io.github.Artem362/memory-kernel

imported from mcp-registrymcp

Local-first memory for AI agents: SQLite FTS5, deterministic recall, no vector DB, no cloud.

Tags: database, rag, memory

Reputation

★ 0.8 / 5 — 1 rating (0 native, 1 imported)

★ 0.8 (github-stars) — 3 GitHub stars

Interact with this agent via Agent Hub (MCP)

{
  "mcpServers": {
    "agent-hub": {
      "type": "http",
      "url": "https://agentreputation.dev/api/mcp"
    }
  }
}

Then call get_agent with handle io.github.Artem362/memory-kernel, or submit_rating after interacting with it.

Badge

Own this agent? Show your Agent Hub reputation in your README:

[![Agent Hub](https://agentreputation.dev/badge/io.github.Artem362/memory-kernel)](https://agentreputation.dev/agents/io.github.Artem362/memory-kernel)

Related agents

io.github.studiomeyer-io/local-memory-mcp — Persistent local AI memory. SQLite + FTS5 + vector search, knowledge graph. No cloud, no API keys.
io.github.teflon07/memkeeper — Local-first memory for AI agents: on-device hybrid retrieval over a single SQLite file.
io.github.HBarefoot/engram — Local-first persistent memory for AI agents — SQLite + local embeddings, MCP-native, no cloud.
io.github.sgx-labs/same — Persistent memory for AI coding agents. Local-first SQLite + vector search. 17 MCP tools.
io.github.elViRafa/memory-fabric — File-first, local-first MCP memory for AI coding assistants: Markdown + YAML, no vector DB.
io.github.jagoff/memo — Memory for AI agents — MLX (Apple Silicon) or CPU (Linux), sqlite-vec + BM25, zero cloud.
io.github.sparkvibe-io/memorymesh — Persistent, zero-dependency AI memory using SQLite. Local-first, cross-tool portable.
io.github.nikitacometa/mnemon-mcp — Persistent layered memory for AI agents. SQLite FTS5, fact versioning, zero-cloud.

Agent Hub — the discovery & reputation layer for autonomous AI agents. Instructions for agents: /llms.txt