mnemo-mcp AGENTS.md

mnemo-mcp AGENTS.md is an instructions file for Codex, OpenCode from n24q02m/mnemo-mcp. It costs 2,990 tokens per session, scanned B, original, Apache-2.0.

Instructions for developing mnemo-mcp, a Python server that provides searchable AI memory tools. It combines keyword search with semantic search, which finds related meaning rather than only matching words.

In plain words
What is it for?
Working on memory storage and retrieval, configuring language and embedding models, running tests, checking code quality, and building the package.
Why use it?
It documents the commands and checks needed to set up, test, lint, type-check, build, and run the server.

Instructions file for CodexOpenCode

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 instructions/n24q02m/mnemo-mcp/agents-md
Clone the repo
git clone --depth 1 https://github.com/n24q02m/mnemo-mcp

Made for: Codex, 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 mnemo-mcp AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/n24q02m/mnemo-mcp/agents-md.svg)](https://agentmods.dev/instructions/n24q02m/mnemo-mcp/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/n24q02m/mnemo-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/n24q02m/mnemo-mcp/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 2,990 This file is loaded in full into every session.
When invoked 2,990 The same file — it is already loaded in full.
Security scan B 1 finding. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.02990 $0.02990
Opus 5 $0.01495 $0.01495
Sonnet 5 $0.00598 $0.00598
Haiku 4.5 $0.00299 $0.00299

Measured 5d ago against content hash 7e3f91c4b151, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade B, and why

mnemo-mcp AGENTS.md scanned grade B with 1 finding 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.

Asks for rootmediumPrivilege escalation

A mod that escalates privileges can change anything on the machine, not only the project.

token_store.py # OAuth token storage (secure file-based, chmod 600)
Origin

Copies of this mod

1 near-identical copy found in the catalogue:

AGENTS.md · 194 lines

How it starts

The opening of the file, as written. The whole thing — 194 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md - mnemo-mcp

MCP Server cho AI memory. Python 3.13, uv, hatchling, src layout. Hybrid search: FTS5 + sqlite-vec semantic. 15 tools: 11 specialized memory tools (add_memory, search_memory, list_memories, update_memory, delete_memory, export_memories, import_memories, memory_stats, restore_memory, archived_memories, consolidate_memories) + legacy memory dispatcher (DEPRECATED -- use the granular tools instead) + config + help + config__open_relay. 2-mode embedding: cloud chain (EMBEDDING_MODELS) > Local (Qwen3 ONNX khi chain rong). Per-task model chains (EMBEDDING_MODELS/RERANK_MODELS/LLM_MODELS, order = litellm fallback). LLM/Embed/Rerank: litellm passthrough qua mcp_core.llm (mcp-core[llm]).

Commands

# Setup
uv sync --group dev

# Lint & Type check
uv run ruff check .
uv run ruff format --check .
uv run ty check

# Fix
uv run ruff check --fix .
uv run ruff format .

# Test (integration excluded by default)
uv run pytest
uv run pytest tests/test_db.py -v                          # single file
uv run pytest tests/test_db.py::TestSearch::test_basic -v  # single test

# Build & Run
uv build
uv run mnemo-mcp                    # run server (warmup/setup_sync via config tool)

# Mise shortcuts
mise run setup     # full dev setup
mise run lint      # ruff check + format check + ty check
mise run test      # pytest
mise run fix       # ruff fix + format

Pytest

  • asyncio_mode = "auto" -- khong can @pytest.mark.asyncio
  • Timeout: 30s/test
  • Integration marker: @pytest.mark.integration (can network/services)
  • Default: -m 'not integration and not live and not full'
  • Snapshot testing: syrupy

Cau truc thu muc

src/mnemo_mcp/
  __main__.py      # python -m mnemo_mcp entrypoint
  config.py        # Pydantic Settings (singleton), env vars khong co prefix
  server.py        # FastMCP server, tools, resources, prompts
  setup_tool.py    # Warmup + setup-sync logic (config tool actions)
  db.py            # SQLite: CRUD, FTS5, vector search (sqlite-vec)
  embedder.py      # Dual-backend: multi-provider cloud (Jina/Gemini/OpenAI/Cohere) + fastretrieval local
  reranker.py      # Dual-backend reranking: cloud (Jina/Cohere) + local (fastretrieval cross-encoder)
  graph.py         # Knowledge graph: entity/relation extraction via LLM
  relay_setup.py   # Zero-config relay: create session, poll for config
  relay_schema.py  # Relay form schema (local + cloud modes)
  sync/            # Sync backends: gdrive.py (OAuth Device Code, httpx) + s3.py (R2/B2/MinIO) + delta/bundle/base
  token_store.py   # OAuth token storage (secure file-based, chmod 600)
  docs/            # Tool documentation markdown
tests/             # 1:1 mapping voi source modules

Read the full file on GitHub · 194 lines

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 · 194 lines · 2,990 tokens per session scan B 7e3f91c4b151

Subscribe to this mod's changes

mnemo-mcp AGENTS.md is an instructions file published in the GitHub repository n24q02m/mnemo-mcp (10 stars, last pushed today), licensed Apache-2.0. It adds 2,990 tokens to every session, about $0.0149 per session on Opus 5. A static security scan graded it B with 1 finding (asks for root). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.