Post-Cortex

Persistent Memory for AI Assistants

Post-Cortex is an MCP server that gives AI assistants long-term memory. It stores conversations, decisions, and insights in a searchable knowledge base with automatic entity extraction.

Features

• Persistent Memory - Conversations survive across sessions
• Semantic Search - Find related content using AI embeddings with HNSW indexing
• Graph-RAG - Search results enriched with entity graph insights and relationship paths
• Knowledge Graph - Automatic entity and relationship extraction
• Privacy-First - All processing runs locally, no external APIs
• Fast - Lock-free Rust architecture, O(log n) vector search, <10ms queries
• Flexible Storage - RocksDB (embedded) or SurrealDB (distributed)

Workspace layout

This repository is a Cargo workspace of 8 publishable crates. Pick the one that matches your need — depending on the facade post-cortex pulls everything, but most consumers only want a subset:

Crate	Pick when you need…	crates.io
post-cortex	The full stack in one dep
post-cortex-core	Domain types + traits only (no I/O, no ML)
post-cortex-proto	gRPC wire types (client-side)
post-cortex-embeddings	BERT embedder + HNSW vector DB
post-cortex-storage	RocksDB + SurrealDB backends
post-cortex-memory	ConversationMemorySystem orchestrator
post-cortex-mcp	MCP tool functions (embed in any MCP host)
post-cortex-daemon	pcx CLI + rmcp/axum/tonic server

Dependency graph (acyclic):

post-cortex-proto ──► post-cortex-core ──► post-cortex-embeddings
                            │                      │
                            ▼                      ▼
                     post-cortex-storage ──► post-cortex-memory ──► post-cortex-mcp
                                                    │                      │
                                                    └──► post-cortex-daemon
                                                              │
                                                              ▼
                                                       post-cortex (facade)

post-cortex-core carries no transport / I/O / ML dependencies — downstream Rust projects can take it for the type system alone without dragging in RocksDB, Candle, or the server stack.

Installation

# Homebrew (macOS/Linux)
brew install julymetodiev/tap/post-cortex

# Or download binary
curl -L https://github.com/julymetodiev/post-cortex/releases/latest/download/pcx-aarch64-apple-darwin -o /usr/local/bin/pcx
chmod +x /usr/local/bin/pcx

Quick Start

1. Configure MCP (once, globally)

# HTTP transport (recommended, requires daemon running)
claude mcp add --scope user --transport http post-cortex http://127.0.0.1:3737/mcp

# Or stdio transport (no daemon needed)
claude mcp add --scope user --transport stdio post-cortex -- pcx

This registers Post-Cortex for all projects on your machine.

2. Set Up Your Project

pcx setup

This creates a session, workspace, CLAUDE.md with memory rules, hooks for enforcement, and installs agent definitions. See Usage Guide for details.

3. Start Coding

claude

Claude will automatically search past knowledge before answering and log new discoveries.

MCP Tools

Daemon Mode

For multiple Claude instances sharing the same memory:

pcx start    # Start daemon
pcx status   # Check status
pcx stop     # Stop daemon

Configure Claude for HTTP transport:

{
  "mcpServers": {
    "post-cortex": {
      "type": "http",
      "url": "http://localhost:3737/mcp"
    }
  }
}

See Daemon Mode docs for details.

Data Export/Import

pcx export --output backup.json       # Full export
pcx export --output backup.json.gz    # Compressed
pcx import --input backup.json        # Import

Storage Backends

Configure in ~/.post-cortex/daemon.toml. See Daemon Mode docs.

Environment Variables

Development

cargo build --release --features "embeddings,surrealdb-storage"
cargo test
cargo bench

License

MIT