Which integrations are available for this server?

Integrates with GitHub Copilot in VS Code to provide persistent memory, allowing storage and retrieval of session summaries and decisions.

How do I use ai-memory-mcp?

1. Click on "Deploy Server". 2. Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state. 3. In the chat, type @ followed by the MCP server name and your instructions, e.g., "@ai-memory-mcp Load my memory for project 'ai-memory-mcp'" That's it! The server will respond to your query, and you can continue using it as needed. Here is a step-by-step guide with screenshots.

ai-memory-mcp

by zhanpu89

Overview Schema Source Related Servers Discussions Admin

Python

Hybrid

🧠 AI Memory MCP

Persistent session memory for AI assistants — store, search and retrieve conversation summaries via the Model Context Protocol.

What is this?

AI assistants forget everything between sessions. AI Memory MCP solves that by giving your AI a structured long-term memory:

📝 Save session summaries with status, tags, modules and file paths
🔍 Search by keyword, full-text (FTS5), or semantic vector similarity
🔄 Restore context at the start of each session with one tool call
📊 Generate weekly reports from completed tasks automatically
🏷️ Multi-project / multi-branch support out of the box

Works with Claude Desktop, Cursor, VS Code, Windsurf, and any MCP-compatible client.

Related MCP server: recall-mcp

Quick Start

1 — Install

# From PyPI (recommended)
pip install ai-memory-mcp

# With vector search support (adds ~500 MB for embedding model)
pip install "ai-memory-mcp[vector]"

# From source
git clone https://github.com/zhanpu89/ai-memory-mcp
cd ai-memory-mcp
pip install -e .

2 — Configure your AI client

Pick the config snippet for your tool and add it to its MCP settings file:

{
  "mcpServers": {
    "ai-memory": {
      "command": "ai-memory-mcp"
    }
  }
}

{
  "mcpServers": {
    "ai-memory": {
      "command": "ai-memory-mcp"
    }
  }
}

{
  "servers": {
    "ai-memory": {
      "type": "stdio",
      "command": "ai-memory-mcp"
    }
  }
}

{
  "mcpServers": {
    "ai-memory": {
      "command": "ai-memory-mcp"
    }
  }
}

Start the server:

ai-memory-mcp --http
# or: python service.py start

Then point your client at:

{
  "mcpServers": {
    "ai-memory": {
      "url": "http://localhost:8000/mcp"
    }
  }
}

All config snippets are available in integrations/.

3 — Use it

At the start of every session, tell your AI:

Load my memory for project "my-project"

The AI will call init_session and restore your previous context automatically.

Features

Feature	Details
Storage	SQLite — zero external services, single file
Full-text search	SQLite FTS5 — fast, no extra deps
Semantic search	ChromaDB + `all-MiniLM-L6-v2` (optional)
Multi-project	Filter by `project_name` + `branch_name`
Task lifecycle	`pending → in_progress → completed / blocked / abandoned`
Key decisions	Attach architectural decisions to sessions
Weekly reports	Auto-generated Markdown report
Transport	stdio (local) or streamable-HTTP (remote)
Docker	Single-container deployment included

Architecture

┌─────────────────────────────────────────────────┐
│               AI Client (Claude / Cursor …)      │
│                    MCP Protocol                  │
└──────────────────────┬──────────────────────────┘
                       │ stdio / HTTP
┌──────────────────────▼──────────────────────────┐
│              AiMemoryMcpServer (FastMCP)         │
│                                                  │
│  ┌──────────────┐    ┌──────────────────────┐   │
│  │  SQLite DB   │    │  ChromaDB (optional) │   │
│  │  FTS5 index  │    │  Sentence-Transformers│  │
│  └──────────────┘    └──────────────────────┘   │
└─────────────────────────────────────────────────┘

Data lives in ~/.ai-memory/ — completely separate from your project files.

Tool Reference

→ See TOOLS.md for the full schema of all 10 tools.

