sqlite-local-ai-memory
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| NOTARY_MODEL | No | Model for the Notary role. Default: gemini/gemini-2.5-flash-lite | |
| ARBITER_MODEL | No | Model for the Semantic Arbiter role. Default: gemini/gemini-2.5-flash-lite | |
| EMBEDDER_MODEL | No | Model for the Embedder role. Default: ollama/nomic-embed-text. Fallback: gemini-embedding-001 | |
| EXPANDER_MODEL | No | Model for the Query Expander role. Default: gemini/gemini-2.5-flash-lite. Set to 'none' to disable. | |
| GEMINI_API_KEY | No | Google Gemini API key used by default for the Notary, Semantic Arbiter, Query Expander, and State Orchestrator roles. | |
| OPENAI_BASE_URL | No | Base URL for OpenAI-compatible API. Used when a model provider is set to openai. | |
| SQLITE_MEM_PATH | No | Path to the SQLite database file. Example: ~/.local-ai-memory/memoria.db | |
| GATEKEEPER_MODEL | No | Model for the Gatekeeper role. Default: ollama/qwen2.5-coder:1.5b | |
| ORCHESTRATOR_MODEL | No | Model for the State Orchestrator role. Default: gemini/gemini-2.5-flash-lite |
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": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| save_factA | Persists an atomic fact, preference, or technical rule into long-term memory with automatic semantic deduplication and vector indexing (append-only write). Use for immediate logging; for search use 'search_memory', for evolution audits use 'get_fact_lineage', and for batch synthesis use 'consolidate'. Returns the assigned fact UUID and status. |
| search_memoryA | Searches long-term memory using hybrid FTS5 BM25 lexical and vector cosine similarity with RRF ranking (read-only). Supports Point-in-Time queries via 'as_of'. Use for factual lookup and technical recall. For active high-level board use 'get_current_state'; for fact revisions use 'get_fact_lineage'. Returns ranked list of scored memory items. |
| get_fact_lineageA | Traces the full evolutionary history and supersede chain of a fact by its UUID (read-only). Use when auditing how or why a rule changed, or resolving conflicting facts. Obtain the UUID via 'search_memory'. Returns chronological revisions and rationale. |
| get_current_stateA | Retrieves the active executive working dashboard, active project focus, and recent milestones (read-only). Use during session bootstrap or task switching for high-level orientation. Do NOT use for granular fact searches (use 'search_memory'). Returns formatted markdown dashboard. |
| consolidateA | Executes cognitive memory maintenance (AutoDream): synthesizes progress, archives obsolete notes, and updates the project dashboard (batch write). Call only at session close or after major milestones, NOT on every turn. Preserves other projects' cards. Returns triage summary report. |
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 has a clearly distinct purpose: two targeted reads (get_fact_lineage, get_current_state), a broad search (search_memory), an atomic write (save_fact), and a batch maintenance write (consolidate). The descriptions explicitly cross-reference each other with 'use X instead of Y' guidance, eliminating selection ambiguity.
Four tools follow a clean verb_noun or verb_noun-ish pattern (get_fact_lineage, get_current_state, save_fact, search_memory), while 'consolidate' is a bare verb. This is a minor deviation that remains readable and predictable.
Five tools is well-scoped for a local memory server, with each earning its place across read, search, write, audit, and maintenance roles. No redundant or trivially fragmented tools.
The surface covers search, atomic persistence, lineage auditing, dashboard state, and batch consolidation, which spans the core memory lifecycle. An explicit forget/delete or update operation is absent, though append-only supersede via save_fact mostly compensates.