OpenMemory and cortexgraph
About OpenMemory
CaviraOSS/OpenMemory
Local persistent memory store for LLM applications including claude desktop, github copilot, codex, antigravity, etc.
Provides multi-sector memory (episodic, semantic, procedural) with temporal reasoning and composite scoring—not just vector retrieval—via self-hosted SQLite/Postgres backends. Offers both embedded SDKs (Python/Node) and a centralized server exposing HTTP API, MCP protocol, and dashboard, with source connectors for GitHub, Notion, Google Drive, and web crawling to populate long-term agent context.
About cortexgraph
prefrontal-systems/cortexgraph
Temporal memory system for AI assistants with human-like forgetting curves. All data stored locally in human-readable formats: JSONL for short-term memory, Markdown (Obsidian-compatible) for long-term. Memories naturally decay unless reinforced. Features knowledge graphs, smart prompting, and MCP server integration for Claude.
Implements a novel temporal decay algorithm combining recency, frequency, and importance scores (with configurable half-life and sub-linear weighting) to determine when memories fade or promote to long-term storage. Operates as an MCP server with dual storage backends (JSONL for git-friendly defaults, SQLite for scale) and includes a multi-agent consolidation pipeline for automated knowledge graph construction from short-term memories.
Related comparisons
Scores updated daily from GitHub, PyPI, and npm data. How scores work