Olares Personal Cloud OS
A self-hosted personal cloud for running AI agents, local models, and apps on hardware you own.
- Source repo
- beclab/Olares
- Stars
- ★ 5.3k
- Last updated
- today
- License
- AGPL-3.0
- Primary language
- Go
- FA score
- Insufficient evidence
At a glance
- How it runs
- Works with
- Platform-specific
- Cost
- Free, no paid service needed
- Setup effort
- High · needs real infrastructure
- You'll need
- Typical use
- A home-server owner who wants to run local models and agents such as OpenClaw without placing personal files and history on third-party servers.
- Not a fit if
- Users with only an HDD or under 150 GB SSD; install fails
- Individuals unwilling to run Kubernetes, storage, and networking
- Windows or macOS users; the script targets Ubuntu 22.04–25.04 and Debian 12/13
- Source review
- Insufficient evidence 8 safety controls not found
What does this agent do, and when should you use it?
Olares is an open-source personal cloud operating system built on Kubernetes for individuals and small teams that want to run AI agents, LLMs, and applications on their own hardware. Its repository is organized around built-in apps, olares-cli, the olaresd system daemon, system services, infrastructure, cloud-native platform components, and device-specific code. The platform presents compute, storage, networking, GPU resources, and applications through browser-based access. Olares Market is intended for one-click installation of open-source AI apps and models, while built-in system apps include Files, Vault, Market, Dashboard, and Control Hub. The documented Linux script targets bare metal or VMs, with separate installation paths noted for Windows, macOS, Raspberry Pi, and VMs.
An operator creates an Olares ID, then runs curl -fsSL https://olares.sh | bash - on a supported Linux host to download and execute the official installer. Activation can continue in a guided web wizard or through olares-cli, which the repository describes for activation, management, and diagnosis. Olares pools compute, storage, networking, and GPU resources across nodes, offering GPU time-slicing, memory-slicing, and exclusive GPU modes for AI, media, and gaming workloads. Its Files app works with local files, synced data, connected cloud storage, and external SMB/NFS shares, with configurable backups; the network layer supplies a private VPN, reverse proxy, and public, private, or internal entrances. After activation, the desktop is reached in a browser at an Olares-ID-based address, such as https://desktop.marvin123.olares.com.
- A home-server owner who wants to run local models and agents such as OpenClaw without placing personal files and history on third-party servers.
- A homelab operator with multiple nodes and GPUs who needs pooled accelerator capacity for local AI, media, or gaming workloads.
- A remote worker who needs browser, desktop, and phone access to self-hosted services through an Olares ID and LarePass.
- A family or small team consolidating local files, synced data, cloud storage, and SMB/NFS shares behind one file interface with backups.
- A developer building, testing, and running agentic applications or workflows in isolated Olares environments.
- A privacy-conscious user transcribing meetings, translating recordings, or generating speech locally rather than uploading audio to a third party.
How do you install or deploy this agent?
Create an Olares ID in LarePass first. For the documented Linux script, prepare a bare-metal or VM host with at least 4 CPU cores, 8 GB available RAM, and 150 GB available SSD storage; Ubuntu 22.04–25.04 and Debian 12 or 13 are supported, and installation fails on an HDD. Run:
curl -fsSL https://olares.sh | bash -This downloads and runs the official installer with Bash. Finish activation in the web wizard or use olares-cli for terminal activation. A dedicated GPU is optional, but enables local AI acceleration.
How do you use this agent?
After activation, open the browser desktop address based on the Olares ID; for example, an ID of marvin123 uses https://desktop.marvin123.olares.com. Install open-source AI apps and models from Market, use Files for local, synced, cloud, and SMB/NFS data, and use Dashboard, Control Hub, and olares-cli for system operation and diagnosis. For remote access, use the Olares ID and LarePass capabilities described for secure login, VPN, and file sync.
What are this agent's strengths and limitations?
- Combines Kubernetes-based compute, storage, networking, application management, and GPU management in one self-hosted personal-cloud system, rather than focusing only on network storage.
- Documented GPU controls include cross-node pooling, time-slicing, memory-slicing, and exclusive modes for several workload types.
- The Files app brings together local files, synced data, cloud storage, and SMB/NFS shares, with configurable backups.
- Private VPN, reverse proxy, and public, private, or internal entrances provide application access without manually exposing each port.
