Supermemory MCPofficial
A
licenseNot graded
qualityF
maintenanceA universal memory server that allows users to access their chat memories across different LLMs without requiring logins or payment.
1,725
MIT
Waggle-mcp
Related Servers
Alternatives to Waggle-mcp
- AlicenseNot gradedqualityDmaintenanceEnables AI assistants to build and query temporally-aware knowledge graphs from conversations and data. Supports adding episodes, searching entities and facts, and maintaining persistent memory across interactions.10Apache 2.0
Related Servers
- AlicenseNot gradedqualityAmaintenanceOpen-source MCP server that gives any LLM long-term memory using a knowledge graph and vector search hybrid. It stores entities, observations, and relationships, enabling semantic recall across sessions with automatic clustering and fail-loud infrastructure.51MIT
- AlicenseNot gradedqualityCmaintenanceA universal MCP server providing persistent, structured memory through a knowledge graph with graph storage, semantic vector search, and multi-hop traversal for AI agents and IDEs.24 PyPI1MIT
- AlicenseAqualityAmaintenanceCognitive memory for AI agents. Works with Claude Code, Cursor, Windsurf, and any MCP-compatible client.21125 PyPI25MIT
- AlicenseNot gradedqualityAmaintenanceA local MCP server that gives LLMs long-term memory by indexing code, infrastructure, logs, and docs into a queryable graph. It enables semantic and structural search, evidence-backed reasoning, and tracked plans that persist across sessions and teams.1Apache 2.0
- AlicenseAqualityAmaintenanceGives any MCP client (Claude, ChatGPT, Cursor, and others) one shared knowledge-graph memory where agents record decisions, problems, and approaches together with their reasoning, then retrieve them by meaning rather than keyword. Spreading activation pulls in linked context and decay lets unused knowledge fade without deleting it.918Apache 2.0
- AlicenseAqualityDmaintenanceAn MCP server that gives LLMs structured, verifiable memory by storing facts in a knowledge graph and enabling logic-based reasoning through natural dialogue.143MIT
TDQS
A3.5/5.0
Scored across 41 tools
Disambiguation3/5
Several tools have overlapping purposes: query_graph, aggregate_graph, get_related, build_context, and prime_context all retrieve memory context, differing mainly in scope and compression. Similarly, export_graph_html, window_graph_viz, and export_markdown_vault all export visualizations, and commit/pull/diff/merge/grep/show/fsck/load_abhi_chunks form a file-management cluster that may confuse agents. However, many tools are distinct (store_node, store_edge, delete_node, resolve_conflict).
Naming Consistency3/5
Most tools use verb_noun snake_case (store_node, delete_node, list_conflicts, resolve_conflict), but there are deviations: 'pull', 'diff', 'merge', 'grep', 'show', 'fsck' are bare git-like verbs, and 'timeline' is a noun. The mixed conventions are readable but not fully consistent.
Tool Count2/5
41 tools is excessive for a memory-graph MCP server. While the domain is broad (graph CRUD, context windows, file import/export, file format utilities), many tools could be consolidated (e.g., multiple export variants, multiple retrieval modes, multiple .abhi file inspection commands). The count feels heavy and will overwhelm agents.
Completeness4/5
The tool surface covers the full memory lifecycle: create/read/update/delete nodes and edges, conflict detection/resolution, context window management, import/export, backup/restore, and diagnostics. Minor gaps exist (e.g., no explicit edge update tool, no batch delete except clear_*), but the domain is thoroughly covered.
Maintenance
ActivityActive
ResponsivenessResponsive