Awesome AI AgentsAI Agent Orchestration

langchain-ai/open-swe

⭐ 10710 TypeScript added to this list on 2025-08-10 repository created 2025-05-21

Open SWE is an open-source asynchronous coding agent designed to autonomously understand, plan, and execute code changes across entire codebases. Built with LangGraph, it operates in a cloud-based sandbox environment, enabling parallel execution of multiple tasks without limitations. The agent features a dedicated planning step that deeply analyzes complex codebases and tasks, allowing users to accept, edit, or reject the proposed plans before execution. It supports human-in-the-loop interaction, enabling real-time feedback and instructions during both planning and execution phases without interrupting the process. Open SWE manages tasks end-to-end by automatically creating GitHub issues and corresponding pull requests that close the issues upon completion. Users can interact with Open SWE through a web application UI or directly from GitHub by labeling issues to trigger tasks, with options for automatic plan acceptance and enhanced performance using advanced language models like Claude Opus 4.1. The project provides comprehensive documentation and a public demo, requiring users to set their own LLM API keys. Open SWE aims to streamline and automate coding workflows, making it easier to manage and implement code changes efficiently across repositories.

https://github.com/langchain-ai/open-swe

agentagentsaianthropicasynchronous-coding-agentautomationclaude-opus-4.1claudecodecloud-basedcode-executioncodebase-understandinggithub-integrationgithub-issueshuman-in-the-looplanggraphllmllm-apillmsopen-sourceopenaiparallel-executionplanningpull-requestssandbox-environmenttask-management

Also in AI Agent Orchestration

ruvnet/claude-flow

Claude-Flow is an enterprise-grade AI orchestration platform that enables deployment and coordination of intelligent multi-agent swarms and autonomous workflows for building advanced conversational AI systems.

code-yeongyu/oh-my-openagent

Oh-My-OpenAgent (OmO) is an advanced AI agent harness designed for complex codebases, orchestrating various AI models like Codex and OpenCode for software engineering tasks.

herdrdev/herdr

Herdr is an agent multiplexer that provides a runtime environment for coding agents directly within your terminal, offering a comprehensive view of agent activities and persistent sessions.

BloopAI/vibe-kanban

Vibe Kanban is a Kanban board tool designed to manage and orchestrate AI coding agents, enabling efficient task tracking and workflow optimization in AI-assisted software development.

Donchitos/Claude-Code-Game-Studios

Transforms Claude Code into a comprehensive game development studio powered by 49 AI agents, 73 workflow skills, and a hierarchical coordination system for structured game creation.

NVIDIA/NemoClaw

NVIDIA NemoClaw is an open-source reference stack enabling the secure and sandboxed operation of AI agents like OpenClaw and Hermes within NVIDIA OpenShell environments, offering managed inference ...

NirDiamant/agents-towards-production

Agents Towards Production is an open-source repository offering end-to-end tutorials and blueprints for building scalable, production-grade Generative AI agents from concept to deployment.

elizaOS/eliza

Eliza is a versatile AI agent operating system that enables the creation and deployment of autonomous agents across multiple platforms with extensible features and document interaction capabilities.