- The Linux script has specific host limits: Ubuntu 22.04–25.04 or Debian 12/13, at least 4 cores, 8 GB available memory, and 150 GB SSD; HDD installation fails.
- Initial activation requires an Olares ID, with LarePass used for the documented secure login, VPN, and file-sync workflow.
- Operating the full stack means taking on Kubernetes, storage, networking, system-service, and application administration beyond a storage-only appliance.
- A dedicated GPU is optional, but users who need local AI acceleration must supply one.
How does this agent compare with similar options?
The repository distinguishes Olares from a traditional NAS: NAS systems primarily focus on network storage, while Olares is positioned as an all-in-one self-hosted personal cloud covering compute, storage, networking, and applications.
Key facts side by side with the most closely related agents.
| Agent | Source review | Form / cost | Stars | Updated | Language | Full support on |
|---|---|---|---|---|---|---|
| Olares Personal Cloud OS This agent | Insufficient evidence | CLIFree | ★ 5.3k | today | Go | — |
| taOS Self-Hosted Agent OS | 71 · Some gaps | Self-hosted serviceFree | ★ 603 | today | Python | Claude Code · OpenAI API · Claude API |
| ODS Private AI Server | 71 · Some gaps | CLIFree | ★ 7.8k | 2d ago | Python | OpenAI API · Claude API |
| Sim AI Workspace | 71 · Some gaps | CLIFreemium | ★ 30k | 1d ago | TypeScript | OpenAI API · Claude API |
How does FollowAgents rate this agent?
Why each dimension lost points
Insufficient evidence: The repository does not provide details on permission model, user confirmation, data flow transparency, sensitive data handling, dependency security, external effects, rollback, or source attribution. README mentions security policy and install script but no implementation details. Hence all criteria scored 0.
Insufficient evidence: No details on self-consistency, dependency availability, or failure messages. README and test scripts do not show error handling or dependency management. Hence all criteria scored 0.
Insufficient evidence: README describes target users and scenarios but lacks details on capability boundaries, trigger precision, or environment fit. Hence all criteria scored 0.
Insufficient evidence: README provides project navigation and install instructions but lacks details on information architecture, naming stability, examples/FAQ, known limitations, versioning, or maintenance responsibility. LICENSE file exists but inconsistency (LICENSE is AGPL-3.0, LICENSE.md is custom) leads to license criterion scored 0.
Insufficient evidence: No details on output usability, marginal value, or cost-benefit. README claims features but no evidence. Hence all criteria scored 0.
Insufficient evidence: No details on claim traceability, cross-source corroboration, or fact/inference separation. README claims not linked to code or tests. Hence all criteria scored 0.
- Not found in source: least-privilege scopingGrant only what the task needs: a dedicated account or read-only token, scoped to specific directories and repos.
- Not found in source: confirmation before actingTurn on (or add) a confirmation step before it acts, and try it in a sandbox or test environment before real data.
- Not found in source: data-flow disclosureWatch which external services it contacts (proxy or firewall logs) and keep sensitive data out until you know where it goes.
- Not found in source: sensitive-data handlingUse dedicated, low-privilege, revocable API keys — never production credentials — and keep secrets out of logs.
- Not found in source: dependency securityPin versions and run a dependency audit (npm audit, pip-audit) before installing; prefer running it in a container.
- Not found in source: disclosed external effectsEstablish which external systems it writes to, sends to or changes, and verify with test accounts or repos before production.
- Not found in source: rollback or recovery pathBack up first, or work on a git branch or snapshot, so its changes can be undone.
- Not found in source: verifiable attributionInstall from the official repo or registry and check the publisher and URL to avoid look-alike packages.
- The repository contains multiple license files (LICENSE is AGPL-3.0, LICENSE.md is custom), which is inconsistent and may cause legal confusion.
- The install script is executed via curl pipe, posing supply chain risk; users should review the script content.
- Workflow files reference Tencent Cloud secrets, but it is not verified if they are securely stored, posing leakage risk.
Recent releases
Latest entries from the project's GitHub Releases. Notes are quoted from upstream as written, not rewritten or tested by FollowAgents.
FAQ
Is a GPU required?
Can the documented Linux script install on an HDD?
Do I need an account before activation?
olares-cli.