Self-hosted dashboard and admin auth (#4837)

Co-authored-by: kartik-mem0 <kartik.labhshetwar@mem0.ai>
This commit is contained in:
Gabriel Stein
2026-04-23 19:06:36 +05:30
committed by GitHub
co-authored by kartik-mem0
parent 15feaa8ac4
commit db8ac61713
252 changed files with 20275 additions and 331 deletions
+19 -21
View File
@@ -15,12 +15,15 @@ Mem0 Open Source delivers the same adaptive memory engine as the platform, but p
- **Extendable codebase**: Fork the repo, add providers, and ship custom automations.
<Info>
Begin with the <Link href="/open-source/python-quickstart">Python quickstart</Link> (or the Node.js variant) to clone the repo, configure dependencies, and validate memory reads/writes locally.
Two ways to run Mem0 OSS: as a **library** inside your app (Python or Node), or as a **self-hosted server** with a dashboard, per-user API keys, and a request audit log.
</Info>
## Choose your path
<CardGroup cols={2}>
<CardGroup cols={3}>
<Card title="Self-hosted setup" icon="rocket-launch" href="/open-source/setup">
Run `make bootstrap` to launch the server + dashboard, create an admin, and issue your first API key.
</Card>
<Card title="Python Quickstart" icon="python" href="/open-source/python-quickstart">
Bootstrap CLI and verify add/search loop.
</Card>
@@ -41,15 +44,6 @@ Mem0 Open Source delivers the same adaptive memory engine as the platform, but p
</Card>
</CardGroup>
<CardGroup cols={2}>
<Card title="Deploy with Docker Compose" icon="server" href="/open-source/features/rest-api">
Reference deployment with REST endpoints.
</Card>
<Card title="Use the REST API" icon="code" href="/open-source/features/rest-api">
Async add/search flows and automation.
</Card>
</CardGroup>
<Tip>
Need a managed alternative? Compare hosting models in the <Link href="/platform/platform-vs-oss">Platform vs OSS guide</Link> or switch tabs to the Platform documentation.
</Tip>
@@ -70,19 +64,27 @@ Mem0 Open Source delivers the same adaptive memory engine as the platform, but p
## Default components
<Note>
Mem0 OSS works out of the box with sensible defaults:
**Library defaults** (when you `import` Mem0 and call `Memory()` directly):
- LLM: OpenAI `gpt-5-mini` (via `OPENAI_API_KEY`)
- Embeddings: OpenAI `text-embedding-3-small`
- Vector store: Local Qdrant instance storing data at `/tmp/qdrant`
- History store: SQLite database at `~/.mem0/history.db`
- Reranker: Disabled until you configure a provider
- Vector store: Local Qdrant at `/tmp/qdrant`
- History store: SQLite at `~/.mem0/history.db`
- Reranker: Disabled until configured
Override any component with <Link href="/open-source/configuration">`Memory.from_config`</Link>.
</Note>
## Keep going
<Note>
**Self-hosted server defaults** (the `server/` Docker Compose stack):
- LLM: OpenAI `gpt-4.1-nano-2025-04-14` (override with `MEM0_DEFAULT_LLM_MODEL`)
- Embeddings: OpenAI `text-embedding-3-small` (override with `MEM0_DEFAULT_EMBEDDER_MODEL`)
- Vector store: Postgres + pgvector
- Bundled providers: `openai`, `anthropic`, `gemini` — switch from the Configuration page
{/* DEBUG: verify CTA targets */}
See <Link href="/open-source/setup#supported-providers">Self-Hosted Setup</Link> for the full provider list and how to extend it.
</Note>
## Keep going
<CardGroup cols={2}>
<Card
@@ -98,7 +100,3 @@ Mem0 Open Source delivers the same adaptive memory engine as the platform, but p
href="/open-source/python-quickstart"
/>
</CardGroup>
<Tip>
Need a managed alternative? Compare hosting models in the <Link href="/platform/platform-vs-oss">Platform vs OSS guide</Link> or switch tabs to the Platform documentation.
</Tip>