A
licenseNot graded
qualityB
maintenanceEnables AI agents to maintain persistent, local memory with retrieval-augmented search, knowledge graphs, and context surfacing, without any cloud dependencies.
180
MIT
wanyi
by 17861102832
Related Servers
Alternatives to wanyi
No user-submitted related servers found.
Related Servers
- FlicenseNot gradedqualityBmaintenanceEnables AI agents to automatically capture durable knowledge and retrieve only relevant, token-bounded context from a secure local-first long-term memory, with support for progressive disclosure, snapshots, health diagnostics, and background tasks.-
- AlicenseAqualityAmaintenanceGives AI agents persistent, local-first memory using SQLite and on-device embeddings, enabling semantic search and recall across sessions with no cloud calls.87MIT
- FlicenseNot gradedqualityCmaintenanceProvides AI agents with persistent, local cross-session shared memory by combining vector semantic retrieval with knowledge graph relationships, and supports short/long-term memory management and local backups.-
- AlicenseNot gradedqualityBmaintenanceLocal-first, multi-user shared memory for AI agents with semantic search, offline support, and team synchronization.MIT
- FlicenseNot gradedqualityDmaintenanceProvides persistent AI agent memory using a local vector database for long-term semantic storage and short-term session scratchpads. It enables low-latency memory operations including search, storage, and bulk management without external cloud dependencies.-
TDQS
B3.2/5.0
Scored across 23 tools
Disambiguation4/5
Most tools target a distinct memory lifecycle or guardrail function, and the detailed descriptions help separate recall from graph search, consolidation from deep gardening, and the various moat tools. A few pairs (LOAD hook vs. proactive partner's brief, sleep consolidation vs. gardener) could still be confused at first glance.
Naming Consistency3/5
All tools share the consistent 万忆 prefix, but the second element mixes noun-style names like 错题本 and 园艺师 with verb-object names like 记录见闻 and 更新交易锚点. The naming is readable, but there is no uniform verb_noun convention across the set.
Tool Count3/5
With 23 tools, this sits in the heavy range, and many tools bundle multiple subcommands, making the actual surface even larger. The count is not absurd for a comprehensive memory-and-reflection system, but it feels over-scoped for a typical MCP server.
Completeness3/5
The server covers memory writing, recall, compression, consolidation, self-checks, hooks, progress persistence, and proactive guardrails very extensively. However, there is no explicit general memory update or delete/forget tool, which leaves a notable gap in the core CRUD lifecycle for arbitrary memories.
Maintenance
ActivityMaintained
ResponsivenessNo issues