Plan Agent with Meta-Agent provides a layered AI agent architecture: the Plan Agent generates structured strategies to achieve high-level goals, while the Meta-Agent oversees execution, adjusts plans in real-time, and delegates subtasks to specialized sub-agents. It features plug-and-play tool connectors (e.g., web APIs, databases), persistent memory for context retention, and configurable logging for performance analysis. Users can extend the framework with custom modules to suit diverse automation scenarios, from data processing to content generation and decision support.

Agent Workflow Memory is a Python library designed to augment AI agents with persistent memory across complex workflows. It leverages vector stores to encode and retrieve relevant context, enabling agents to recall past interactions, maintain state, and make informed decisions. The library integrates seamlessly with frameworks like LangChain’s WorkflowAgent, providing customizable memory callbacks, data eviction policies, and support for various storage backends. By housing conversation histories and task metadata in vector databases, it allows semantic similarity searches to surface the most relevant memories. Developers can fine-tune retrieval scopes, compress historical data, and implement custom persistence strategies. Ideal for long-running sessions, multi-agent coordination, and context-rich dialogues, Agent Workflow Memory ensures AI agents operate with continuity, enabling more natural, context-aware interactions while reducing redundancy and improving efficiency.