Claude Agent Sdk Python Packages

hubzoid

Open-source SDK to build and run your team’s AI agents. Define them in Markdown, host them on your infrastructure, and use them in chat, automated workflows, or your own AI assistant.

clicker4ai

Self-hosted web app to drive Claude Code sessions on your Linux server from a phone, tablet or laptop

agent-runtime-kit

Typed Python runtime API for Claude Agent SDK, OpenAI Codex SDK, and Google Antigravity SDK.

oak-ci

| Maintenance Mode | OAK automatically captures the plans, decisions, and trade-offs that usually vanish. Intelligence powered memories, context injection, autonomous agents, and more.

mnemara

Controlled rolling-context conversation runtime for Claude. Stop your agent from running away with your bill.

agentlift

Deploy agents to Claude Managed Agents, AWS Bedrock AgentCore, and Google. One folder, one definition, one command.

mainsheet

An agent runtime with guardrails. Define an agent in one file, run it governed, prove what it did: a policy gate at the tool-call boundary, sandboxing, budgets, OpenTelemetry traces, a signed audit trail, and taxonomy-driven evals. Built on the Claude Agent SDK.

chessplaza

A virtual chess plaza with AI-powered chess hustlers, each with their own unique personality and playing style.

charette

Hand Claude a PRD, get reviewed pull requests. Multi-agent orchestrator with a plan gate, adversarial QA, budget caps and a live dashboard — built on the Claude Agent SDK.

charrette

Hand Claude a PRD, get reviewed pull requests. Multi-agent orchestrator with a plan gate, adversarial QA, budget caps and a live dashboard — built on the Claude Agent SDK.

aiyoplane-claude-agent-sdk

AEAP Composition Boundary Adapter for the Claude Agent SDK (Python). Thin wrapper that attaches the AEAP Runtime Decision Point to agent tool invocations — especially useful for coding agents. Published as aiyoplane-claude-agent-sdk on PyPI.

agentanycast

Python SDK for AgentAnycast — connect AI agents across any network

claude-credit-audit

Forecast which Claude calls in your repo burn Agent SDK credit after the 2026-06-15 billing change — scans your CI, claude -p, and claude-code-action to predict monthly cost, the burn-out day, and savings before your credit runs out.

gemma-mnemara

Controlled rolling-context conversation runtime for Claude. Stop your agent from running away with your bill.

pytest-claude-agent-sdk

Use Claude Code in your pytests, or pytest your own Claude Code agents — or both

kagura-agent

Memory-backed autonomous AI agent on the Claude Agent SDK / kagura-brain — Docker security membrane, per-task credential leasing, capability graduation, and a Slack/Discord cockpit. Runnable, Apache-2.0.

loopgrid-claude-agent

LoopGrid Claude Agent SDK integration — cryptographically verifiable decision evidence, policy enforcement, human approval, and secure tool execution.

ariadne-sensemaking

One agent tracing a single entity's evidence across graph, relational, and text stores into a cited analytic note. Built on the Claude Agent SDK.

nuvel-cli

Production-ready agents, your way.

harness-agent-kit

Agent Kit is a comprehensive AI agent development framework that integrates Claude Agent SDK, providing a complete solution from frontend to backend. This project aims to help developers quickly build, deploy, and scale production-grade AI Agent applications.