memoryweb
Related Servers
Alternatives to memoryweb
- AlicenseAqualityAmaintenancePersistent memory for AI agents with sectioned entries (project/user/context/etc), semantic search, CLI, and per-project scope. Local JSON, zero config, no server required.12108 PyPI4MIT
- AlicenseNot gradedqualityDmaintenanceA local AI memory system that stores all conversations verbatim and organizes them into navigable structures. It provides 19 MCP tools for AI assistants to search and retrieve past decisions, debugging sessions, and architecture debates automatically.MIT
- AlicenseAqualityAmaintenanceCognitive memory engine for AI agents with 5,100+ knowledge modules, circadian rhythm awareness, emotional state tracking (PAD model), and hybrid semantic search. Supports persistent per-user memory, project-scoped contexts, and multi-protocol access.2623Apache 2.0
Related Servers
- AlicenseAqualityCmaintenanceMCP server providing persistent memory for AI agents, enabling them to read, write, and query memories across sessions.917 npmMIT
- AlicenseNot gradedqualityCmaintenanceAn MCP server that lets coding agents build and query a persistent knowledge graph of concepts, architecture, and decisions, enabling them to remember across sessions.194 npm564MIT
- AlicenseNot gradedqualityCmaintenancePersistent memory infrastructure for AI agents, enabling cross-session recall and autonomous memory evolution via an MCP server.1MIT
- AlicenseNot gradedqualityCmaintenanceMCP server that gives AI agents persistent long-term memory, storing and recalling facts, decisions, errors, procedures, and episodes across sessions.20 npm3Apache 2.0
- FlicenseNot gradedqualityCmaintenanceA self-hosted MCP server that gives AI agents persistent, searchable memory with importance scoring, knowledge graphs, and autonomous memory consolidation.1-
- AlicenseNot gradedqualityBmaintenanceMCP server providing persistent AI memory with four-tier retrieval (SQLite FTS5, graph, vector, LLM agent) to give AI assistants structured, long-term memory without RAG.1Apache 2.0
TDQS
Scored across 18 tools
Most tools have distinct purposes (remember, search, recall, connect, disconnect, audit, orient, history, significance, domains, visualise), but remember/revise/forget/forget_all/restore_all overlap somewhat in the memory lifecycle space, and connect/disconnect/disconnect_all/why_connected form a cluster that could confuse. The descriptions are detailed enough to mostly disambiguate, but the batch variants (forget_all, restore_all, disconnect_all) and single variants create some boundary ambiguity.
The naming is a mix of bare verbs (remember, recall, search, orient, audit, connect, disconnect, forget, revise, history, domains, visualise) and verb_verb or verb_noun compounds (forget_all, restore_all, disconnect_all, suggest_connections, why_connected). There's no consistent verb_noun pattern; some are single-word verbs, some are imperative phrases. The naming is readable and mostly intuitive, but the convention is inconsistent across the set.
18 tools is on the higher end but appropriate for a memory/knowledge graph server that needs CRUD for nodes, edges, search, audit, orientation, and visualization. Each tool serves a distinct function in the memory lifecycle, though the batch variants (forget_all, restore_all, disconnect_all) could arguably be folded into their single counterparts.
The tool surface covers the full memory lifecycle: create (remember), read (search, recall, orient, history, significance, why_connected), update (revise), delete/archive (forget, forget_all, restore_all), connection management (connect, disconnect, disconnect_all, suggest_connections), health/audit (audit), domain administration (domains), and visualization (visualise). No obvious dead ends or missing operations for a memory graph server.