SkyworkAI/DeepResearchAgent
A hierarchical multi-agent system built on LLM-based agents with self-evolution protocol for deep research and general-purpose task solving.
DeepResearchAgent is a self-evolution protocol and runtime for LLM-based agent systems. It decouples resource management (RSPL layer) from evolution logic (SEPL layer), modeling prompts, agents, tools, environments, and memory as versioned protocol-registered resources. The system implements an iterative Act-Observe-Optimize-Remember loop where agents produce actions using LLMs, capture outcomes, update via optimizers like reflection or RL-style methods, and persist insights to memory. It supports dynamic tool-calling, environment interaction (filesystem, trading, browser/mobile), and hierarchical coordination of specialized agents.
Frequently asked
- What is SkyworkAI/DeepResearchAgent?
- A hierarchical multi-agent system built on LLM-based agents with self-evolution protocol for deep research and general-purpose task solving.
- Is DeepResearchAgent open source?
- Yes — SkyworkAI/DeepResearchAgent is open source, released under the MIT license.
- What language is DeepResearchAgent written in?
- SkyworkAI/DeepResearchAgent is primarily written in Python.
- How popular is DeepResearchAgent?
- SkyworkAI/DeepResearchAgent has 3.5k stars on GitHub.
- Where can I find DeepResearchAgent?
- SkyworkAI/DeepResearchAgent is on GitHub at https://github.com/SkyworkAI/DeepResearchAgent.