What is Mnemo-MCP AGENTS.md?

Instructions for Mnemo-MCP, an AI memory server that stores and searches information in a database. It combines ordinary text search with meaning-based search and provides tools for adding, updating, finding, archiving, and restoring memories.

Installing and running the server, searching or managing memories, importing and exporting them, viewing memory statistics, and checking or fixing the Python project.

It helps an assistant retain and retrieve information across tasks instead of relying only on the current conversation.

How expandingideas-ai/Mnemo-MCP configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to expandingideas-ai/Mnemo-MCP. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/expandingideas-ai/Mnemo-MCP/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/expandingideas-ai/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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/expandingideas-ai/mnemo-mcp/agents-md.svg)](https://agentmods.dev/instructions/expandingideas-ai/mnemo-mcp/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/expandingideas-ai/mnemo-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/expandingideas-ai/mnemo-mcp/agents-md.svg" alt="Measured on agentmods" height="20"></a>

Per session 3,208 This file is loaded in full into every session.

When invoked 3,208 The same file — it is already loaded in full.

Security scan B 1 finding. A grade says what 26 rules found in the file — not that it is safe.

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.

Model	Per session	Once invoked
Fable 5.1	$0.03208	$0.03208
Opus 5	$0.01604	$0.01604
Sonnet 5	$0.00642	$0.00642
Haiku 4.5	$0.00321	$0.00321

Measured 6d ago against content hash e90fb216b31e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, 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 6d 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:

Mnemo-MCP CLAUDE.md — 95% identical, 2 lines differ

AGENTS.md · 203 lines

How it starts

The opening of the file, as written. The whole thing — 203 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 + 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) + qwen3-embed local
  reranker.py      # Dual-backend reranking: cloud (Jina/Cohere) + local (qwen3-embed cross-encoder)
  graph.py         # Knowledge graph: entity/relation extraction via LLM
  relay_setup.py   # Legacy ECDH relay client (ensure_config); no live caller -- HTTP setup uses the OAuth-AS browser form at <PUBLIC_URL>/authorize
  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 · 203 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.

6d ago First seen · 203 lines · 3,208 tokens per session scan B e90fb216b31e

Subscribe to this mod's changes

Mnemo-MCP AGENTS.md is an instructions file published in the GitHub repository expandingideas-ai/Mnemo-MCP (0 stars, last pushed 2mo ago), licensed MIT. It adds 3,208 tokens to every session, about $0.0160 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.

Memory and context

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,182 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

Mnemo-MCP: Instructions file for Codex