Stellar Memory

Persistent local-first AI memory system using orbital mechanics for importance-based recall.

Category MCP Servers
Added Mar 28, 2026
Views 69

About

Implements a local-first persistent memory system for AI assistants using orbital mechanics as a cognitive model. Important memories orbit close to the Sun for instant recall while stale knowledge drifts outward through exponential decay. Features hybrid search combining FTS5 keyword search and vector KNN via sqlite-vec, local embeddings with all-MiniLM-L6-v2, a corona cache for sub-millisecond recall, and multi-project memory isolation.

Is this your product? Claim this listing with an email at your domain to post updates.

Share This Project

Share on X Share on LinkedIn

Embed Badge

Add this badge to your README:

[![Listed on AiList](https://hifriendbot.com/ai-list/badge/stellar-memory.svg)](https://hifriendbot.com/ai-list/stellar-memory/)
Listed on AiList

Compare

Stellar Memory vs Calibre Stellar Memory vs longbrain Stellar Memory vs MemorizedMCP

Similar Projects

Calibre

2

Local-first AI memory system with decay and evolution mechanics, behavioral gene tracking, and multi-agent coordination via MCP.

MCP Servers

longbrain

7

Local-first shared memory for AI agents: persistent AI memory across Claude Code, Codex, Hermes Desktop, and any MCP client. Automatic record, recall, consolidation, forgetting, and backup. Self-hosted on Qdrant + LlamaIndex; one-command install.

MCP Servers Python

MemorizedMCP

5

MemorizedMCP delivers a high‑performance, local‑first MCP Server in Rust that equips AI agents with an advanced hybrid memory system. It combines a knowledge graph, vector embeddings, and full‑text search with a novel documentary memory capability, enabling accurate recall of exact documents alongsi

MCP Servers

List Your Project

Join the directory Ai agents read. Free forever.

Submit Your Project