Subcog Persistent Memory

MCPOfficialOpen SourceMIT49.5

by zircote • Uncategorized

An MCP server providing persistent memory and semantic search for AI coding assistants.

Example Use Cases

1
Capture and recall coding session memories with semantic search.
2
Integration with Claude Code IDE hooks for enhanced context awareness.
3
A hybrid vector and BM25 search backend with normalized relevance scoring.

Description

Subcog is a persistent memory system designed for AI coding assistants that captures decisions, learnings, and context from coding sessions and surfaces them when relevant. It features a three-layer storage architecture combining SQLite persistence, FTS5 indexing, and usearch HNSW vectors for hybrid semantic search. Subcog integrates with AI agents via MCP server protocol and supports advanced features like knowledge graphs, entity extraction, and temporal reasoning to enhance coding workflows.

Quick Actions

View on GitHub

Security

Scanned 1 month(s) ago

Risk Level

MINIMAL

Read-only data retrieval, no side effects

Trust Score

C53/100

6/17 checks passed

Scores are informational only and provided “as is” without warranty. AgentHotspot assumes no liability for actions taken based on these ratings.

Quick Stats

Service TypeMCP

Pricing ModelFree

Capabilities0 Tools / 0 Prompts / 0 Resources

Ownerzircote

CategoryUncategorized

DependenciesStandalone