Awesome AI AgentsAI Agent Development

OpenHands/software-agent-sdk

⭐ 1104 Python repository created 2025-08-23

The OpenHands Software Agent SDK is a set of Python and REST APIs for building agents that operate on codebases. It targets three kinds of work: one-off tasks such as writing a README for a repository, routine maintenance such as updating dependencies, and larger multi-agent efforts such as refactors and rewrites. The core programming model is small. A developer configures an LLM object with a model name and API key, constructs an Agent with a list of tools, and opens a Conversation bound to a workspace directory; messages are sent to the conversation and the run method drives the agent loop. Bundled tools include a terminal, a file editor and a task tracker, and custom tools can be registered alongside them. Agents can use the local machine as their workspace or run inside ephemeral workspaces in Docker or Kubernetes through the Agent Server, which exposes a REST and WebSocket interface for client-server deployments. The SDK is the engine behind the OpenHands CLI and OpenHands Cloud, so it is also intended as a foundation for building new developer-facing agent products. A skills and plugins system lets agents load reusable guidance: enabling public skills through AgentContext pulls in the OpenHands extensions marketplace, which ships skills for modern package tooling such as uv and deno, and agents pick those up automatically when a repository shows markers like uv.lock or deno.json. The examples directory is organised by scenario, covering standalone SDK usage, the remote agent server, GitHub CI workflows, and skills and plugins. Documentation covers getting started, architecture and core concepts, guides for custom tools and MCP integration, and an agent server API reference. The project is MIT licensed, has an accompanying technical report on arXiv, and reports a SWE-Bench score of 77.6.

https://github.com/OpenHands/software-agent-sdk

agent-sdkcoding-agentspythonopenhandsagent-servertoolsmcp

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.