Memoria
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| MEMORIA_DATA_DIR | No | Optional data directory for running an isolated Memoria server, e.g. a temporary directory, to avoid touching the live ~/.memoria database or port 48210. |
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 |
|---|---|
| recallA | Search memories of previous work by keywords/question. Returns facts, decisions, tasks and fixed errors. Call at session start! |
| project_contextA | Fetch the latest context of a project: decisions, pending tasks, completed work. Default mode "index" returns one compact line per memory with its id (cheap on tokens); call get_memory with the ids you need for full text. Use mode "full" to get everything at once. |
| file_contextA | Before editing a file, ask what is known about it: fixed errors, decisions, open tasks and preferences that mention this file path. Pass an absolute or relative path. |
| get_memoryA | Fetch the full text of specific memories by id (ids come from project_context, recall, or related). |
| rememberA | Store an important memory (decision, fact, user preference, completed/pending task) so every tool remembers it. |
| relatedA | Fetch memories connected (backlinks/similarity) to one memory. Use when recall context is incomplete or you need related detail. Pass a memory id or a text query. |
| update_memoryA | Correct an existing memory: replace its content (auto re-embedded so semantic search stays accurate), change its kind, or adjust importance. Pass the memory id from recall. |
| forgetA | Delete a stale or wrong memory. Pass the memory id for a direct delete, or a query: a confident match is deleted immediately, otherwise candidates are listed for you to pick an explicit id. |
| build_contextA | One ready-to-use context block for a project: auto-maintained project brief + key memories + optional query matches + 1-hop relations, capped to maxChars. Ideal first call at session start. |
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 9 tools
The core CRUD operations (get_memory, remember, update_memory, forget) are cleanly distinct, and recall vs related vs file_context are differentiated by input type and intent. The main soft spot is the read-side overlap: project_context in 'full' mode and build_context both return a ready-made context block, and recall with a query partly duplicates build_context's optional query matches, though the descriptions do enough to steer selection.
There is no single convention: snake_case verb_noun (get_memory, update_memory, build_context), bare verbs (recall, remember, forget), and noun-only names (project_context, file_context, related) coexist. Each name is individually readable and snake_case formatting is uniform, but the verb-vs-noun alternation breaks predictability.
Nine tools is well within the sweet spot for a memory/knowledge server, and each one corresponds to a distinct step in the memory lifecycle (store, search, retrieve, relate, update, delete, assemble context). No tool appears redundant padding.
Full lifecycle is covered: create (remember), read (get_memory, recall, project_context, file_context, build_context), update (update_memory), delete (forget), and graph traversal (related). Minor gaps remain — no way to enumerate or browse all stored memories, filter by kind/project, or bulk-delete/prune stale entries.