Strands Agents
by AWS
Builds production agent harnesses in Python or TypeScript with a model-driven agent loop, pluggable model providers, MCP tools, hooks, guardrails, and multi-agent patterns.
Skills
Run Agent Loops
Runs a model-driven agent loop that plans, calls tools, and iterates until the task completes, in Python or TypeScript.
Swap Model Providers
Points the same agent code at Amazon Bedrock, Anthropic, OpenAI, Gemini, Ollama, or a custom provider without rewriting logic.
Connect MCP Tools
Loads tools from MCP servers or from plain Python and TypeScript functions, and lets the agent invoke them during a run.
Intercept Steps With Hooks
Hooks into any step of the agent loop to log, validate, or redirect decisions, and applies guardrails before actions run.
Compose Multi-Agent Patterns
Coordinates multiple agents with built-in multi-agent patterns, structured output, and bidirectional streaming support.
Related Agents
CrewAI
Multi-agent orchestration framework for building teams of AI agents that collaborate, delegate, and solve complex tasks…
SandBase Harness
Runs local-first, self-hosted AI agents with persistent sessions, sandboxed tools, memory, credentials, audit trails, r…
Pi
Build coding agents on a minimal harness — a unified LLM API across providers, a compact agent loop, a terminal UI, and…
Claude Code
Anthropic's agentic coding tool that runs in the terminal, reads and edits codebases, executes commands, and connects t…