mem0-aio
jsonbored/mem0-aio:latest
https://hub.docker.com/r/jsonbored/mem0-aio
bridge
sh
false
https://github.com/JSONbored/mem0-aio/issues
https://github.com/JSONbored/mem0-aio
Mem0 OpenMemory gives LLM apps a persistent memory layer with a web UI, MCP/API server, and pluggable vector backends.
[b]All-In-One Unraid Edition[/b]
`mem0-aio` packages the OpenMemory UI, API, and embedded Qdrant into one Unraid-first container so beginners can get a working first boot without wiring a separate vector database.
[b]Quick Install (Beginners)[/b]
1. Install the template and leave the default appdata path in place.
2. For the fastest hosted path, set [code]OPENAI_API_KEY[/code].
3. For the normal local-LLM homelab path, set [code]OLLAMA_BASE_URL[/code] to your external Ollama root URL and set the Ollama chat/embed models you actually have pulled.
4. Start the container and open the Web UI. The wrapper will auto-default to Ollama when [code]OLLAMA_BASE_URL[/code] is set and no explicit provider overrides are supplied.
5. Leave the direct API/MCP port unpublished unless you intentionally need external MCP/API clients behind your own access controls. If you publish it, set [code]MEM0_API_HOST=0.0.0.0[/code] and protect that endpoint yourself.
[b]Advanced View[/b]
- Leave storage defaults in place for the bundled SQLite + Qdrant path.
- If you use external vector storage, configure exactly one backend. The wrapper rejects competing selectors such as Redis plus PGVector plus external Qdrant because OpenMemory can only initialize one vector store at a time.
- Provider overrides are available for native Ollama, OpenAI-compatible endpoints, hosted model providers, and supported external vector stores, but only set the fields your chosen path needs.
[b]Important Notes[/b]
- This wrapper is meant to simplify first boot on Unraid, not remove the real complexity of model/provider credentials and external-service tuning.
- Actual memory generation still requires a valid LLM/embedder configuration. Leaving [code]OPENAI_API_KEY[/code] blank is fine if you are using Ollama, but you still need to provide a reachable Ollama endpoint and valid model names.
- Native Ollama uses the root API URL such as [code]http://host.docker.internal:11434[/code], not an OpenAI-compatible [code]/v1[/code] path. If your reverse proxy adds auth and only exposes an OpenAI-style [code]/v1[/code] endpoint, use the advanced OpenAI-compatible base URL fields instead of the native Ollama provider path.
- The embedded Qdrant service is intentionally bundled for the beginner AIO path; it is skipped only when one valid external vector backend is configured.
### 2026-05-28
- Generated from CHANGELOG.md during release preparation. Do not edit manually.
- Bump mem0 to v2.0.4
AI Productivity Tools:Utilities
http://[IP]:[PORT:3000]
https://raw.githubusercontent.com/JSONbored/awesome-unraid/main/mem0-aio.xml
https://github.com/JSONbored/mem0-aio#readme
https://raw.githubusercontent.com/JSONbored/awesome-unraid/main/icons/mem0.jpeg
ai memory mcp llm openmemory qdrant ollama anthropic groq deepseek embeddings vector database
OpenMemory still needs a valid LLM/embedder setup for actual memory generation. For the easiest first boot, keep bundled storage defaults and either set OPENAI_API_KEY or point the app at a reachable native Ollama endpoint with chat and embedding models you already have pulled. External vector storage is advanced: configure exactly one backend.
https://raw.githubusercontent.com/JSONbored/awesome-unraid/main/screenshots/mem0-aio/01-home.png
https://raw.githubusercontent.com/JSONbored/awesome-unraid/main/screenshots/mem0-aio/02-memories.png
https://raw.githubusercontent.com/JSONbored/awesome-unraid/main/screenshots/mem0-aio/03-settings.png
Support JSONbored on GitHub Sponsors.
https://github.com/sponsors/JSONbored
bridge
3000
3000
tcp
/mnt/user/appdata/mem0-aio/storage
/mem0/storage
rw
3000
/mnt/user/appdata/mem0-aio/storage
default_user
127.0.0.1
/openmemory-api
default_user
auto
auto
sqlite:////mem0/storage/openmemory.db
127.0.0.1
6333
true
true
true
true
true