mem-zero

Docker app from sworcery's 2nd Repository

Overview

Self-hosted memory server for AI coding assistants. Store, search, and manage persistent context across sessions so your tools remember what happened last week without stuffing everything into the context window. Each project gets its own isolated vector collection with automatic fact extraction, deduplication, and semantic search. Works with Claude Code, Cursor, Windsurf, and any MCP-compatible client. Includes a bundled LLM for zero-config operation, or connect to Ollama or OpenAI for better quality. Web dashboard included for browsing and managing memories.

Runtime arguments

Web UI: http://[IP]:[PORT:8765]/
Network: bridge
Shell: bash
Privileged: false
Extra Params: --add-host=host.docker.internal:host-gateway

Template configuration

WebUI PortPorttcp

Web dashboard and MCP server HTTP port

Target: 8765
Default: 8765
Value: 8765

Qdrant PortPorttcp

Qdrant API port (optional, for direct access)

Target: 6333

StoragePathrw

Persistent storage for Qdrant data

Target: /mem-zero/storage
Default: /mnt/user/appdata/mem-zero
Value: /mnt/user/appdata/mem-zero

LLM BackendVariable

LLM backend: bundled (self-contained), ollama, or openai. Auto-detected if not set.

Target: LLM_BACKEND
Default: bundled
Value: bundled

Ollama URLVariable

Ollama API base URL (only used when backend=ollama)

Target: OLLAMA_BASE_URL

LLM ModelVariable

Ollama language model (only used when backend=ollama)

Target: LLM_MODEL
Default: qwen2.5:7b
Value: qwen2.5:7b

Embedder ModelVariable

Ollama embedding model (only used when backend=ollama)

Target: EMBEDDER_MODEL
Default: nomic-embed-text
Value: nomic-embed-text

Embedder DimensionsVariable

Embedding vector dimensions

Target: EMBEDDER_DIMENSIONS
Default: 768
Value: 768

OpenAI API KeyVariable

API key for OpenAI-compatible backend (only used when backend=openai)

Target: OPENAI_API_KEY

OpenAI Base URLVariable

Base URL for OpenAI-compatible API (works with Groq, Anthropic, etc.)

Target: OPENAI_BASE_URL
Default: https://api.openai.com/v1
Value: https://api.openai.com/v1

OpenAI ModelVariable

Chat model for OpenAI-compatible backend

Target: OPENAI_MODEL
Default: gpt-4o-mini
Value: gpt-4o-mini

OpenAI Embed ModelVariable

Embedding model for OpenAI-compatible backend

Target: OPENAI_EMBED_MODEL
Default: text-embedding-3-small
Value: text-embedding-3-small

Bundled ThreadsVariable

CPU threads for bundled LLM inference

Target: BUNDLED_THREADS
Default: 4
Value: 4

API KeyVariable

API key for MCP and REST endpoints (leave empty to disable). Generate one with: openssl rand -hex 32

Target: API_KEY

Dashboard UsernameVariable

Username for web dashboard login (leave empty to disable auth)

Target: DASHBOARD_USER

Dashboard PasswordVariable

Password for web dashboard login (leave empty to disable auth)

Target: DASHBOARD_PASS

DiagnosticsVariable

Enable performance and accuracy metrics on the dashboard

Target: DIAGNOSTICS_ENABLED
Default: false
Value: false

Links

Template Support Registry

Details

Repository

ghcr.io/sworcery/mem-zero:latest

Registry

https://github.com/sworcery/mem-zero

Last Updated2026-05-31

First Seen2026-05-04

Run mem-zero on Unraid.

mem-zero is listed in Community Apps for Unraid OS. Explore Unraid to build a flexible home server, NAS, or homelab.

Explore Unraid OS