Tool	Description
`save_summary`	Persist a new session summary
`update_summary`	Update status / content
`add_decision`	Record a key technical decision
`search_summaries`	Keyword / FTS5 / vector search
`search_summaries_fts`	Dedicated FTS5 full-text search
`get_summary_by_id`	Exact lookup by session ID
`list_recent_sessions`	List latest sessions
`init_session`	Restore context at session start
`weekly_review`	Generate Markdown weekly report
`maintenance`	Rebuild index, VACUUM, persist vectors

Configuration

All settings are optional — sensible defaults work out of the box.

Env var	Default	Description
`AI_MEMORY_DB_PATH`	`~/.ai-memory/ai_memory.db`	SQLite database path
`AI_MEMORY_MODEL_PATH`	`~/.ai-memory/models`	Embedding model cache
`AI_MEMORY_HOST`	`127.0.0.1`	HTTP server bind address
`AI_MEMORY_PORT`	`8000`	HTTP server port

Create ~/.ai-memory/.env to persist settings:

AI_MEMORY_DB_PATH=/custom/path/ai_memory.db
AI_MEMORY_PORT=9000

Docker

Optimized for China: Uses Tsinghua pip mirror + HuggingFace mirror for fast downloads.

# Option 1: Core-only (lightweight, ~200 MB image)
docker compose up -d

# Option 2: Full (with vector search)
# Step 1: Pre-download model to avoid large image
python3 scripts/download_model_for_docker.py --output ./models

# Step 2: Build with vector support (~700 MB image + 500 MB external model)
docker compose build --build-arg INSTALL_VECTOR=true
docker compose up -d

# View logs
docker compose logs -f

The MCP endpoint will be available at http://localhost:8000/mcp.

📖 Full deployment guide: See DOCKER.md for:

Image size optimization strategies
Chinese mirror configuration
Model pre-downloading
Production deployment examples

Development

# Clone and install in editable mode with dev extras
git clone https://github.com/zhanpu89/ai-memory-mcp
cd ai-memory-mcp
pip install -e ".[dev]"

# Run tests
pytest

# Run tests with coverage
pytest --cov=src/mcp_server --cov-report=term-missing

# Start in HTTP mode for manual testing
ai-memory-mcp --http

Project Structure

ai-memory-mcp/
├── src/mcp_server/
│   ├── __init__.py
│   └── server.py          # All 10 MCP tools + server class
├── tests/
│   ├── unit/              # 24 unit tests
│   └── integration/
├── scripts/
│   ├── download_model.py  # Manual model download
│   ├── migrate_db.py      # Database migration helper
│   └── migrate_vector.py  # Vector store migration
├── integrations/          # Ready-to-use MCP client configs
│   ├── claude_desktop_config.json
│   ├── cursor_mcp.json
│   ├── vscode_mcp.json
│   ├── windsurf_mcp.json
│   └── http_mode_config.json
├── TOOLS.md               # Full tool schema reference
├── INSTALL.md             # Detailed installation guide
├── Dockerfile
├── docker-compose.yml
└── pyproject.toml

Testing

24 passed in 7s

pytest tests/unit/test_mcp_server.py -v

All 24 unit tests cover: save/update/search/FTS/vector/decisions/maintenance/init/review/schema.

Requirements

Python 3.10+
mcp >= 1.6.0
python-dotenv >= 1.0.0

Optional (vector search):

chromadb >= 0.6.0
sentence-transformers >= 3.0.0

License

MIT © AI Memory Team

Available Tools

10 tools

add_decisionB

为指定会话添加关键决策记录。

Args: params (AddDecisionInput): 包含： - session_id (str): 关联的会话 ID - decision_type (str): 决策类型，如 tech_stack / api_design / architecture - description (str): 决策描述 - reasoning (Optional[str]): 决策理由

