Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@Memex search for that Python API client we discussed last month"
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.
One Memory. All CLIs. Never Compacted. Exact Search.
Session history management for AI coding assistants. Never lose your conversations again.
On-demand search - You control when to search; automatic injection is opt-in
Original preservation - Raw messages always kept; summaries are optional layers
Multi-CLI support - Claude Code, Codex, OpenCode, Gemini in one database
Powerful search - Full-text (FTS5) + semantic vectors + hybrid ranking
MCP integration - Search directly from your AI CLI
REST API - Integrate into any workflow
Local storage - All data stays on your machine
Related MCP server: Claude Code History MCP
brew install vimo-ai/tap/memex
# Verify server is running
curl http://localhost:10013/healthZero-dependency CLI, reads local session data directly:
brew install vimo-ai/tap/memex-lite
memex search "anything you want"
memex list -n 10macOS / Linux:
docker run -d -p 10013:10013 \
-v ~/.vimo:/data \
-v ~/.claude/projects:/claude:ro \
-v ~/.codex:/codex:ro \ # 可选: Codex
-v ~/.local/share/opencode:/opencode:ro \ # 可选: OpenCode
-v ~/.gemini/tmp:/gemini:ro \ # 可选: Gemini
-e OLLAMA_HOST=http://host.docker.internal:11434 \ # 可选: 本机 Ollama (Docker Desktop)
ghcr.io/vimo-ai/memex:latestWindows (PowerShell):
docker run -d -p 10013:10013 `
-v "$env:USERPROFILE\.vimo:/data" `
-v "$env:USERPROFILE\.claude\projects:/claude:ro" `
-v "$env:USERPROFILE\.codex:/codex:ro" ` # 可选: Codex
-v "$env:LOCALAPPDATA\opencode:/opencode:ro" ` # 可选: OpenCode
-v "$env:USERPROFILE\.gemini\tmp:/gemini:ro" ` # 可选: Gemini
-e OLLAMA_HOST=http://host.docker.internal:11434 ` # 可选: 本机 Ollama (Docker Desktop)
ghcr.io/vimo-ai/memex:latestBinary downloads available at Releases.
# Claude Code
claude mcp add memex -- npx -y mcp-remote http://localhost:10013/api/mcp
# Codex
codex mcp add memex -- npx -y mcp-remote http://localhost:10013/api/mcp
# Gemini
gemini mcp add --transport http memex http://localhost:10013/api/mcp
# OpenCode - edit ~/.config/opencode/opencode.json
# { "mcp": { "memex": { "type": "remote", "url": "http://localhost:10013/api/mcp" } } }Then search in your AI CLI:
use memex search "anything you want"Auto-inject relevant memory context into Claude Code sessions. See Hook Documentation for setup.
Join our Discord server for discussions, support, and updates.
This server cannot be deployed
Persistent memory for Claude Code and Cursor. Stop re-explaining your project every session.
One searchable history across every AI coding tool, with secret scanning and a shared task board.
Private persistent memory for Claude, ChatGPT & Gemini via MCP - semantic search, zero-code setup.
Persistent cross-session memory shared by Codex, Claude Code, ChatGPT, and other AI agents.