Name: SQLite Local AI Memory
Author: cheveguerra

SQLite Local AI Memory MCP

100% In-Process Bare-Metal Hybrid Memory Engine & MCP Server for LLMs (SQLite + Int8 Vectors).

Grade A Local · stdio API key 5 tools v1.5.0 · 19 Oct 2026

No reviews yet by cheveguerranpm 943 Runs on your machine, nothing hosted

99/100

trust score

943

downloads a day

local

runs on your machine

tools declared

What it does

100% In-Process Bare-Metal Hybrid Memory Engine & MCP Server for LLMs (SQLite + Int8 Vectors).

Quickstart

# 1 — add it to Claude Code
claude mcp add --scope user sqlite-local-ai-memory-mcp '--' npx -y sqlite-local-ai-memory

# 2 — ask your agent for something these tools do
#   save_fact, search_memory, get_current_state and 2 more

SQLite Local AI Memory costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.

Publishernot claimed

cheveguerra1 server

1 category

All 1 server

Collected from a public index. Nobody has claimed this account, so nothing here was written by its author — claim it if it is yours.

Installation

Where are you running it?

Every route below installs the same thing and ends at the same approval screen. This one runs on your machine: your client starts SQLite Local AI Memory as a process under your own user, with your files and your network, so the tool surface below is what it can do to your computer rather than to a server somewhere else. Its scan result is on the Security tab — read the surface before you approve it.

Claude Codedeclared by this listing

This is a public server: you run it yourself and this marketplace is not in the path. You need Node.js — the current LTS (24) is the safe choice; npx comes with it. Claude Code registers it in one command; --scope user makes it available in every project. The '--' is in quotes so that PowerShell passes it on.

claude mcp add --scope user sqlite-local-ai-memory-mcp '--' npx -y sqlite-local-ai-memory

Reconnect, or start a new session, and the tools appear in the model’s tool list.

Free on mcprush, and it runs from its publisher’s own package: this marketplace is not in the path, so there is no key of ours to hold and no card to add.

What it asks of you

Nothing is required, but it can take GEMINI_API_KEY (Google Gemini API key for Out-of-the-Box cloud cognitive agents and embeddings (gemini-2.5-flash-lite & gemini-embedding-001).), SQLITE_MEM_PATH (Optional custom path to the SQLite database file (defaults to ~/.local-ai-memory/memoria.db).) if you want to set them.

What it writes

One config entry your client uses to start the process locally. A local server runs with your file system and your network, which is why it is priced without metering.

What you approve

5 tools, with what each one reads, writes and reaches shown before you agree — the same list on every route above. Read the tool surface.

Tool surface

What the model actually sees. Descriptions are diffed on every release — see version history.

Only tools that write or reach the network

Stores a new fact, preference, or technical knowledge directly in memory.

Parameter	Type	Required	Notes
fact	string	yes	The fact or information to save.
userId	string	no	Optional user ID to scope the memory fact.
source	string	no	Source or project tag, e.g. 'TOTALCONNECT', 'SQLITE_MEMORY' (optional, alphanumeric only).

Searches long-term memory for relevant facts or historical context using hybrid FTS5 BM25 + Int8 Vector search. Optionally pass recent conversation history to improve query disambiguation.

Parameter	Type	Required	Notes
query	string	yes	Search terms or topic to recall.
limit	integer	no	Maximum number of results to return (default: 5, max: 20).
userId	string	no	Optional user ID to scope the search.
history	string	no	Optional recent conversation history (e.g. 'U: hi A: hello U: what was that thing?'). When provided, the Query Expander uses it to resolve ambiguous references.

Retrieves the active, current working state summary (Dashboard).

Parameter	Type	Required	Notes
userId	string	no	Optional user ID to read the dashboard for.

Runs background memory maintenance (AutoDream): summarizes recent progress, cleans up outdated notes, saves key technical takeaways, and updates the active project board.

Parameter	Type	Required	Notes
userId	string	no	User ID to consolidate (optional, default: user_default).
source	string	no	Current project or source being consolidated (e.g. 'TOTALCONNECT'). Preserves items from other projects in dashboard. Alphanumeric only.

No parameter schema on file.

Free

$0 forever

Every tool, no call limit
No card, and mcprush charges nothing for it
Source published under MIT
Runs on your machine — nothing of it reaches our gateway
Nothing to cap, because mcprush bills nothing

Nothing here is billable: mcprush charges nothing to install SQLite Local AI Memory or to call it, at any volume.

ATrust score 99 / 100

Release 1.5.0 · scanned 20 Oct 2026

Two independent axes, because powerful and malicious are different questions. The grade is threat only. The capability level is blast radius, and it is never a penalty on the grade — it is priced as one subtract-only term in the score, where you can see it.

Threat score100

Client score99

Findings0 threat · 0 capability

Capabilityminimal

Coveragesource

Verificationrepo

Surface digestd9660ce1d1fd1a0325808d2d6cfd8e82fd2cb70afaa61572a10b4f387e66db38

Score vectorthreat 100 → client 99

Term	Level	What it prices	Points
capability-exposure	minimal	capability blast radius (minimal) — client exposure if the model is manipulated	−0
verification-discount	repo	publisher verification (public source) — no provenance, but the source is public and inspectable	−1
coverage-honesty	source	inspection depth (source) — how much of the target the scan could see	−0

score = clamp(round(threatScore − E_cap − E_ver − E_cov), 0, 100). No model, no opinion, no network call at scoring time: the same methodology version against the same bytes always produces this number, and every line above is a field of the report rather than a summary of it.

What the scan could actually read

A grade is only as meaningful as its coverage, so the scanner publishes its own depth before it publishes its result.

Tool surfaceread

Implementation sourceread

Package metadataread

Live transportnot available

Tools were statically extracted from the published source (5 recovered), not enumerated from a running server. Tool-poisoning, Unicode-smuggling, capability and toxic-flow analysis ran on this inferred surface, but a mis-parsed registration could be missed or mis-attributed, so tool-derived findings are capped below “confirmed”. To grade the real runtime surface, scan the running server: --command "npx -y <package>".

Capability — what it could do if the model were manipulated

Tags derived from each tool’s schema and the implementation, not from what the tool calls itself. minimal is the level these add up to.

Tool	Capability tags	Why the tag was assigned
save_fact	no tags
search_memory	no tags
get_fact_lineage	no tags
get_current_state	no tags
consolidate	no tags

Toxic-flow graph

The lethal trifecta, checked as a graph rather than as a checklist: untrusted input, a sensitive source and an external sink have to meet before there is a path worth worrying about.

The public result for this release does not print the flow graph, so there is nothing to show here. That is not the same as "no paths were found": what the scan did read is above, under coverage.

Supply chain and provenance

Integrityfirst-seen

Surface digestd9660ce1d1fd1a03

Scanned2026-10-20

This is the first scan of this surface here, so there is nothing yet to compare it against.

Every result on this tab comes from one deterministic pass over the published package — offline, rule by rule, and auditable line by line above. Same methodology version, same bytes, same score.