engrim
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
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 | {
"listChanged": false
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| engrim_recallA | Read-only query: Search this project's engrim memory for records relevant to a query using hybrid BM25 keyword and semantic vector ranking. Use before starting non-trivial work to recall prior architectural decisions, technical facts, user feedback, and project state. Safe to invoke repeatedly with zero mutations or side effects. |
| engrim_contextA | Read-only query: Return this project's curated session-boot memory pack (high-signal architectural decisions, active constraints, and conventions) to orient an agent at the start of a session or after clearing context. Safe to call repeatedly with zero mutations or external side effects. Records are prioritized and truncated to strictly fit within the specified character budget. |
| engrim_addA | Write operation: Save a durable memory record to local SQLite storage so it persists across sessions and agent restarts. Call this whenever a non-trivial architectural choice, durable fact, user constraint, or state milestone is established. Appends a new record to the project memory database. |
| engrim_reviewA | Read-only check: Inspect conversation and flight recorder history before clearing context to surface recent architectural decisions not yet saved to curated memory. Safe to call with no side effects. Returns heuristic verdict (safe_to_clear: true/false/null) and uncaptured candidate records. |
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 4 tools
Each tool has a clearly distinct purpose: context retrieval, semantic search, writing records, and pre-clear review. There is no overlap between reading curated context, searching all memory, adding new records, or checking for unsaved decisions.
All tools share the engrim_ prefix and use short, consistent verb-like suffixes (context, recall, add, review). Minor deviation: 'context' and 'recall' are nouns/verbs rather than a strict verb_noun pattern, but the naming is predictable and readable.
Four tools is a well-scoped set for a memory server: read curated context, search all memory, write new memory, and review unsaved history. Each tool earns its place with no redundancy.
The core memory lifecycle is covered: add, recall, context, and pre-clear review. A minor gap is the lack of explicit update/delete operations for correcting or removing stale records, but agents can work around this by adding superseding records.