Authors: Sumers et al.
CoALA provides a unified cognitive architecture for language agents, drawing from decades of cognitive science research. It defines four memory systems that work together to enable sophisticated agent behavior: working memory for active tasks, episodic memory for experiences, semantic memory for facts, and procedural memory for skills.
Awareness directly implements CoALA's 4-tier structure:
**Working Memory** → Task-focused ephemeral storage - Current task description - Scratchpad for reasoning - Active context summary - Pending action items
**Episodic Memory** → Experience-based retrieval - Full conversation history - Tool execution results - State snapshots at turn boundaries - Retrieved by recency + importance + relevance
**Semantic Memory** → Fact-based knowledge - Extracted facts from conversations - Entity definitions and relationships - Long-term knowledge storage - Retrieved by semantic similarity
**Procedural Memory** → Skill-based execution - Learned workflows and patterns - Tool usage patterns - Successful solution templates - Invoked by task type matching
interface CoALAMemory {
working: {
currentTask: string;
scratchpad: Record<string, unknown>;
activeContext: string;
};
episodic: ConversationMessage[];
semantic: ExtractedFact[];
procedural: LearnedSkill[];
}Core memory tier system design - defines our memory taxonomy
Virtual context management, heartbeat mechanism, OS-inspired memory paging
Importance scoring algorithm for memory retrieval, reflection mechanism
Two-phase memory pipeline, conflict resolution (ADD/UPDATE/DELETE/NOOP), graph-enhanced variant