A
licenseA
qualityB
maintenanceLocal persistent memory for AI agents with recall, semantic search, forgetting, and encrypted storage.
12
8
579 npm
27
Apache 2.0
ctxvault
Related Servers
Alternatives to ctxvault
No user-submitted related servers found.
Related Servers
- FlicenseNot gradedqualityBmaintenancePersistent memory for AI coding agents: local-first semantic search, dependency graphs, git history.1-
- AlicenseNot gradedqualityDmaintenanceLocal-first persistent memory for AI agents via MCP, enabling semantic search and memory sharing across agents with zero cloud cost and full privacy.10 npm1MIT
- AlicenseNot gradedqualityBmaintenanceEnables AI agents to maintain and sync long-term memory and reusable skills across devices using local folder sync, with support for multiple agents and optional semantic recall.6 npm1MIT
- AlicenseAqualityBmaintenanceLocal memory for AI agents over plain Markdown files: hybrid vector + BM25 recall (RRF), one isolated memory per agent directory, fully offline with no LLM in the loop. Tools: cogvault_recall and cogvault_record.242 PyPI1MIT
- AlicenseAqualityDmaintenancelocal-first long-term memory for MCP agents (no DB, no API keys)37 npmMIT
TDQS
A3.6/5.0
Scored across 17 tools
Disambiguation4/5
Tools split cleanly into three domains (document vaults, skill vaults, episodic memory) and the descriptions cross-reference each other explicitly, e.g. invalidate_episode points to supersede_episode and revise_episode distinguishes 'world changed' from 'said better'. The only residual overlap is between query/query_episodes/list_docs, which is mitigated but not eliminated by the doc-vs-episode framing.
Naming Consistency4/5
Fourteen of seventeen tools follow a clean verb_noun snake_case pattern (list_vaults, write_doc, read_skill, supersede_episode, list_entities). The outliers — query, episode_history, warmup_status — are readable but break the verb-first convention.
Tool Count4/5
Seventeen tools is slightly heavy but justified by covering three distinct storage modes (documents, skills, temporal episodes) plus warmup and entity enumeration. No tool looks redundant enough to remove; episode lifecycle tools each handle a genuinely different case.
Completeness3/5
Episodic memory is exceptionally complete (write, query, confirm, invalidate, supersede, revise, dispute, history), but the document and skill surfaces are write/list/read only — no update, delete, or move for docs or skills, and no create_vault despite list_vaults implying vault management. These gaps will cause dead ends for maintenance workflows.
Maintenance
ActivityActive
ResponsivenessNo recent community issues