Claude Agent SDK (Python)
Python SDK that runs the Claude Code agent loop inside your own program, with custom tools and hooks written as Python functions.
Harness by Anthropic
Install
From the package registry. Read the repository before you give any tool access to your data.
pip install claude-agent-sdk
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: code-generation, agent-orchestration
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Fact sheet
- Languages
- PythonREADME
- Packages
- claude-agent-sdk (pypi)README
- MCP support
- Built inREADME
- Streaming
- YesREADME
- Memory
- short-termREADME
- Model providers
- anthropicREADME
- Maturity
- Betagithub.com
Facts extracted by Claude Haiku 5.5 from the linked sources on Oct 24, 2026; reviewed Oct 24, 2026. Wrong fact? Tell us.
Alternatives
Frameworks for the same language with a similar way of orchestrating agents.
- 0.853score
LlamaIndex
LlamaIndex
Open-source Python toolkit for RAG and agents over your own data, with event-driven workflows and 300+ integration packages.
HarnessAFreshness: A★ 52.6K↓ 1.4M/wk - 0.753score
LangChain
LangChain
Python framework of interoperable components and integrations for building agents and LLM apps, with LangGraph and Deep Agents layered above it.
HarnessAFreshness: A★ 148.4K↓ 37.3M/wk - 0.748score
LangGraph
LangChain
Low-level Python orchestration framework for long-running stateful agents, with durable execution, human review points and short- and long-term memory.
HarnessAFreshness: A★ 43.8K↓ 13.1M/wk - 0.732score
CrewAI
CrewAI
Open-source Python framework for multi-agent workflows, with role-based Crews and event-driven Flows.
HarnessAFreshness: A★ 60.1K↓ 644.6K/wk - 0.627score
AutoGen
Microsoft
Archived Microsoft Python framework for multi-agent apps; Microsoft directs new users to Microsoft Agent Framework.
HarnessAFreshness: A★ 61.5K↓ 89K/wk
Compare and alternatives
- Alternatives to Claude Agent SDK (Python) →
- Claude Agent SDK (Python) vs CrewAI
- Claude Agent SDK (Python) vs LlamaIndex
- Claude Agent SDK (Python) vs LangGraph
Featured in
Signals
- Stars
- 8,342
- Forks
- 1,373
- Open issues
- 229
- Weekly downloads
- 7,924,764
- Last commit
- Oct 24, 2026 (3 days ago)
- Last release
- Oct 24, 2026 (3 days ago)
- Last package publish
- Oct 24, 2026 (3 days ago)
From GitHub (fetched Oct 24, 2026) and the package registry.
Details
- Packages
- pypi
claude-agent-sdk - License
- MIT
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- READMEDocsgithub-graphql
More from Anthropic
- 0.761score
legal-risk-assessment-anthropic
Anthropic
Assess and classify legal risks using a severity-by-likelihood framework with escalation criteria.
SkillBFreshness: B★ 895Claude Code +9 - 0.761score
compliance-anthropic
Anthropic
Navigate privacy regulations (GDPR, CCPA), review DPAs, and handle data subject requests.
SkillBFreshness: B★ 895Claude Code +9 - 0.761score
canned-responses-anthropic
Anthropic
Generate templated responses for common legal inquiries and identify when situations require individualized attention.
SkillBFreshness: B★ 895Claude Code +9 - 0.761score
meeting-briefing-anthropic
Anthropic
Prepare structured briefings for meetings with legal relevance and track resulting action items.
SkillBFreshness: B★ 895Claude Code +9 - 0.761score
nda-triage-anthropic
Anthropic
Screen incoming NDAs and classify them as GREEN (standard), YELLOW (needs review), or RED (significant issues).
SkillBFreshness: B★ 895Claude Code +9 - 0.761score
contract-review-anthropic
Anthropic
Review contracts against your organization's negotiation playbook, flagging deviations and generating redline suggestions.
SkillBFreshness: B★ 895Claude Code +9
Cite this page
Claude Agent SDK (Python). Agent Mart. https://agentmart.dev/harnesses/claude-agent-sdk-python (last updated 2026-10-24)