Lucas Soares
Cognitive AI Systems Researcher
AI researcher and educator on YouTube and Substack with over 60,000 subscribers, specializing in cognitive agent architectures, neuro-symbolic AI, episodic memory systems, and autonomous multi-step reasoning.
Areas of focus
Professional niches
Watch Lucas Soares in Action
Proof of Work
Agentic Memory Systems and Cognitive Graph Blueprints
Created open-source Python implementations of dynamic knowledge graph generation and stateful memory reflection for autonomous research agents.
Graph schema extraction from unstructured text can generate redundant edge relations without entity reconciliation.
Context: Python, NetworkX, Neo4j, LlamaIndex, OpenAI API.
View missionCognitive Architectures for Autonomous AI Agents: Memory, Planning, and Action
Analyzed cognitive science frameworks (ACT-R, Soar) mapped to modern LLM agents, detailing episodic and semantic memory indexing for long-horizon task execution.
Memory retrieval latency increases exponentially without hierarchical vector pruning.
Context: Episodic memory, vector graph retrieval, tree-of-thought search, Claude 3.5 Sonnet.
View mission