DeepResearchAgent
NormalDescription
DeepResearchAgent is a hierarchical multi-agent system designed for deep research tasks and general-purpose problem solving, using a top-level planning agent to coordinate specialized sub-agents for automated task decomposition and efficient cross-domain execution.
Key Features
- Hierarchical multi-agent system with top-level planning agent coordinating specialized sub-agents
- RSPL protocol layer modeling prompts, agents, tools, environments, and memory as versioned resources
- SEPL self-evolution protocol for proposing, assessing, and committing improvements with rollback support
- Act-Observe-Optimize-Remember iterative loop enabling continuous self-improvement during execution
- Composable architecture allowing add/replace of agents, tools, environments, and optimizers independently
- Structured tracing and versioning for inspectable reasoning trajectories and artifact management
Use Cases
💡 Conduct automated deep research tasks requiring multi-step reasoning and cross-domain knowledge
💡 Build self-evolving AI systems that improve their prompts and strategies through experience
💡 Execute complex problem-solving workflows with automatic task decomposition and agent coordination
💡 Develop research agents that persist insights and learn from previous session outcomes
Categories
Quick Start
Install dependencies in your Python environment. Copy `.env.template` to `.env` and set your model API key (e.g. `OPENROUTER_API_KEY`). Run: `python examples/run_tool_calling_agent.py --config configs/tool_calling_agent.py`. Override model with `--cfg-options model_name=openrouter/gpt-4o`.