agentmods.dev

memory-mcp AGENTS.md

Project instructions for Memory MCP, a personal memory service that stores information for later search. It uses semantic search, which finds related meaning, and a knowledge graph, which records connections between things.

In plain words
What is it for?
Use it when working on the Memory MCP server, its command-line client, tests, documentation, or storage system. It covers installing dependencies, starting the service, testing, and code checks.
Why use it?
It gives coding agents the project structure, technology choices, commands, and rules they need to make consistent changes. It also records important implementation history.

Instructions file for CodexOpenCode

0 3mo ago A scan 2,162 tokens original MIT
View the source file kassol/memory-mcp
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/kassol/memory-mcp/agents-md
Clone the repo
git clone --depth 1 https://github.com/kassol/memory-mcp

Made for: Codex, OpenCode.

Per session 2,162 This file is loaded in full into every session.
When invoked 2,162 The same file — it is already loaded in full.
Security scan A 0 findings. 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 $0.02162 $0.02162
Opus 5 $0.01081 $0.01081
Sonnet 5 $0.00432 $0.00432
Haiku 4.5 $0.00216 $0.00216

Measured yesterday against content hash 5721f46c1c47, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

memory-mcp AGENTS.md 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 yesterday.

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.

AGENTS.md · 100 lines

How it starts

The opening of the file, as written. The whole thing — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Memory MCP

项目概述

个人记忆服务，基于语义向量检索与知识图谱，通过 MCP Streamable HTTP 对外提供能力。

技术栈

  • Python 3.11+
  • MCP SDK
  • LanceDB
  • NetworkX
  • Starlette / Uvicorn

目录索引

  • src/ - 服务端源代码
  • tests/ - 服务端测试
  • cli/ - CLI 客户端（独立包 memory-mcp-cli）
  • claude-code-plugin/ - Claude Code 插件（hooks/skills/commands）
  • docs/ - 项目文档
  • data/ - 运行时数据

常用命令

  • 安装依赖：pip install .
  • 开发服务：python -m memory_mcp
  • 运行测试：pytest
  • 代码检查：ruff check .

全局规范

  • MCP Streamable HTTP 为主传输协议；REST API (/api/v1/*) 为 CLI/hooks 等非 MCP 客户端提供轻量接入，复用同一套 tool 函数
  • Tool 返回值统一为 JSON 字符串
  • 记忆数据持久化：向量存储 + 图存储并行
  • 变更必须更新本文件
  • 涉及线上服务能力的任务，只有更新到线上并完成线上验证后才算终结；仅完成本地代码、测试或文档不算完成

变更日志

2026-05-21 M1 存储底座（v2 schema）

  • 引入 SQLite v2 主存储（aiosqlite + alembic 1.18 + WAL/FK/busy_timeout pragmas）
  • 新建 0001_initial_v2 migration：memories / memories_fts / entities / relations / threads / thread_messages / thread_messages_fts / jobs / working_memory_cache + 全部索引 + FTS5 触发器
  • LanceDB 精简到 (id, vector)，元数据全部走 SQLite；VectorStore.search 改为「ANN 取候选 ID → SQLite WHERE id IN (...) 拼装 MemoryNode」
  • GraphStore 改为运行时按需把 entities/relations 加载进 nx.MultiDiGraph，写时双写，废弃 data/graph/*.json 持久化与 evolution_chains.json
  • MemoryNode 增加 v2 字段：title / title_tokens / content_tokens / review_status / origin_client / origin_session_id / source_thread_id / source_refs / access_count / last_accessed_at / reinforce_count
  • 应用层 jieba 分词，写入 memories 时自动填充 content_tokens / title_tokens，支持 MEMORY_MCP_JIEBA_USER_DICT 自定义词典
  • 新增 python -m memory_mcp.scripts.migrate_v1_to_v2 --src ... --dst ... --backup ... --dry-run --verify 一次性迁移脚本（review_status 全部标 legacy）
  • FastAPI lifespan 启动时自动跑 alembic upgrade head（MEMORY_MCP_AUTO_MIGRATE 控制）；/health 新增 schema_version 字段，status 由 healthy 改为 ok
  • CLI 新增 mem db upgrade/downgrade/current/history 子命令（M6 runbook 离线运维入口）
  • 7 个原有 MCP tools 对外契约保持不变；新字段全部默认值；hybrid search / memory_crud / threads / worker 留给 M2-M4

2026-04-29 Relation 删除能力与交付规则

  • 新增 unrelate MCP tool，用于按 relation_id 删除实体关系边
  • 新增 REST API DELETE /api/v1/relations/{relation_id}，返回 deleted/not_found
  • CLI 新增 mem unrelate <relation_id>
  • 明确交付规则：线上服务更新并验证通过才视为任务完成

Read the full file on GitHub · 100 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. yesterday First seen · 100 lines · 2,162 tokens per session scan A 5721f46c1c47

Subscribe to this mod's changes

memory-mcp AGENTS.md is an instructions file published in the GitHub repository kassol/memory-mcp (0 stars, last pushed 3mo ago), licensed MIT. It adds 2,162 tokens to every session, about $0.0108 per session on Opus 5. 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.

Memory and context
Related

Other instructions, from other repositories

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

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 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

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,345 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

next.js 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