Awesome AI AgentsAI Agent Development

strands-agents/sdk-typescript

⭐ 693 TypeScript repository created 2025-09-19

The Strands Agents TypeScript SDK brings the model-driven agent approach of the Python Strands framework to JavaScript and TypeScript. Its core is a lightweight agent loop that runs in Node.js 20 or newer and in browser environments, published on npm as @strands-agents/sdk. Rather than encoding control flow as a hand-written state machine, the model itself decides which tools to call and when the task is finished, which the project positions as a way to build anything from a simple assistant to a complex workflow with a small amount of code. Tools are declared with Zod schemas, giving runtime input validation together with compile-time type inference, and the same mechanism produces structured output: a response can be constrained to a Zod schema, with automatic retries when the model returns something that fails validation. The SDK is model agnostic, shipping first-class providers for Amazon Bedrock and OpenAI while allowing custom providers through an extensible interface. Model Context Protocol client support is built in, so agents can attach to external MCP servers and use their tools without bespoke glue. Responses can be streamed token by token, lifecycle hooks allow monitoring and customisation of agent behaviour at defined points, and conversation management strategies control how history is retained and trimmed against a context window. For coordinating several agents the SDK provides graph and swarm patterns. The wider project also publishes a Python SDK, a tools package, an agent builder and an MCP server, with documentation at strandsagents.com and a samples repository. The code is Apache-2.0 licensed. Note that this repository has been archived: development, issues and pull requests moved to the strands-agents/harness-sdk monorepo, where the source now lives under the strands-ts directory.

https://github.com/strands-agents/sdk-typescript

agent-sdktypescriptmcpbedrockopenaimulti-agentzodstreamingarchived

Also in AI Agent Development

kepano/obsidian-skills

Obsidian Skills provides a collection of agent skills enabling AI agents to interact with Obsidian vaults, facilitating content creation and editing of Markdown, Bases, and JSON Canvas files, as we...

Panniantong/Agent-Reach

Agent-Reach allows AI agents to access web content from major social media and video platforms through a CLI, without API fees, enhancing their perceptual capabilities.

JCodesMore/ai-website-cloner-template

This project provides a reusable Next.js template for reverse-engineering and cloning any website into a modern codebase using various AI coding agents.

huggingface/smolagents

Smolagents is a minimalistic Python library by Hugging Face for creating intelligent agents that think and act by generating and executing Python code, supporting multiple LLMs, modalities, and tool integrations.

alibaba/page-agent

Page Agent is a JavaScript in-page GUI agent enabling natural language control of web interfaces without browser extensions or headless browsers, supporting various LLMs.

TencentCloud/TencentDB-Agent-Memory

TencentDB Agent Memory provides a local, 4-tier progressive pipeline for AI agent long-term memory, enhancing performance and reducing token usage without external API dependencies.

titanwings/distilly

A meta-skill that distills messages, documents, interviews and public sources about a person into a source-grounded Person Profile, packaged as an Agent Skill for coding agents and chat bots.

coze-dev/coze-studio

Coze Studio is an all-in-one AI agent development platform that simplifies the creation, debugging, and deployment of AI agents through visual tools and supports no-code and low-code development approaches.