A
licenseNot graded
qualityA
maintenanceSelf-learning memory for AI tools. Remembers user preferences and context across Claude, Cursor, and Codex with multi-parameter forgetting and cross-tool identity.
14
MIT
global-memory
by chy4pro
Related Servers
Alternatives to global-memory
No user-submitted related servers found.
Related Servers
- AlicenseNot gradedqualityAmaintenanceGives Claude Code persistent cross-session memory with semantic search, automatic detection and classification of user corrections into behavioral patterns, and self-evolving frameworks that refine judgment over time. Everything runs locally through hooks and MCP tools, with no cloud, API keys, or telemetry.6 npmMIT
- AlicenseNot gradedqualityAmaintenanceEnables Claude Code, Cursor, Codex, and Claude Desktop to carry project decisions, rules, bugs, to-dos, and failed approaches across sessions by saving them as lines in a repo file and bringing the relevant ones back on each prompt. It also checks commands and file edits against those saved rules before they run, flagging anything that might break one.236 npmMIT
- AlicenseNot gradedqualityAmaintenanceEnables Claude Code, Cursor, and Codex sessions to persist decisions, rules, bugs, to-dos, and failed approaches in a repository file and automatically recall relevant saved context in later sessions. It also checks planned commands or edits against those saved rules before they run.236 npmMIT
- -licenseNot gradedqualityNot gradedmaintenanceEnables AI assistants to maintain persistent conversations and context between sessions through automated saving and global installation across projects. Provides zero-configuration memory persistence with automatic conversation history preservation.-
- AlicenseNot gradedqualityAmaintenanceGives Claude Code persistent cross-session memory with semantic search over saved facts, decisions, and journals, alongside automatic detection and classification of user corrections as trackable behavioral patterns. It also extracts behavioral signals from sessions and evolves self-authored frameworks over time, so the assistant develops judgment that carries forward between conversations — all local, with no cloud or API key required.6 npmMIT
TDQS
A3.8/5.0
Scored across 9 tools
Disambiguation4/5
Most tools have clearly distinct roles: recall/record_usage, list/overview, and start_consolidation/apply_consolidation are well separated. The only potential confusion is between update_memory and apply_consolidation (both can modify presets) and between delete_memory and apply_consolidation's delete, but the usage context (direct user action vs. consolidation workflow) disambiguates them.
Naming Consistency4/5
Eight of nine tools follow a consistent verb_noun pattern (record_usage, list_memories, update_memory, start_consolidation, apply_consolidation, recall_presets, save_requirement, delete_memory). memory_overview breaks the pattern by being noun_noun, but it is still readable and clearly the odd one out.
Tool Count5/5
Nine tools is a well-scoped size for a memory/preset management server. Each tool covers a distinct operation or workflow stage—CRUD, recall, usage reporting, and consolidation—without redundancy or bloat.
Completeness5/5
The tool surface covers the full lifecycle: save_requirement creates presets, list_memories/memory_overview/recall_presets read them, update_memory plus apply_consolidation handle updates/disable/archive, and delete_memory covers deletion. The two-phase consolidation workflow and record_usage for outcome tracking round out the domain with no obvious gaps.
Maintenance
ActivitySlowing
ResponsivenessNo issues