HomeProjectsArticlesPK BoardAbout
Explore Projects

Strands Agents SDK

Active
GitHub Python Apache-2.0

Description

Strands Agents SDK is an AWS open-source agent framework using a model-driven approach to build AI agents with built-in tool use, conversation memory, and multi-agent collaboration.

Key Features

  • Model-driven agent framework with simple Python API in just a few lines of code
  • Support for 12+ model providers including Bedrock, Anthropic, Gemini, OpenAI, Ollama
  • Native MCP integration for accessing thousands of pre-built tools
  • Multi-agent orchestration with autonomous workflows and streaming support
  • Python decorator-based custom tool creation with hot-reloading from directories
  • TypeScript SDK and WebAssembly bindings for cross-language agent interoperability

Use Cases

💡 Building conversational AI assistants with tool-use capabilities
💡 Creating multi-agent systems for complex task decomposition
💡 Developing RAG pipelines with integrated vector store tools
💡 Prototyping and deploying production AI agents with minimal boilerplate

Strengths & Limitations

✅ Strengths

  • • Actively maintained, recent updates
  • • High community interest (6.9k stars)
  • • Permissive open-source license (Apache-2.0)

⚠️ Limitations

  • • High issue backlog (663 open issues)

Tags

agent-framework aws multi-agent python

Categories

🤖 Agent Framework

Quick Start

Install: `pip install strands-agents strands-agents-tools`. Minimal example: `from strands import Agent; from strands_tools import calculator; agent = Agent(tools=[calculator]); agent("What is sqrt(1764)")`. Requires Python 3.10+. Configure AWS credentials or set up an alternative model provider.
Visit GitHub Visit Website

Related Projects

Hive

10.9k · Python
Active A

Hive is a production-ready multi-agent execution harness providing state management, failure recovery, observability, and human-in-the-loop control with auto-generated multi-agent topologies for complex business workflows.

multi-agentagent-frameworkproduction +3
  • · Zero-setup, model-agnostic execution harness that auto-generates multi-agent topologies for complex workflows
  • · Graph-based execution DAG for safe parallel task coordination with deterministic fault tolerance
  • · Persistent role-based memory that evolves with project context — no manual state management
View full details → View on GitHub

AgentScope

29.0k · Python
Active A+

Open-source multi-agent framework from Alibaba, enabling the construction of observable and interpretable agents with rich distributed capabilities.

agent-frameworkmulti-agentdistributed +2
  • · Built-in ReAct Agent — Create agents with reasoning and tool-use capabilities in 5 minutes
  • · Tool & Skill System — Built-in Bash, Grep, file I/O tools with custom extension support
  • · Multi-Agent Orchestration — Flexible multi-agent collaboration via Message Hub
View full details → View on GitHub

Agno

41.7k · Python
Active A

Agno is a high-performance agent framework for building multimodal AI agents with memory, knowledge, and tool-use capabilities, supporting multiple LLM providers.

agent-frameworkmulti-agentllm +1
  • · Production API — 50+ endpoints with SSE and WebSocket to build products on top
  • · 100+ pre-built tool integrations — Connect to 100+ tools via pre-built toolkits
  • · Context Providers — Access live data from Slack, Drive, wikis, MCP, and custom sources
View full details → View on GitHub

CrewAI

57.2k · Python
Active A+

CrewAI is a multi-agent framework for orchestrating role-playing, autonomous AI agents that collaborate like a team to tackle complex tasks.

multi-agentagent-frameworkrole-playing +2
  • · Role-playing agents — every agent has role, goal, backstory and a private toolset
  • · Task orchestration — express dependencies, parallelism and context handoff between tasks
  • · Autonomous collaboration loops — delegation, hierarchical and consensual processes built-in
View full details → View on GitHub

Related Articles

Agent 工程生产监控Prompt A/B 测试

Agent Canary Deployment and Production Monitoring: From Prompt A/B Testing to Automatic Rollback

How do you know a prompt change is better, not worse? A systematic guide to canary deployment, quality gates, auto-rollback architecture, and continuous behavioral drift monitoring for agents in production.

Read more →
容错工具调用重试

Agent Tool-Call Fault Tolerance: Timeouts, Retries, Fallbacks, Idempotency

A systematic guide to seven tool-call fault tolerance patterns: timeout hierarchy, exponential backoff with jitter, circuit breakers, fallback provider chains, recoverable error classification, structured validation, and idempotency keys -- keeping agents stable in unstable real-world environments.

Read more →