#779 · Primary category： AI Agents & Automation
DeepResearchAgent
Hierarchical multi-agent system for deep research and general-purpose task solving, with a planning agent coordinating specialized agents and self-evolution capabilities.
Project last updated：05/04/26
GitHub Stars
3.5K
Forks
456
Contributors
4
License
MIT
Why we included this project
Most agent frameworks run a fixed pipeline and stop; this one is built so the agent itself gets better over time. DeepResearchAgent treats prompts, tools, environments, and memory as versioned resources with explicit lifecycles, then wraps them in a closed improvement loop: the system acts, observes what happened, and proposes changes that get assessed and committed, with rollback when they don't pan out. In practice you can start with a plain tool-calling agent for research or general tasks and let reflection-based or reinforcement-style optimizers refine its behavior across sessions. The modular pieces, agents, environments, memory, optimizers, and tracing, make it a workable choice for teams that want a versioned, inspectable stack instead of hand-wired glue code.
Articles for this project
No articles for this project yet.
To suggest a topic or contribute an article, contact us.
Related projects in this category
openclaw
Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞
hermes-agent
The agent that grows with you
n8n
Fair-code workflow automation platform with native AI capabilities. Combine visual building with custom code, self-host or cloud, 400+ integrations.
deepseek-harness
DeepSeek Harness: Everything is a Plugin.
AutoGPT
AutoGPT is the vision of accessible AI for everyone, to use and to build on. Our mission is to provide the tools, so that you can focus on what matters.