Researchers behind ChatDev released ChatDev 2.0, branded DevAll, a no-code platform for building, executing, and inspecting heterogeneous LLM-based multi-agent systems. It targets the tradeoff between expressive but engineering-intensive code frameworks and easy but constrained no-code builders. For practitioners, it promises MAS authoring without writing code while retaining expressive agent interactions.
A new arXiv paper presents a mixed-method experience report on developing LLM-based multi-agent systems (MAS) for software engineering. It documents the shift from single-LLM assistance to collaborative multi-agent orchestration and highlights the practical challenges developers face. The report offers grounded insights for practitioners adopting MAS in real-world development workflows.
A new arXiv paper presents a mixed-method experience report on developing LLM-based multi-agent systems (MAS) for software engineering. It documents the shift from single-LLM assistance to collaborative multi-agent orchestration and highlights the practical challenges developers face. The report offers grounded insights for practitioners adopting MAS in real-world development workflows.
CleanSlate is an IDE that integrates an agent manager directly, allowing developers to create, manage, and switch between multiple coding agents without leaving the editor. It solves the friction of toggling between separate agent management tools and the IDE, enabling seamless context preservation and multi-agent orchestration for developers working with LLM-powered coding agents.
CleanSlate is an IDE that integrates an agent manager directly, allowing developers to create, manage, and switch between multiple coding agents without leaving the editor. It solves the friction of toggling between separate agent management tools and the IDE, enabling seamless context preservation and multi-agent orchestration for developers working with LLM-powered coding agents.
An open-source control engine for building and managing AI agents. It uses LLMs to orchestrate agent workflows, enabling developers to create autonomous systems for tasks like data processing or automation. Solves the problem of coordinating multiple AI agents in a reliable, customizable framework.
An open-source control engine for building and managing AI agents. It uses LLMs to orchestrate agent workflows, enabling developers to create autonomous systems for tasks like data processing or automation. Solves the problem of coordinating multiple AI agents in a reliable, customizable framework.
CrewAI is a multi-agent system that automates the orchestration of multiple LLM calls, eliminating the need for developers to write custom glue code. The framework handles task delegation, inter-agent communication, and workflow sequencing out of the box.
CrewAI is a multi-agent system that automates the orchestration of multiple LLM calls, eliminating the need for developers to write custom glue code. The framework handles task delegation, inter-agent communication, and workflow sequencing out of the box.
Multi-Agent System Editor is a web app that lets users design networks of LLM agents on a visual canvas instead of writing orchestration code. It runs inference on the user's own machine via a WebSocket tunnel to local Ollama, solving the problem of hard-to-change system structures in existing frameworks. It is free to register and try, currently seeking first users.
Multi-Agent System Editor is a web app that lets users design networks of LLM agents on a visual canvas instead of writing orchestration code. It runs inference on the user's own machine via a WebSocket tunnel to local Ollama, solving the problem of hard-to-change system structures in existing frameworks. It is free to register and try, currently seeking first users.