Memory OS AI
Adaptive memory system for AI agents — universal MCP server for Claude Code, Codex CLI, VS Code Copilot, ChatGPT, and any MCP-compatible client.
接入你的智能体
發布者自己的指令。不是 PlugMCP 端點。
用我們的金鑰與日誌託管一份副本。
uvx memory-os-ai==3.0.1Claude Code 沒有本機指令的安裝連結。複製下方指令並在終端機中執行。
claude mcp add io.github.romainsantoli-web-memory-os-ai -- uvx memory-os-ai==3.0.1在終端機中執行。
{ "mcpServers": { "io.github.romainsantoli-web-memory-os-ai": { "command": "uvx", "args": [ "memory-os-ai==3.0.1" ] } }}claude_desktop_config.json
遠端 URL 還是本機指令? 兩種安裝方式的差異
來自發布者
Adaptive memory system for AI agents — universal MCP server for Claude Code, Codex CLI, VS Code Copilot, ChatGPT, and any MCP-compatible client.
Adaptive memory for AI agents — FAISS search, chat extraction, cross-project linking
Memory OS AI transforms your local documents (PDF, DOCX, images, audio) into a semantic memory queryable by any AI model through the MCP (Model Context Protocol).
┌──────────────────────────────────┐
│ AI Client (any MCP-compatible) │
│ Claude Code / Codex / Copilot │
│ ChatGPT / custom agents │
├──────────────────────────────────┤
│ MCP Protocol │
│ stdio / SSE / Streamable HTTP │
├──────────────────────────────────┤
│ Memory OS AI Server │
│ ┌────────┐ ┌───────────────┐ │
│ │ FAISS │ │ Chat Extractor│ │
│ │ Index │ │ (4 sources) │ │
│ └────────┘ └───────────────┘ │
│ ┌────────────────────────────┐ │
│ │ Cross-Project Linking │ │
│ └────────────────────────────┘ │
└──────────────────────────────────┘
--sse), Streamable HTTP (--http)memory://documents/*, memory://logs/conversation, memory://linked/*tesseract (OCR), ffmpeg (audio), antiword (legacy .doc)# macOS
brew install tesseract ffmpeg antiword
# Ubuntu/Debian
sudo apt-get install tesseract-ocr ffmpeg antiword
git clone https://github.com/romainsantoli-web/Memory-os-ai.git
cd Memory-os-ai
pip install -e ".[dev,audio]"
# Setup for your AI client:
memory-os-ai setup claude-code # Claude Code
memory-os-ai setup codex # Codex CLI
memory-os-ai setup vscode # VS Code Copilot
memory-os-ai setup claude-desktop # Claude Desktop
memory-os-ai setup chatgpt # ChatGPT (manual bridge)
memory-os-ai setup all # All of the above
# Check status:
memory-os-ai setup status
# stdio (default — Claude Code, VS Code, Codex)
memory-os-ai
# SSE transport (port 8765)
memory-os-ai --sse
# Streamable HTTP (port 8765)
memory-os-ai --http
Memory-os-ai/
├── src/memory_os_ai/
│ ├── __init__.py # Public API: MemoryEngine, ChatExtractor, TOOL_MODELS
│ ├── __main__.py # python -m memory_os_ai entry point
│ ├── server.py # MCP server — 21 tools, 3 transports, resources
│ ├── engine.py # FAISS engine — indexing, search, compact, session brief
│ ├── cloud_storage.py # 8 cloud backends (GDrive, iCloud, Dropbox, OneDrive, S3, Azure, Box, B2)
│ ├── storage_router.py # Smart routing: local-first with cloud overflow
│ ├── models.py # 21 Pydantic models + TOOL_MODELS registry
│ ├── chat_extractor.py # 4 extractors: Claude, ChatGPT, Copilot, terminal
│ ├── instructions.py # MEMORY_INSTRUCTIONS for AI clients
│ └── setup.py # Auto-setup CLI for 5 AI clients
├── bridges/
│ ├── claude-code/ # CLAUDE.md with memory rules
│ ├── claude-desktop/ # config.json for Claude Desktop
│ ├── codex/ # AGENTS.md for Codex CLI
│ ├── vscode/ # mcp.json for VS Code
│ └── chatgpt/ # mcp-connection.json for ChatGPT
├── tests/ # 410+ tests — 96% coverage
│ ├── test_memory.py # Engine + models (60 tests)
│ ├── test_chat_extractor.py # Chat extraction (39 tests)
│ ├── test_bridges.py # Bridge configs (22 tests)
│ ├── test_gaps.py # Compact, cross-project, resources (34 tests)
│ ├── test_server_dispatch.py # Server dispatch + async (61 tests)
│ ├── test_setup.py # Setup CLI targets
│ ├── test_z_coverage_boost.py # Coverage boost (35 tests)
│ └── test_zz_full_coverage.py # Full coverage (97 tests)
├── pyproject.toml # v3.1.0 — deps, scripts, coverage config + cloud optional deps
├── Dockerfile # Container deployment
└── README.md
When local disk runs low (< 500 MB free by default), memory data automatically overflows to a configured cloud backend.
# Configure via environment (auto-activates on server start)
export MEMORY_CLOUD_PROVIDER=icloud
export MEMORY_CLOUD_CONFIG='{"container": "memory-os-ai"}'
memory-os-ai
# Or configure at runtime via MCP tool:
# memory_cloud_configure(provider="s3", credentials={"bucket": "my-bucket", ...})
# memory_cloud_status() → local disk + cloud usage
# memory_cloud_sync("push") → backup to cloud
# memory_cloud_sync("pull") → restore from cloud
# memory_cloud_sync("auto") → offload if disk low
# Install dev dependencies
pip install -e ".[dev]"
# Run tests
python -m pytest tests/ -v
# Run with coverage
python -m pytest tests/ --cov=memory_os_ai --cov-report=term-missing
# Coverage threshold: 80% (enforced in pyproject.toml)
GNU Lesser General Public License v3.0 (LGPL-3.0). See LICENSE for details.
For commercial licensing, contact [email protected].
Memory OS AI is designed to work alongside the OpenClaw agent infrastructure:
Together they form a complete stack: memory (this repo) → skills & souls (setup-vs-agent-firm) → security & orchestration (mcp-openclaw-extensions).
Contributions welcome! See CONTRIBUTING.md for guidelines.
⚠️ Contenu généré par IA — validation humaine requise avant utilisation.
Adaptive memory for AI agents — FAISS search, chat extraction, cross-project linking
{ "mcpServers": { "io.github.romainsantoli-web-memory-os-ai": { "command": "uvx", "args": [ "memory-os-ai==3.0.1" ] } }}工具
尚無工具清單。遠端伺服器會在首次健康檢查後取得工具清單。
常見問題
在本頁複製適用於 Cursor、Claude Desktop、Claude Code 或 VS Code 的 stdio 設定。它使用發布者的安裝方式,而不是 PlugMCP 代理伺服器。
這筆記錄未列出必要的環境變數。
Memory OS AI 透過 stdio 在本機執行。
上次檢查時間:2026-11-10。 Adaptive memory for AI agents — FAISS search, chat extraction, cross-project linking