Mnemosyne
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| OLLAMA_URL | No | Ollama server for embeddings | http://localhost:11434 |
| MEMORY_DB_DSN | No | PostgreSQL connection string | |
| EMBEDDING_MODEL | No | Sentence-transformers model | all-MiniLM-L6-v2 |
| MEMORY_VAULT_PATH | No | Markdown vault directory | ~/Documents/Kimi/Workspaces/Mnemosyne/obsidian-vault |
| MEMORY_SQLITE_PATH | No | SQLite database path | ~/.mnemosyne/mnemosyne.db |
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 |
|---|---|
| memory_rememberA | Store a private memory note in the vault with semantic embedding, tags, and hierarchical wing/room scope. |
| memory_publish_sharedA | Publish a sanitized, curated finding or policy to the cross-agent shared fleet memory. |
| memory_recallB | Search memory by semantic meaning, keywords, or graph. Retrieves from both private and shared stores. |
| memory_ingest_sessionA | Ingest a full conversation transcript verbatim into memory, split along conversational turn boundaries. |
| memory_timelineB | View recent memory operations (remember, recall, remind, consolidate) as a chronological timeline. |
| memory_historyB | View version history of a specific memory note (previous edits). |
| memory_remind_meB | Schedule a future reminder or recurring task |
| memory_assemble_contextA | Retrieve and format high-salience memories into a strict token-budgeted XML prompt block ready for direct agent context injection. |
| memory_auditA | Get memory system statistics, health check, active wings, and version info |
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
Most tools target distinct memory operations: storing, retrieving, scheduling, auditing, and publishing. Some overlap exists between memory_recall (search) and memory_assemble_context (curated retrieval), but their descriptions make the intended use clear.
All tool names follow a consistent memory_verb_noun pattern using snake_case (e.g., memory_ingest_session, memory_publish_shared). The one slight deviation is memory_remind_me, but it still fits the overall verb-first convention.
Nine tools cover the core memory management lifecycle without feeling bloated. The set is well-scoped for a memory server, with each tool serving a clear and necessary function.
The server covers storing, retrieving, scheduling, sharing, and diagnostics, but lacks explicit update or delete/forget tools. Memory_history implies prior edits exist, yet no edit tool is exposed, which is a notable gap for a memory management system.