Research Foundation

Our research agenda is driven by a practical goal: making AI assistants more affordable, more reliable, and genuinely useful across industries. We pursue three interconnected research directions that together form a comprehensive approach to building production-grade AI systems.

AI Agent Architecture

We research agent architectures designed to make AI copilots and generative assistants both more cost-effective and more reliable. Our core concept is the agent as a recursive orchestrator of skills: the orchestration itself can be guided by prompts or code, while skills are simply prompts or tools the assistant can invoke. This modular, composable approach enables sophisticated behaviors while keeping systems maintainable and predictable.

Specification-Driven R&D

We believe rigorous specification management is the key to unlocking AI's creative potential. Our research transforms AI into a true compiler from specifications to artifacts: code, diagrams, research theories, articles, novels, images, films, and any other creative output. By keeping specifications clear, traceable, and versioned, we enable reproducible, auditable AI-assisted creation across every domain, from software engineering to scientific research to artistic production.

Trustworthy AI Research

We investigate neurosymbolic solutions to address the fundamental challenges of trustworthy AI: the opacity of results, bias in training data, and the hallucinations that prevent adoption in highly regulated industries. Built around AGISystem2, our research has produced tangible results: working systems for knowledge representation and formal, verifiable reasoning that can explain their conclusions and guarantee logical consistency.

Agents Under Study for Integration

Beyond our own agent development, we actively study and evaluate open-source AI agents for potential integration as Ploinky Agents. Our goal is to identify tools that complement the AssistOS ecosystem and can be adapted to work within our secure, sandboxed workspace model.

Open Interpreter — github.com/OpenInterpreter/open-interpreter
OpenHands CLI — interactive coding agent with browser and terminal access
Agent Laboratory — autonomous research agent for end-to-end scientific workflows
The AI Scientist — automated paper writing and research generation
OpenCode — open-source AI coding assistant
DeepAnalyze — automated deep data analysis agent
PandasAI — conversational data analysis with pandas
Agentic Data Scientist — autonomous data science pipeline agent
MLJAR — automated machine learning with explainable models
LIDA — automatic data visualization and infographic generation
AutoML Agent — bohrium.com / github.com/deepauto-ai/automl-agent

Each of these agents is evaluated for compatibility with Ploinky's sandbox model, MCP tool integration potential, and alignment with AssistOS's specification-driven workflow. We welcome contributions from the maintainers of these projects and from researchers who want to help adapt them for the AssistOS ecosystem.