claude-sdk

Claude Code ZeroClaw Pro 2026: AI Multitool & CLI Router for Claude SDK Subagents

A self-evolving Agent OS — every interaction sharpens how it judges, not just what it knows. Four ideas: self-evolution (mistakes become code gates, not logged lessons), brain-first domain brains that grow and decay, cognition that persists between sessions, and proprioception — it senses and drives its own body. Human directs. AI delivers.

It shows how to use model-context-protocol.

AI-first subjectivity kernel for agents — persistent emotional state, relation dynamics, adaptive reply loops. Zero extra LLM calls.

Idiomatic Kotlin wrapper around com.anthropic:anthropic-java — suspend / Flow / sealed types over the official Anthropic Java SDK.

Coding Harness - A Human-in-the-Loop Claude Code SDK coding agent with GitLab integration and minimal textual TUI.

A Rust SDK for Anthropic's Claude API that won't panic on you — no unwrap/expect/panic, denied at compile time. Typed structured output and tools derived from Rust structs, streaming, thinking, caching, batches.

A Telegram bot with Claude Agent SDK for knowledge-dense lives

One-file setup for Claude Code that drops a complete "plan → tests → code → docs → PR" workflow into any Git repo, powered by Claude AI

Built 100% With CC. Browser light sandboxed self building IDE wrapper for Claude Code

Define Once. Deploy Anywhere. Govern Automatically. Framework-agnostic platform to build, deploy & govern enterprise AI agents — LangGraph · CrewAI · Claude SDK · OpenAI Agents · Google ADK · AWS · GCP · Azure · K8s · RBAC · A2A · MCP

Trilith v0.1 beta — context engineering for agents (budgeted memory, 3 tiers, audit trail). Core is Python; use via REST or adapters (LangGraph / OpenAI Agents / Claude / TS). Needs trilith serve locally. No API key for Trilith itself. Not prod-hardened. Clone → pip install -e ".[server]" → try docs/adapters.md → open issues.

Hands-on CCA-F exam prep: Customer Support Resolution Agent demonstrating all 6 architectural patterns (escalation, compliance, tool design, caching, context, handoffs) through 9 Jupyter notebooks with anti-pattern vs correct-pattern contrast. 234 tests. Python 3.13+ / Anthropic SDK.

Claude Code via e-mail based on an addressbook with UNIX style rwx permissions per interaction pair.

Documentation for NanoClaw — a lightweight, secure AI assistant that runs Claude agents in isolated containers with multi-messenger support

deep research agent for codebase

An opinionated Agent Runtime built on top of the OpenAI Agent SDK, inspired by Claude-style agent programming.一个构建在 OpenAI Agent SDK 之上的、具有强约定的 Agent 运行时框架，设计理念源自 Claude 风格的 Agent 编程模型。

AI-powered design assistant using Claude's multi-agent architecture. 7 specialized agents for UI/UX reviews, accessibility audits, and design system guidance.

BioTools Agent - 生物信息学工具自动分析系统。基于 Claude Agent SDK 的 GitHub 仓库深度分析工具，支持安全扫描、架构分析和多格式报告生成。

Agent Org — AI-native multi-agent system that turns a single idea into a full production-ready software delivery package (PRD, code, architecture, tests, and DevOps) through coordinated autonomous AI teams.