74
/ 100
1 month ago
glama

Thoth-Mem

Persistent memory for AI coding agents, storing learned architecture decisions, patterns, and bug fixes in a local SQLite database with full-text search, enabling agents to recall information across sessions.

Is this your MCP?

Claim it to get a verified publisher badge, a free copy of our full audit findings, and direct contact for any high-priority issues we find.

Install from

M8ven verifies MCPs across every public registry — install directly from whichever one you prefer.

// key findings
No credential exfiltration, no sensitive file access, no obfuscation
Static analysis found nothing flowing your secrets to unexpected places.
// required environment variables
This server reads these from process.env. You'll be asked to provide them before it can run.
configGITHUB_REF_NAME
configGITHUB_REPOSITORY
configGITHUB_REPOSITORY_OWNER
configTHOTH_DATA_DIR~/.thoth Data directory for SQLite database
configTHOTH_DEDUPE_WINDOW_MINUTES15 Rolling deduplication window
configTHOTH_EMBEDDING_BASE_URLprovider-specific Base URL for remote/local API providers
configTHOTH_EMBEDDING_DIMENSIONSinferred for known models Optional embedding dimensions override
configTHOTH_EMBEDDING_MODELUse the exact model id shown by LM Studio for .
configTHOTH_EMBEDDING_PROVIDERlmstudio \
configTHOTH_HTTP_DISABLEDtrue thoth-mem mcp
configTHOTH_HTTP_PORT7438 HTTP REST API port
configTHOTH_HYDE_BASE_URLunset Optional HyDE provider base URL
configTHOTH_HYDE_ENABLEDtrue Enable HyDE dual-input semantic query expansion
configTHOTH_HYDE_MODELonnx-community/Qwen2.5-Coder-0.5B-Instruct HyDE generation model id
configTHOTH_HYDE_PROVIDERtransformers_local HyDE generation provider (transformers_local, ollama, lmstudio)
configTHOTH_HYDE_TIMEOUT_MS4000 HyDE timeout before raw-query-only fallback
configTHOTH_KG_LLM_BASE_URLunset KG LLM provider base URL for remote providers
configTHOTH_KG_LLM_ENABLEDfalse Enable optional LLM KG enrichment for long observations
configTHOTH_KG_LLM_MIN_CONTENT_CHARS12000 Minimum observation size that triggers LLM enrichment
configTHOTH_KG_LLM_MODELonnx-community/Qwen2.5-Coder-0.5B-Instruct \
configTHOTH_KG_LLM_PROVIDERtransformers_local \
configTHOTH_KG_LLM_TIMEOUT_MS8000 KG LLM timeout before deterministic-only fallback
configTHOTH_MAX_CONTENT_LENGTH100000 Max content length (warns, never truncates)
configTHOTH_MAX_CONTEXT_RESULTS20 Max observations in context response
configTHOTH_MAX_SEARCH_RESULTS20 Max search results returned
configTHOTH_PREVIEW_LENGTH300 Search result preview length
configTHOTH_RETRIEVAL_EVAL_NOISEScale the retrieval eval with when you want hundreds or thousands of synthetic distractors. In PowerShell:
// full audit trail
The full breakdown of what we checked, the deductions that landed, the network hosts, the dependency advisories, and concrete fix guidance is available to verified publishers.
// improvement guidance — verified publishers only
We have 2 concrete improvements we can share with the publisher of this MCP. Each comes with specific guidance to raise the trust score.
// embed badge in your README
[![M8ven Score](https://m8ven.ai/badge/mcp/eremesng-thoth-mem-93m8sm)](https://m8ven.ai/mcp/eremesng-thoth-mem-93m8sm)
commit: d3ca25e27c9be806bb641572a967fe3f7129aa08
code hash: 7fc8325525f6ea4058890d89b43931426b870b6bf4155d9d574f5eb3fda6113f
verified: 6/11/2026, 12:23:22 PM
view raw JSON →