memory-agent
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| MEMORY_AGENT_DB | No | Path to the SQLite index database. Defaults to the database under the data root. Can also be configured in config.json as `db` or via the CLI `--db` argument. | |
| MEMORY_AGENT_HOME | No | Data root directory. Defaults to ~/.memory_agent. | |
| MEMORY_AGENT_VAULT | No | Path to the Markdown vault directory. Defaults to the vault directory under the data root. Can also be configured in config.json as `vault` or via the CLI `--vault` argument. |
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 |
|---|---|
| memory_searchA | 检索本地长期记忆库，返回最相关的知识卡摘要。当需要项目背景、历史决策、之前讨论过的方案、环境配置、踩过的坑，或任何「我之前是不是记过这件事」的场景时调用。查不到就说明没记过，不要凭猜测继续。支持中文词、英文标识符（如 nginx、id_ed25519）、IP、路径片段。 |
| memory_getA | 读取某张知识卡的完整内容。先用 memory_search 拿到 id，再调用本工具展开全文。检索结果里的摘要被截断时使用。长卡会按长度上限分片返回：结果末尾会写明还有多少字符未显示，并按需给出继续读用的 offset —— 看到「还有 N 字符未显示」时，若那部分对你有用，就用返回的 offset 再调一次。 |
| memory_captureA | 把一条值得长期复用的知识写进记忆库，供以后所有会话和其他 agent 检索。写入后本卡会被立即索引，不需要再调用 memory_reindex。触发时机：完成一个任务、解决一个报错、确认一个环境配置、做出一个影响后续的决策之后。写入前请自己先蒸馏——你是 LLM，用一两段话把结论写清楚，不要倒贴整段对话原文。标题要写成「以后你会用什么词去搜它」，正文要写清事实、命令、路径、以及为什么这么做。不要写入：临时状态、一次性的中间过程、密码与私钥等凭据。 |
| memory_statsA | 查看记忆库概览：卡片总数、类型与来源分布、最近更新。不确定库里有什么、或想确认检索范围时先调用它。 |
| memory_reindexA | 把 Markdown 记忆源的最新改动同步进检索索引。当确认某事已被记录、但 memory_search 检索不到时调用。 |
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 5 tools
Each tool targets a distinct memory operation: search for retrieval, stats for overview, get for full card content, capture for writing, reindex for sync. Boundaries are clear and the recommended search→get workflow is explicitly documented.
All tools use snake_case with a consistent memory_ prefix (memory_search, memory_stats, memory_get, memory_capture, memory_reindex). No deviations or mixed conventions.
5 tools is well-scoped for a memory agent: retrieval, inspection, writing, and indexing are all covered without redundancy. Each tool has a clear purpose and earns its place.
Covers read (search/get/stats), write (capture), and index sync (reindex). However, there is no explicit update or delete operation for existing memory cards, which is a notable gap for correcting or removing outdated knowledge. Append-only may be intentional, but agents cannot manage stale entries directly.