Build AI Agents, Visually

DeepResearchAgent is a hierarchical multi-agent system designed not only for deep research tasks but also for general-purpose task solving. The framework leverages a top-level planning agent to coordinate multiple specialized lower-level agents, enabling automated task decomposition and efficient execution across diverse and complex domains.

Must-read Papers on LLM Agents.

The Open Source Memory Layer For Autonomous Agents

Build, run and scale AI agents like API and microservices - observable,auditable and identity-aware from day one.

Agentic AI Hedge Fund OS (AIMM)

DATAGEN: AI-driven multi-agent research assistant automating hypothesis generation, data analysis, and report writing.

A selection of state-of-the-art research materials on trajectory prediction

For your multi-agent needs

SMAC: The StarCraft Multi-Agent Challenge

🦠 Simulator for a particle system showing life-like behaviour.

A Multi-Agent Reinforcement Learning Environment for Large Scale City Traffic Scenario

Open-source alternative to Claude Agent SDK, ChatGPT Agents, and Manus.

Building LLM-Enabled Multi Agent Applications from Scratch

freephdlabor: customizing personalized multiagent systems that researchs 24/7 on your own scientific problem

🔥🔥🔥 ICLR 2025 Oral. Automating Agentic Workflow Generation.

Finetune any multiagent system on any task w/ MAPPA

Golang SDK for A2A Protocol

Benchmark for automated failure attributions in agentic systems (🏆 ICML 2025 Spotlight)

Smart Python Agent Development Environment