Returns: Dict: {"success": bool, "message": str}

Inputs: params (required). Returns: result

get_summary_by_idA

Read-onlyIdempotent

根据 session_id 精确查询单条摘要记录。

Args: params (GetSummaryByIdInput): 包含： - session_id (str): 目标会话 ID

Returns: Dict: {"success": bool, "data": Dict}

Inputs: params (required). Returns: result

init_sessionA

Read-onlyIdempotent

会话启动时调用，返回最近 3 天内进行中的任务列表，帮助恢复上下文。

Args: params (InitSessionInput): 包含： - project_name (Optional[str]): 项目名称过滤，精确匹配 - branch_name (Optional[str]): 分支名称过滤，精确匹配

Returns: Dict: {"success": bool, "data": List[Dict], "prompt": str}

Inputs: params (required). Returns: result

list_recent_sessionsA

Read-onlyIdempotent

列出最近的会话摘要，支持按项目和分支过滤。

Args: params (ListRecentSessionsInput): 包含： - limit (int): 最大返回条数，默认 10 - project_name (Optional[str]): 项目名称过滤，精确匹配 - branch_name (Optional[str]): 分支名称过滤，精确匹配

Returns: Dict: {"success": bool, "data": List[Dict]}

Inputs: params (required). Returns: result

maintenanceA

Idempotent

执行数据库维护：重建 FTS5 全文索引、压缩数据库，并持久化向量存储。

Returns: Dict: {"success": bool, "message": str}

Inputs: no named parameters. Returns: result

save_summaryA

保存会话摘要到数据库，同步更新全文索引和向量索引。

Args: params (SaveSummaryInput): 包含： - session_id (str): 唯一会话 ID，不可重复 - task_title (str): 任务标题 - summary_content (str): 摘要正文内容 - status (TaskStatus): 任务状态，默认 completed - next_steps (Optional[str]): 下一步计划 - tags (Optional[str]): 标签，逗号分隔 - module (Optional[str]): 所属模块 - file_paths (Optional[str]): 涉及文件路径，逗号分隔 - project_name (Optional[str]): 项目名称 - branch_name (Optional[str]): 分支名称

Returns: Dict: {"success": bool, "message": str}

Inputs: params (required). Returns: result

search_summariesB

Read-onlyIdempotent

搜索会话摘要，支持关键词、标签、模块、状态、项目、分支过滤，以及 FTS5 全文检索和向量语义检索。

Args: params (SearchSummariesInput): 包含： - query (Optional[str]): 搜索关键词 - tags (Optional[str]): 标签过滤，模糊匹配 - module (Optional[str]): 模块过滤，模糊匹配 - status (Optional[TaskStatus]): 状态过滤，精确匹配 - project_name (Optional[str]): 项目名称过滤，精确匹配 - branch_name (Optional[str]): 分支名称过滤，精确匹配 - use_fts (bool): 是否使用 FTS5 全文检索，默认 False - use_vector (bool): 是否使用向量语义检索，默认 False - limit (int): 最大返回条数，默认 10

Returns: Dict: {"success": bool, "data": List[Dict]}

Inputs: params (required). Returns: result

search_summaries_ftsA

Read-onlyIdempotent

使用 FTS5 全文索引搜索会话摘要，适合精确关键词匹配场景。

Args: params (SearchSummariesFtsInput): 包含： - query (str): 全文检索关键词，支持 FTS5 查询语法 - project_name (Optional[str]): 项目名称过滤，精确匹配 - branch_name (Optional[str]): 分支名称过滤，精确匹配 - status (Optional[TaskStatus]): 状态过滤，精确匹配 - limit (int): 最大返回条数，默认 10

Returns: Dict: {"success": bool, "data": List[Dict]}

Inputs: params (required). Returns: result

update_summaryA

Idempotent

更新已有会话摘要的状态或内容，同步更新全文索引。

Args: params (UpdateSummaryInput): 包含： - session_id (str): 要更新的会话 ID - new_status (Optional[TaskStatus]): 新状态 - updated_content (Optional[str]): 新的摘要内容

