AutoGPT is an open-source platform for building, running, and scheduling AI agents that carry out multi-step workflows from plain-English descriptions or a visual builder.
victordibia/designing-multiagent-systems
Companion code for the book Designing Multi-Agent Systems, centered on PicoAgents, a multi-agent framework built from scratch for teaching.
- Звёзды
- 1,366
- Форки
- 0
- Открытые issues
- 0
- Последний коммит
- 2 месяца назад
Ключевые возможности
- 01Single-agent framework with tools, memory, streaming, and human-in-the-loop approval
- 02Playwright-based browser automation agents with vision-model reasoning
- 03Type-safe workflow engine with streaming observability
- 04Round-robin, LLM-driven, and plan-based multi-agent orchestration
- 05LLM-as-judge and reference-based evaluation framework
- 06Web UI with auto-discovery of agents and workflows, launched via a CLI command
Сценарии использования
- Learning how multi-agent systems work from first principles
- Prototyping agent applications with OpenAI, Anthropic, or local OpenAI-compatible models
- Comparing orchestration patterns across PicoAgents, LangGraph, and Google ADK
- Building a software engineering or data analysis agent using the included examples
Темы
Частые вопросы
- Что такое designing-multiagent-systems?
- Companion code for the book Designing Multi-Agent Systems, centered on PicoAgents, a multi-agent framework built from scratch for teaching.
- designing-multiagent-systems можно использовать бесплатно? Какая у него лицензия?
- designing-multiagent-systems распространяется с открытым исходным кодом под лицензией Apache-2.0. Перед использованием в коммерческих продуктах проверьте условия лицензии.
- designing-multiagent-systems всё ещё поддерживается?
- Обновлялся за последние 6 месяцев. Последний коммит в designing-multiagent-systems — 24 авг. 2026 г..
- Для чего можно использовать designing-multiagent-systems?
- Learning how multi-agent systems work from first principles Prototyping agent applications with OpenAI, Anthropic, or local OpenAI-compatible models Comparing orchestration patterns across PicoAgents, LangGraph, and Google ADK Building a software engineering or data analysis agent using the included examples
- Где скачать designing-multiagent-systems?
- Исходный код и инструкции по установке — на GitHub: https://github.com/victordibia/designing-multiagent-systems
Описание создано ИИ на основе README проекта. Статистика GitHub обновляется ежедневно.
Похожие проекты
A Python framework and runtime for building, serving, and managing AI agent platforms, with a web UI for administration.
An open-source agent runtime and terminal app for long-horizon research and file-based work, with ReAct and parallel Agent Team modes.
A Python library and runnable Jupyter textbook implementing 35 agentic AI architectures, from Reflexion and ReAct to MemGPT and BrowserAgent, on LangGraph.
A framework for autonomous Android and computer use, letting an LLM plan and execute UI tasks with local or remote models.
A curated Awesome list of resources, patterns, and templates for designing the scaffolding around AI agents: tools, memory, MCP, permissions, evals, and orchestration.