agentmods.dev

llama-memory

llama-memory is an MCP server for Claude Code, Codex, Cursor, Gemini CLI, OpenCode from noualit/llama-server-memory-local. Its token cost is not measured, scanned A, original, MIT.

A local launcher for quantized Llama language models, which are smaller model files designed to use less computer memory. It runs the models on a CPU through the llama-memory Python package.

In plain words
What is it for?
Use it to deploy and run quantized Llama models on a CPU from an agent configuration.
Why use it?
It provides a way to run supported Llama models locally without relying on a remote model service.

MCP server for Claude CodeCodexCursorGemini CLIOpenCode

Written for no agent in particular: it speaks MCP, so any client can run it.

not rated 0 +1 12d ago A scan tokens not measured original MIT
View the source file noualit/llama-server-memory-local
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add mcp/noualit/llama-server-memory-local/llama-memory
Clone the repo
git clone --depth 1 https://github.com/noualit/llama-server-memory-local

Made for: Claude Code, Codex, Cursor, Gemini CLI, OpenCode.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for llama-memory

README.md
[![agentmods](https://agentmods.dev/badge/mcp/noualit/llama-server-memory-local/llama-memory.svg)](https://agentmods.dev/mcp/noualit/llama-server-memory-local/llama-memory)
Your own site
<a href="https://agentmods.dev/mcp/noualit/llama-server-memory-local/llama-memory"><img src="https://agentmods.dev/badge/mcp/noualit/llama-server-memory-local/llama-memory.svg" alt="Measured on agentmods" height="20"></a>
Per session not measured What this adds to a session before it is invoked.
When invoked not measured Not applicable: nothing here is loaded into a session.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Security

Grade A, and why

llama-memory scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

listed in the official MCP registry · 8 lines

What it actually says

{ "llama-memory": { "command": "uvx", "args": [ "llama-memory" ] } }

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 5d ago First seen · 8 lines scan A e4a65b199bd6

Subscribe to this mod's changes

llama-memory is an MCP server published in the GitHub repository noualit/llama-server-memory-local (0 stars, last pushed 12d ago), licensed MIT. Its token cost is not measured: an MCP server costs its tool schemas, not its config file. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Data and AIllama-cppmcp-server
Related

Other mcp servers, from other repositories

mongodb-mcp-server

MongoDB Model Context Protocol Server. Runs locally from the mongodb-mcp-server npm package. Needs 42 environment variables to run.

mongodb-js/mongodb-mcp-server · not measured

haiku-rag

Local-first agentic RAG with citations - hybrid search, reranking and multimodal retrieval over your own documents, no database server required. Runs locally from the haiku-rag Python package.

ggozad/haiku.rag · not measured

octocode

AI-powered code indexer with semantic search and knowledge graphs. Runs locally from the @muvon/octocode npm package.

Muvon/octocode · not measured

mcp-local-rag

Easy-to-setup local RAG server with minimal configuration. Runs locally from the mcp-local-rag npm package. Needs 8 environment variables to run.

shinpr/mcp-local-rag · not measured

prism-mcp

Persistent session memory for AI coding agents that never leaves your machine — including the on-device model that reasons over it. Restores your prior decisions, open TODOs, and changed files across sessions; adds associative recall of related past work. Runs locally from the prism-mcp-server npm package. Needs 1…

dcostenco/prism-coder · not measured

yfmcp

MCP server "yfmcp" as configured in narumiruna/yfinance-mcp. Runs locally from the yfmcp Python package.

narumiruna/yfinance-mcp · not measured