mrkeyoor.com_
Wed 12 Aug 16:46 UTC
LLM Toolsevaluationupdated 12 Aug 2026

holaOS

holaOS is an English-documented desktop workspace that lets Codex, Claude Code, and its own agent work over the same files, tools, apps, integrations, and local memory. It solves the fragmentation of keeping separate context and connections for each agent, while offering hosted models or bring-your-own-provider keys.

Verdict

holaOS is worth trying if your real problem is coordinating several agents, integrations, and durable context, because its shared workspace is more substantial than another chat wrapper. Treat it as a powerful operator console, not a privacy appliance: review the hosted defaults, permissions, and modified license before adoption. Individuals can experiment now; security-sensitive teams should pilot it in a constrained workspace first.

Setup3/5Installer automates a sizable Electron and local-runtime bootstrap
Docs4/5Clear install, runtime, memory, MCP, and security documentation
Community4/5Recent pushes, frequent binary builds, and a small active queue
Maturity3/5Broad working surface, but young code and packaging gaps remain

Who it’s for

Developers who regularly switch between Codex, Claude Code, and another agent but want one workspace and memory layer.
Technical users who want MCP servers, connected SaaS tools, a controllable browser, and editable files beside an agent.
Teams prepared to inspect agent permissions and configure provider keys, runtime paths, and integration boundaries.
Organizations using the software internally that can accept the modified license and decide which vendor-hosted services remain enabled.

Who it’s NOT for

Companies intending to resell holaOS as a hosted service or embed substantial parts in a commercial product without negotiating a license: the modified Apache terms explicitly restrict both uses.
White-label desktop products: the license prohibits removing or changing the holaOS logo and copyright information from its frontend.
Users who interpret local-first as air-gapped by default: the supplied desktop environment points authentication, backend, control-plane, and web-app URLs to holaOS-operated domains.
Administrators unwilling to audit broad agent authority: the README advertises access to files, signed-in browsers, integrations, apps, MCP tools, messaging channels, and scheduled automation.
Operators relying on the current Docker runtime build without checking main: an open issue documents missing package-lock files, with a proposed fix still open on August 12, 2026.

Setup reality

The one-line installer is credible for a developer machine, but it is not a tiny desktop download. It can install Git and Node.js 24, clone into a default home-directory path, install a Bun monorepo, build and stage the local runtime, type-check it, and optionally launch Electron. Manual setup exposes the same moving parts, and a clean source build needs an environment file plus native Electron dependencies. Independent deployment adds runtime packaging, bind addresses, local state paths, model-proxy configuration, and optional remote bridges. The published macOS and Windows installers are roughly 450 to 540 MB, while Linux is represented by a runtime archive rather than a comparable desktop installer in the latest binary release.

One desk for agents, apps, and memory

holaOS is built around a useful observation: switching AI agents is easy, but rebuilding their working environment is not. Codex may know one set of project instructions, Claude Code another, and a desktop assistant may hold separate integrations and history. holaOS puts those agents inside one Electron workspace, where they can share files, tools, skills, connected apps, and durable memory.

The interface is meant to show live applications beside the agent instead of reducing every result to chat. A browser, Notion page, or custom HolaApp can remain interactive while the agent operates it. The README also advertises Gmail, Slack, GitHub, Linear, Notion, and more than 50 other one-click connections, community MCP servers, document creation, messaging-channel access, and scheduled automation. This is a much wider target than a coding assistant. It is an attempt at an agent-operated workstation.

That scope is the reason to consider holaOS and the main source of risk. Connecting one process to signed-in browsers, local files, SaaS accounts, tools, and schedules concentrates authority. The repository has a responsible security policy covering credential exposure, remote execution, sandbox escape, privilege escalation, authentication bypass, and unsafe local-runtime defaults. A policy document is not a substitute for your own permission review, especially when an installed MCP server can expose all its discovered tools unless a workspace sets an explicit allowlist.

The local memory design has real substance

Shared memory is holaOS's strongest differentiator. The current design stores canonical durable material as human-readable Markdown, organized into workspace interaction trees and global integration trees. Databases and embeddings act as indexes rather than the only copy. If an index disagrees with the Markdown, the files remain authoritative and derived state can be rebuilt.

