Exocortex

Created at a month ago

by fuwasegu

starstarstarstarstar

xocortex — an MCP server that gives your AI persistent memory across ALL your projects. • Semantic search recalls past solutions by meaning • Knowledge graph connects related insights • 100% local, no API keys Went deep into cognitive science for this: 🔥 Frustration Indexing (Somatic Marker Hypothesis) → Painful debugging sessions get PRIORITY recall. Those 3-hour bugs? Never forgotten. 😴 Sleep/Dream Mechanism → Background consolidation links & deduplicates memories. Like how human sleep organizes memory. Tech stack: • MCP (Cursor/Claude native) • KùzuDB (graph + vector in one embedded DB) • fastembed (local embeddings)

Categories

research-and-data

Tags

mcp

ai-memory

knowledge-graph

What is Exocortex?

Exocortex is a local MCP (Model Context Protocol) server designed to serve as a developer's "second brain," providing persistent memory across all projects. It allows AI assistants to retrieve contextually relevant memories, enhancing productivity and knowledge management.

How to use Exocortex?

To use Exocortex, clone the repository from GitHub, install dependencies, and start the server. Configure your AI assistant (like Cursor) to connect to the Exocortex server for memory retrieval and storage.

Key features of Exocortex?

  • Fully local data storage ensuring privacy.
  • Semantic search capabilities for finding memories by meaning.
  • A knowledge graph that maintains relationships between insights.
  • Frustration indexing to prioritize painful debugging memories.
  • Automatic memory consolidation and pattern recognition.

Use cases of Exocortex?

  1. Storing and recalling technical decisions across multiple projects.
  2. Enhancing debugging processes by recalling past solutions.
  3. Facilitating cross-project knowledge sharing and learning.

FAQ from Exocortex?

  • Is Exocortex secure?

Yes, all data is stored locally, ensuring privacy and security.

  • Can I use Exocortex with multiple projects?

Yes, Exocortex is designed for cross-project knowledge sharing.

  • How does frustration indexing work?

It prioritizes memories associated with painful debugging experiences to help avoid repeating mistakes.

View More