Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
THOTH_DATA_DIRNoData directory for SQLite database~/.thoth
THOTH_HTTP_PORTNoHTTP REST API port7438
THOTH_HYDE_MODELNoHyDE generation model idonnx-community/Qwen2.5-Coder-0.5B-Instruct
THOTH_HYDE_ENABLEDNoEnable HyDE dual-input semantic query expansiontrue
THOTH_KG_LLM_MODELNoKG LLM model idonnx-community/Qwen2.5-Coder-0.5B-Instruct
THOTH_HTTP_DISABLEDNoDisable HTTP REST API bridgefalse
THOTH_HYDE_BASE_URLNoOptional HyDE provider base URLunset
THOTH_HYDE_PROVIDERNoHyDE generation provider (transformers_local, ollama, lmstudio)transformers_local
THOTH_KG_LLM_ENABLEDNoEnable optional LLM KG enrichment for long observationsfalse
THOTH_PREVIEW_LENGTHNoSearch result preview length300
THOTH_EMBEDDING_MODELNoEmbedding model idnomic-ai/nomic-embed-text-v1.5
THOTH_HYDE_TIMEOUT_MSNoHyDE timeout before raw-query-only fallback4000
THOTH_KG_LLM_BASE_URLNoKG LLM provider base URL for remote providersunset
THOTH_KG_LLM_PROVIDERNoKG LLM provider (transformers_local, ollama, lmstudio)transformers_local
THOTH_KG_LLM_TIMEOUT_MSNoKG LLM timeout before deterministic-only fallback8000
THOTH_EMBEDDING_BASE_URLNoBase URL for remote/local API providersprovider-specific
THOTH_EMBEDDING_PROVIDERNoEmbedding provider (transformers_local, ollama, lmstudio)transformers_local
THOTH_MAX_CONTENT_LENGTHNoMax content length (warns, never truncates)100000
THOTH_MAX_SEARCH_RESULTSNoMax search results returned20
THOTH_MAX_CONTEXT_RESULTSNoMax observations in context response20
THOTH_EMBEDDING_DIMENSIONSNoOptional embedding dimensions overrideinferred for known models
THOTH_DEDUPE_WINDOW_MINUTESNoRolling deduplication window15
THOTH_KG_LLM_MIN_CONTENT_CHARSNoMinimum observation size that triggers LLM enrichment12000

Capabilities

Features and capabilities supported by this server

CapabilityDetails
tools
{
  "listChanged": true
}

Tools

Functions exposed to the LLM to take actions

NameDescription
mem_saveA

Save memory. This single write tool handles observations, user prompts, session summaries, and passive learning capture.

For durable observations, use kind=observation and structured content: What: [concise description] Why: [reasoning or problem] Where: [files/paths affected] Learned: [gotchas, edge cases]

Use topic_key for evolving topics that should update in-place.

mem_recallA

Primary retrieval tool. Runs fused hybrid recall across sentence vectors, chunk vectors, keyword FTS, and knowledge-graph enrichment.

mem_contextA

Get recent memory context from previous sessions. Shows recent sessions, user prompts, and observations to understand what was done before.

Use this at the start of a session to recover context, or when the user asks to recall past work.

Returns bounded Markdown with:

  • Recent sessions (last 5 with activity)

  • Recent user prompts (last 10)

  • Recent observations (configurable limit)

  • Memory stats (total counts)

Observation bodies are previewed by default; use mem_get(id=...) for full content.

mem_getC

Fetch a saved observation or prompt by ID. Use include_timeline=true when the surrounding observation chronology matters.

mem_projectC

Project-level memory navigation. Lists projects, summarizes one project, reads graph facts, or inspects topic-key memory.

mem_sessionB

Manage the active memory session. Use action=start at session start and action=summary before ending.

Prompts

Interactive templates invoked by user choice

NameDescription

No prompts

Resources

Contextual data attached and managed by the client

NameDescription

No resources

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/EremesNG/thoth-mem'

If you have feedback or need assistance with the MCP directory API, please join our Discord server