post-cortex-memory 0.3.0

Conversation memory orchestrator for post-cortex. Ties storage + embeddings + graph + session + summary into a single lock-free memory hierarchy with async pipelines and a canonical PostCortexService API.

post-cortex-memory

Conversation memory orchestrator for post-cortex.

Ties post-cortex-core, post-cortex-storage, post-cortex-embeddings, and post-cortex-proto into a single lock-free memory hierarchy with async pipelines and a canonical service trait.

Install

[dependencies]
post-cortex-memory = "0.2"

What's inside

Module	Contents
`ConversationMemorySystem`	Top-level orchestrator
`MemoryServiceImpl`	Implementation of `post_cortex_core::services::PostCortexService`
`Pipeline` / `PipelineConfig`	Bounded MPSC work queues for non-blocking writes
`memory_system::*`	Session manager, storage actor, circuit breaker
`content_vectorizer::*`	Embedding ingestion + semantic search engine
`semantic_query_engine`	High-level query API over vector + storage
`query_cache`	LRU cache for repeated semantic queries
`context_assembly`	Graph-aware context retrieval
`scoring`	Relevance scoring helpers (temporal decay, composite)
`performance`	Performance metrics + monitor

Example

use post_cortex_memory::{ConversationMemorySystem, SystemConfig};

# async fn run() -> Result<(), Box<dyn std::error::Error>> {
let config = SystemConfig {
    data_directory: "./pcx-data".into(),
    ..Default::default()
};
let system = ConversationMemorySystem::new(config).await?;
let session_id = system.create_session(None, None).await?;
println!("created session {session_id}");
# Ok(()) }

Features

Feature	Default	What it enables
`embeddings`	yes	Pull the BERT backend from `post-cortex-embeddings`
`surrealdb-storage`	no	Forward to `post-cortex-storage/surrealdb-storage`
`otel`	no	OpenTelemetry exporter wiring

License

MIT — see LICENSE.