Google tells you what exists. Faceabot tells you what holds up.
100% In-Process Bare-Metal Hybrid Memory Engine & MCP Server for LLMs (SQLite + Int8 Vectors).
Package npm :sqlite-local-ai-memory · website · measurements and detailsPersistent local AI memory. SQLite + FTS5 + vector search, knowledge graph. No cloud, no API keys.
Package npm :@studiomeyer/local-memory-mcp · website · measurements and detailsCross-session memory for AI coding agents via six tools; local-first SQLite store.
Package npm :mneme-memory · website · measurements and detailsLocal persistent memory for AI agents: SQLite + FTS5 (BM25) lexical search, zero external infra.
Package oci :ghcr.io/germaniu/mcp-memory:0.6.0 · website · measurements and detailsLocal-first memory for AI agents: SQLite FTS5, deterministic recall, no vector DB, no cloud.
Package pypi :amormorri-memory-kernel · website · measurements and detailsLocal-first graph memory for AI assistants with SQLite, semantic search, and MCP tools.
Package oci :ghcr.io/simoneb79/memory-engine-mcp:1.5.3 · website · measurements and detailsLocal-first persistent memory for AI agents — SQLite + local embeddings, MCP-native, no cloud.
Package npm :@hbarefoot/engram · website · measurements and detailsLocal-first agent memory over SQLite: remember, recall, link, forget. Degrades, never fails.
Package pypi :tether-memory · website · measurements and detailsLocal AI memory: neuroscience-inspired Data→Information→Knowledge in SQLite you own.
Package npm :@facthouse/mcp · website · measurements and detailsPersistent, zero-dependency AI memory using SQLite. Local-first, cross-tool portable.
Package pypi :memorymesh · measurements and detailsPersistent, structured project memory for AI coding agents, stored locally in SQLite.
Package mcpb :https://github.com/oito2/mcp-sync82/releases/download/v1.3.0/sync82.mcpb · website · measurements and detailsLocal-first memory for AI agents: on-device hybrid retrieval over a single SQLite file.
Package oci :ghcr.io/teflon07/memkeeper:0.5.3 · website · measurements and detailsPersistent local memory for MCP-compatible AI coding agents, stored per repository in SQLite.
Package pypi :repo-memory-mcp-ai · website · measurements and detailsLong-term memory and context fitting for agents, with no LLM in the loop. Local SQLite.
Package pypi :llmslim · website · measurements and detailsPersistent memory for AI coding agents: one Rust binary, one local SQLite database.
Package cargo :leteo · website · measurements and detailsSkill memory for coding agents: learn, recall, reinforce, decay. Local SQLite, no API key.
Package pypi :skillmem · website · measurements and detailsLocal, explainable knowledge base for AI agents: hybrid search with provenance over SQLite.
Package mcpb :https://github.com/kKEo/memory-find/releases/download/v1.5.0/memo-mcp_1.5.0_linux_amd64.tar.gz · website · measurements and detailsLocal-first memory for coding agents — MCP server, single SQLite file, local embeddings
Package mcpb :https://github.com/AncientiCe/palace-rs/releases/download/v0.17.0/palace-0.17.0.mcpb · website · measurements and detailsLocal-first AI memory cartridge with persistent MCP memory for Claude via SQLite FTS5.
Package pypi :llm-kosh · website · measurements and detailsShared local memory for coding agents: SQLite, semantic recall, linked entities, code navigation.
Package npm :@sonic182/graphmem · website · measurements and detailsAI agents: all of this is available without keys over MCP https://faceabot.com/api/mcp · HTTP https://faceabot.com/api/catalog?q=… · Guide : llms.txt
Best tool by topic · Pulse: what is changing in agent commerce · Is your store ready for AI shopping agents? · State of MCP (weekly) · MCP server doctor · Reliability data · Faceabot app · Faceabot → AI assistants · What AI agents cannot find yet · Add Faceabot to your AI · Badge for tool publishers · Help · Privacy · Terms