Crate ainl_memory 

AINL Memory - Graph-based agent memory substrate

Graph-as-memory for AI agents. Execution IS the memory.

AINL Memory implements agent memory as an execution graph. Every agent turn, tool call, and delegation becomes a typed graph node. No separate retrieval layer—the graph itself is the memory.

Quick Start

use ainl_memory::GraphMemory;
use std::path::Path;

let memory = GraphMemory::new(Path::new("memory.db")).unwrap();

// Record an episode
memory.write_episode(
    vec!["file_read".to_string(), "agent_delegate".to_string()],
    Some("agent-B".to_string()),
    None,
).unwrap();

// Recall recent episodes
let recent = memory.recall_recent(100).unwrap();

Architecture

AINL Memory is designed as infrastructure that any agent framework can adopt:

• Zero dependencies on specific agent runtimes
• Simple trait-based API via GraphStore
• Bring your own storage backend

Node Types

• Episode: What happened during an agent turn (tool calls, delegations)
• Semantic: Facts learned with confidence scores
• Procedural: Reusable compiled workflow patterns
• Persona: Agent traits learned over time

Re-exports

pub use node::AinlEdge;

pub use node::AinlMemoryNode;

pub use node::AinlNodeType;

pub use query::find_high_confidence_facts;

pub use query::find_patterns;

pub use query::find_strong_traits;

pub use query::recall_recent;

pub use query::walk_from;

pub use store::GraphStore;

pub use store::SqliteGraphStore;

Modules

node

AINL graph node types - the vocabulary of agent memory.

query

Graph traversal and querying utilities.

store

Graph storage backends for AINL memory.

Structs

GraphMemory

High-level graph memory API - the main entry point for AINL memory.