criminal IP’s Attack Surface Management (ASM) is a threat-intelligence–driven platform that continuously discovers, inventories, and monitors every internet-connected asset associated with an organization, including shadow and forgotten resources, so teams see their true external footprint from an attacker’s perspective. The solution combines automated asset discovery with OSINT techniques, AI enrichment and advanced threat intelligence to surface exposed hosts, domains, cloud services, IoT endpoints and other Internet-facing vectors, capture evidence (screenshots and metadata), and correlate findings to known exploitability and attacker tradecraft. ASM prioritizes exposures by business context and risk, highlights vulnerable components and misconfigurations, and provides real-time alerts and dashboards to speed investigation and remediation.
Learn More
Rate This Project
Login To Rate This Project

User Reviews

Be the first to post a review of Anthropic SDK Python!

Additional Project Details

Programming Language

Python

Related Categories

Python AI Models

Registered

2025-10-06
Report inappropriate content