total-agent-memory
Related Servers
Alternatives to total-agent-memory
No user-submitted related servers found.
Related Servers
- AlicenseAqualityAmaintenancePersistent memory for AI coding agents, storing decisions, bug fixes, conventions, and discoveries in a local SQLite database and automatically recalling them when relevant. Works with Claude Code, Codex, Cursor, Gemini CLI, and other MCP-compatible agents.222MIT
- AlicenseNot gradedqualityBmaintenancePersistent memory for AI coding agents that stores and recalls preferences, decisions, and conventions via semantic similarity, with zero cloud dependencies and plug-and-play MCP integration for Claude Code.Apache 2.0
- AlicenseAqualityDmaintenanceGives Claude Code, Claude Desktop, Cursor, VS Code Copilot, and other MCP-compatible tools persistent memory.1853 npm1MIT

Memcellofficial
AlicenseNot gradedqualityBmaintenanceLiving memory for AI coding agents (Claude Code, Cursor, Copilot, Codex). Cross-vendor persistent memory, decision recall, and outcome calibration via MCP and hooks.1,299 npmApache 2.0- FlicenseNot gradedqualityBmaintenanceLocal-first memory for AI coding agents. Indexes your Claude Code, Codex, Cursor, Cline and Gemini CLI history by repo/branch/worktree and hands a context capsule (decisions, touched files, next steps) to the next agent over MCP.-
- AlicenseNot gradedqualityAmaintenanceEnables AI coding agents to maintain persistent, cross-session memory of codebase architecture, naming conventions, and decisions through MCP tools. Eliminates repetitive project re-explanation by automatically injecting stored context into every session with local-first SQLite storage and optional team sharing capabilities.4MIT
TDQS
Scored across 77 tools
Many retrieval tools overlap heavily (memory_recall, memory_search_fast, memory_associate, memory_recall_iterative, memory_context_build, memory_answer, memory_temporal_query) and save variants blur (memory_save vs memory_save_fast vs memory_observe vs memory_episode_save). Descriptions add nuance, but an agent can easily misselect among these clusters.
Nearly all names use snake_case and many carry domain prefixes (memory_, kg_, workflow_, self_), but conventions are mixed: prefix_noun (memory_save), verb_noun (save_intent, classify_task), and bare verb/noun (analogize, benchmark, file_context). Still readable, but not a predictable pattern throughout.
77 tools is far beyond a well-scoped memory server; many are eval, debug, perf, or internal admin utilities that could be consolidated. This creates severe surface bloat and high selection cost.
Core lifecycle is well covered: save/update/delete/recall/history/export/forget/consolidate plus graph, episodes, skills, rules, and sessions. Minor gaps exist (e.g., no explicit import counterpart to export, some tools are eval/admin rather than user-facing memory operations), but core workflows have no dead ends.