Returns: Dict: {"success": bool, "message": str}

Inputs: params (required). Returns: result

weekly_reviewA

Read-onlyIdempotent

生成本周项目周报，汇总完成任务、关键决策和下一步建议。

Args: params (WeeklyReviewInput): 包含： - project_name (Optional[str]): 项目名称过滤，精确匹配 - branch_name (Optional[str]): 分支名称过滤，精确匹配

Returns: Dict: {"success": bool, "data": {"report": str}}

Inputs: params (required). Returns: result

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

Deploy Server

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

TDQS

A3.8/5.0

Scored 2026-05-26 07:55 across 10 tools

Disambiguation4/5

Most tools serve distinct purposes, but search_summaries and search_summaries_fts overlap significantly, potentially confusing an agent about which to use for searching summaries.

Naming Consistency4/5

Names mostly follow verb_noun pattern (add_decision, save_summary) but include a few outliers like maintenance (noun) and longer phrases like get_summary_by_id, deviating from strict consistency.

Tool Count5/5

With 10 tools covering session initialization, CRUD, search, maintenance, and reporting, the count is well-scoped for an AI memory server without being overwhelming.

Completeness3/5

Covers saving, retrieving, updating, and searching summaries, but lacks delete functionality and has no dedicated tools for retrieving or removing decisions, leaving notable gaps.

Maintenance

ActivityInactive

ResponsivenessOutdated data

Resources

Related MCP Connectors

goldhold
io.github.jerrysrodz
Persistent memory for AI agents. Search, store, and recall across sessions.
Knowledge & Memory Autonomous Agents RAG Systems
2
https://relay.goldhold.ai/mcp
CLS++ Memory
io.github.rajamohan1950
Cross-LLM persistent memory: store context once, recall it from any AI model.
Knowledge & Memory AI & Machine Learning
2
https://www.clsplusplus.com/mcp
MemorySyncA
io.memorysync
Persistent memory for AI agents. Search and store durable facts, preferences and decisions.
Autonomous Agents Developer Tools Knowledge & Memory
151
https://mcp.memorysync.io/mcp
AI Cortex StorageA
dev.aic0rt3x.memory
Persistent cloud memory for AI agents. Store and search key-value memories across sessions.
Knowledge & Memory Cloud Storage Agent Orchestration
2
https://memory.aic0rt3x.dev/mcp

Related MCP Servers

codebase-memory
Knowledge & Memory Coding Agents
yuga-hashimoto
A
license
Not graded
quality
D
maintenance
Provides persistent memory for AI coding agents through the Model Context Protocol, enabling them to store and retrieve project knowledge across sessions.
Updated 8 months ago (2026-03-09 13:47 UTC)
27 npm
MIT
recall-mcp
Knowledge & Memory Search
jadeleke
A
license
Not graded
quality
D
maintenance
Persistent, searchable memory for AI agents over the Model Context Protocol, enabling memory storage, full-text search with BM25 ranking, and retrieval across sessions.
Updated 4 months ago (2026-07-13 04:07 UTC)
10 npm
MIT
io.github.silversurfer562/memd
Knowledge & Memory RAG Systems Developer Tools
Smart-AI-Memory
A
license
Not graded
quality
D
maintenance
Provides persistent, project-specific memory to AI assistants via the Model Context Protocol, enabling context-aware collaboration across sessions without cloud dependencies.
Updated a year ago (2025-12-08 18:12 UTC)
33 PyPI
1
Apache 2.0
mcp-memory
bobmatnyc
A
license
Not graded
quality
D
maintenance
A standalone memory service that provides persistent storage for AI assistants via the Model Context Protocol.
Updated a year ago (2025-09-27 16:07 UTC)
MIT

🧠 AI Memory MCP

What is this?

Quick Start

1 — Install

2 — Configure your AI client

3 — Use it

Features

Architecture

Tool Reference

Configuration

Docker

Development

Project Structure

Testing

Requirements

License

Available Tools

Tool Schema Changelog

TDQS

Maintenance

Resources

Related MCP Connectors

Related MCP Servers

codebase-memory

recall-mcp

io.github.silversurfer562/memd

mcp-memory