Retour aux applications Soumettre une applicationSoumettre

mem-zero

Application Docker from sworcery's 2nd Repository

Vue d'ensemble

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.

Arguments d'exécution

Interface utilisateur Web: http://[IP]:[PORT:8765]/
Réseau: bridge
Coquille: bash
Privilégié: false
Paramètres supplémentaires: --add-host=host.docker.internal:host-gateway

Configuration du modèle

WebUI PortPorttcp

Web dashboard and MCP server HTTP port

Cible: 8765
Défaut: 8765
Valeur: 8765

Qdrant PortPorttcp

Qdrant API port (optional, for direct access)

Cible: 6333

StoragePathrw

Persistent storage for Qdrant data

Cible: /mem-zero/storage
Défaut: /mnt/user/appdata/mem-zero
Valeur: /mnt/user/appdata/mem-zero

LLM BackendVariable

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

Cible: LLM_BACKEND
Défaut: bundled
Valeur: bundled

Ollama URLVariable

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

Cible: OLLAMA_BASE_URL

LLM ModelVariable

Ollama language model (only used when backend=ollama)

Cible: LLM_MODEL
Défaut: qwen2.5:7b
Valeur: qwen2.5:7b

Embedder ModelVariable

Ollama embedding model (only used when backend=ollama)

Cible: EMBEDDER_MODEL
Défaut: nomic-embed-text
Valeur: nomic-embed-text

Embedder DimensionsVariable

Embedding vector dimensions

Cible: EMBEDDER_DIMENSIONS
Défaut: 768
Valeur: 768

OpenAI API KeyVariable

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

Cible: OPENAI_API_KEY

OpenAI Base URLVariable

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

Cible: OPENAI_BASE_URL
Défaut: https://api.openai.com/v1
Valeur: https://api.openai.com/v1

OpenAI ModelVariable

Chat model for OpenAI-compatible backend

Cible: OPENAI_MODEL
Défaut: gpt-4o-mini
Valeur: gpt-4o-mini

OpenAI Embed ModelVariable

Embedding model for OpenAI-compatible backend

Cible: OPENAI_EMBED_MODEL
Défaut: text-embedding-3-small
Valeur: text-embedding-3-small

Bundled ThreadsVariable

CPU threads for bundled LLM inference

Cible: BUNDLED_THREADS
Défaut: 4
Valeur: 4

API KeyVariable

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

Cible: API_KEY

Dashboard UsernameVariable

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

Cible: DASHBOARD_USER

Dashboard PasswordVariable

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

Cible: DASHBOARD_PASS

DiagnosticsVariable

Enable performance and accuracy metrics on the dashboard

Cible: DIAGNOSTICS_ENABLED
Défaut: false
Valeur: false

Catégories

Tools > Utilities

Liens

Modèle Soutien Registre

Détails

Référentiel

ghcr.io/sworcery/mem-zero:latest

Registre

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

Dernière mise à jour2026-06-01

Première vue2026-05-04

Exécutez mem-zero sur Unraid.

mem-zero est listé dans Community Apps pour Unraid OS. Explorez Unraid pour créer un serveur domestique flexible, un NAS ou un laboratoire domestique.

Explorez Unraid OS