Zurück zu Anwendungen Eine App einreichenEinreichen

mem-zero

Docker-Anwendung from sworcery's 2nd Repository

Übersicht

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.

Laufzeit-Argumente

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

Konfiguration der Vorlage

WebUI PortPorttcp

Web dashboard and MCP server HTTP port

Ziel: 8765
Standard: 8765
Wert: 8765

Qdrant PortPorttcp

Qdrant API port (optional, for direct access)

Ziel: 6333

StoragePathrw

Persistent storage for Qdrant data

Ziel: /mem-zero/storage
Standard: /mnt/user/appdata/mem-zero
Wert: /mnt/user/appdata/mem-zero

LLM BackendVariable

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

Ziel: LLM_BACKEND
Standard: bundled
Wert: bundled

Ollama URLVariable

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

Ziel: OLLAMA_BASE_URL

LLM ModelVariable

Ollama language model (only used when backend=ollama)

Ziel: LLM_MODEL
Standard: qwen2.5:7b
Wert: qwen2.5:7b

Embedder ModelVariable

Ollama embedding model (only used when backend=ollama)

Ziel: EMBEDDER_MODEL
Standard: nomic-embed-text
Wert: nomic-embed-text

Embedder DimensionsVariable

Embedding vector dimensions

Ziel: EMBEDDER_DIMENSIONS
Standard: 768
Wert: 768

OpenAI API KeyVariable

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

Ziel: OPENAI_API_KEY

OpenAI Base URLVariable

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

Ziel: OPENAI_BASE_URL
Standard: https://api.openai.com/v1
Wert: https://api.openai.com/v1

OpenAI ModelVariable

Chat model for OpenAI-compatible backend

Ziel: OPENAI_MODEL
Standard: gpt-4o-mini
Wert: gpt-4o-mini

OpenAI Embed ModelVariable

Embedding model for OpenAI-compatible backend

Ziel: OPENAI_EMBED_MODEL
Standard: text-embedding-3-small
Wert: text-embedding-3-small

Bundled ThreadsVariable

CPU threads for bundled LLM inference

Ziel: BUNDLED_THREADS
Standard: 4
Wert: 4

API KeyVariable

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

Ziel: API_KEY

Dashboard UsernameVariable

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

Ziel: DASHBOARD_USER

Dashboard PasswordVariable

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

Ziel: DASHBOARD_PASS

DiagnosticsVariable

Enable performance and accuracy metrics on the dashboard

Ziel: DIAGNOSTICS_ENABLED
Standard: false
Wert: false

Kategorien

Tools > Utilities

Links

Vorlage Unterstützung Registry

Einzelheiten

Repository

ghcr.io/sworcery/mem-zero:latest

Registry

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

Zuletzt aktualisiert2026-06-02

Erstmals gesehen2026-05-04

Führen Sie mem-zero auf Unraid aus.

mem-zero ist gelistet in Community Apps für Unraid OS. Erkunden Sie Unraid, um einen flexiblen Heimserver, ein NAS oder ein Heimlabor aufzubauen.

Erkunden Sie Unraid OS