蓝汐 · 潮汐认知图谱
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| LANXI_LLM_API_KEY | No | API key for optional AI intelligent condensation using an OpenAI-compatible /chat/completions endpoint. | |
| LANXI_EMBEDDING_API_KEY | No | API key for optional semantic vector hybrid retrieval using an OpenAI-compatible /embeddings endpoint. |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| cg_writeB | 写入长期记忆节点到 Markdown 认知图(默认落 episodic 情景层;重要长期结论请显式指定 knowledge/structural;importance >= 0.7 或 anchor/self 层可开启硬保护)。 |
| cg_recallB | 按关键词、分层、项目与潮汐加权检索记忆(若已配置 Embedding API 则自动执行 FTS5 + 向量语义混合召回),并强化命中节点。 |
| cg_readA | 按节点 ID 读取完整记忆详情、潮汐保留度、出入边关系与磁盘文件路径。 |
| cg_updateB | 更新记忆节点内容、层级、标签、别名或重要度(若节点受硬保护,降低重要度、从受保护层迁出或解除保护需传 override: true)。 |
| cg_forgetA | 显式遗忘/归档记忆节点(绝不静默物理删除,仅移入 vault/archive/;硬保护节点需传 override: true)。 |
| cg_linkB | 在两个记忆节点之间建立有向语义关系(同时写入 SQLite 边表与源文件 frontmatter)。 |
| cg_graphB | 获取记忆关系子图(以某节点为中心或按层级返回关联度最高的节点和边)。 |
| cg_goalB | 列出或创建/更新长期目标与待办(存储在 goals 层,默认硬保护)。 |
| cg_reflectB | 记录元认知反思或待解决问题(写入 self 或 unresolved 层,并关联 derived_from 依据节点)。 |
| cg_maintainC | 潮汐维护:查看维护队列(queue),晋升情景(promote),强化访问(touch),批量修改/确认重要度(set_importance),手动或 AI 智能凝结(consolidate / ai_consolidate),补全向量(backfill_embeddings),或重建索引(rebuild)。 |
| cg_statsA | 获取蓝汐(Lanxi)认知图谱运行概览、潮汐水位分布、各层节点统计、磁盘真源新鲜度检测(dataStale)与配置(密钥已脱敏)。 |
| cg_import_vaultB | 以严格只读方式从外部 Markdown 目录(兼容标准 Frontmatter、Obsidian Vault 与 DSH mdcg)导入历史笔记到蓝汐认知图谱。 |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 12 tools
Core operations are clearly separated: cg_read/cg_write/cg_update/cg_recall/cg_link/cg_graph each target a distinct action on the memory graph. The main soft spot is the cluster of node-creation tools (cg_write, cg_goal, cg_reflect, cg_import_vault), which all produce nodes and are distinguished mainly by which layer they default to rather than by a fundamentally different operation. cg_stats vs cg_maintain(queue) also border on overlapping, though the descriptions clarify the read-only overview versus maintenance-queue split.
Every tool uses the same cg_ prefix and snake_case, giving a predictable family identity. However the stems mix verbs (cg_read, cg_write, cg_forget, cg_link, cg_recall, cg_reflect, cg_maintain) with bare nouns (cg_stats, cg_graph, cg_goal), and cg_import_vault is the lone two-word stem. Readable and mostly predictable, but not a single uniform convention.
Twelve tools is well within the comfortable range for a memory-graph server and each tool maps to a recognizable lifecycle operation. The maintain tool bundles eight sub-actions into one entry point, which keeps the surface lean rather than bloating it with near-duplicate maintenance verbs.
The lifecycle is largely covered: create, read, update, recall/search, link, subgraph traversal, goals, reflection, stats, import, and maintenance. Notable gaps include no way to remove or retype an existing edge (cg_link exists but there is no unlink/relink), and no explicit bulk list/enumerate-nodes or export path outside recall. These are workable gaps rather than dead ends.