The documentation also distinguishes durable knowledge from session residue. Stable facts, procedures, repeated blockers, preferences, and references can survive, while one-off logs and transient failures should not. Workspace paths reject absolute paths and parent traversal, and cross-workspace access is blocked. This is a more thoughtful memory boundary than saving every transcript and hoping retrieval finds the right paragraph. Users can inspect what persists, and teams can back up or version the meaningful files.

MCP support is similarly explicit. A workspace YAML file defines servers and optional tool allowlists. The runtime resolves environment placeholders, starts its sidecar, and passes the permitted tool surface to the selected harness. The catch deserves emphasis: omitting an allowlist, or leaving it empty, means all tools discovered from that configured server can be exposed for the run. Security-conscious deployments should treat allowlists as required configuration, not advanced tuning.

Local-first does not mean offline by default

The source is runnable on your machine, and the independent runtime documentation shows how to place workspaces, state databases, and memory under a chosen sandbox root. Operators can bind the API to localhost, package the runtime for Linux, macOS, or Windows, and override model and bridge endpoints. Bring-your-own keys support OpenAI, Anthropic, and compatible services.

The default desktop template still points authentication, backend, control plane, and web HolaApps to holaOS domains. Built-in models necessarily arrive through the product's service. The honest reading is that workspace execution and memory can be local while some account, model, integration, and app paths are hosted unless you replace or disable them. Anyone with an air-gap, data-residency, or vendor-isolation requirement needs a traffic inventory and a documented configuration, not the phrase local-first.

Licensing also changes the adoption decision. This is not ordinary Apache 2.0 despite the familiar base. Internal commercial use is allowed, but offering the source as a hosted third-party service or embedding substantial parts in a sold product requires written authorization or a commercial license. Frontend users may not remove or alter the product logo and copyright notice. Contributors also agree that the producer may adjust the agreement and use contributed code commercially. Those terms may be acceptable for an internal tool, but platform vendors and white-label products should stop and get legal review.

Setup is automated, not small

A curl-to-shell installer can provision Git and Node.js 24, clone the repository, install dependencies, copy the environment template, build the local runtime, and run type checks. It stops before launching Electron unless asked. The manual guide is unusually precise and tells an automation agent when to stop on type-check or GUI failure.

Behind that convenience is a large Bun and Turbo workspace with Electron, native SQLite, image tooling, multiple runtime services, bundled Node and Python runtimes, and platform packaging. The August binary release contains Windows and macOS installers around 450 to 540 MB and a Linux runtime archive around 430 MB. An open issue from August 8 says the Dockerfile references package-lock files that no longer exist after the workspace moved to Bun; an open pull request addresses it. Source users should expect active-build friction even when the desktop installer works.

Young, active, and worth a constrained trial

The repository was created in March 2026 and last pushed on August 12. GitHub showed six open items combining issues and pull requests, with three true open issues. The separate binary repository published several builds from late July through August 9. That combination indicates fast, current development, though not long production history.

For an individual developer frustrated by fragmented agents, holaOS offers a coherent answer and unusually transparent memory mechanics. For an enterprise, its value rises with the number of tools it can unify, but so does the permission and network review. Start with a disposable workspace, explicit MCP allowlists, minimal integrations, and your own provider key. Adopt it more broadly only after you understand which data stays in local Markdown, which requests use hosted services, and whether its license fits what you plan to distribute.

Alternatives

ProjectWhat it isPick it when
GooseAn Apache-licensed extensible local agent that can edit, execute, and test with different models.pick this instead when you want a focused local coding and automation agent with a standard Apache license, not a multi-app desktop workspace.
OpenHandsAn open platform centered on software-development agents and delegated coding tasks.pick this instead when coding delegation is the main job and shared consumer apps, memory, and browser surfaces are secondary.
Open InterpreterA terminal-oriented coding agent for running open models against a local computer.pick this instead when you prefer a smaller command-line workflow and do not need holaOS's desktop marketplace or shared agent UI.

What people are saying

  1. [github-trending] holaboss-ai/holaOS

Sources

  1. holaOS repository and overview
  2. holaOS modified Apache license
  3. holaOS installation guide
  4. holaOS independent runtime deployment
  5. holaOS default desktop environment
  6. holaOS Docker lockfile issue
  7. holaOS binary releases