Choose theme
AI Resources
holaOS
holaOS is a local-first desktop workspace where you and coding agents can work from the same projects, memory, files, tools, skills, and apps.
It can run Claude Code, Codex, or the built-in holaOS agent, connect to documented integrations, and use built-in model access or your own provider keys. Local-first describes the workspace, not every connection: selected models and integrations can still send content to outside services. The shared workspace keeps project context and tools that would otherwise be scattered across separate chats and apps. Use this as a first read, not a recommendation. Open the original project before trusting details like terms, limits, privacy, cost, setup, or safety.
What it is
One workspace for you and your agents
Projects can keep their files, memory, tools, skills, apps, and working history together, so a later session does not have to begin from an empty chat.
Why it stands out
Memory, workspaces, and sub-agents together
Claude Code, Codex, and the built-in agent can work inside the same local-first environment, with integrations and model choices available from one place.
Availability
Desktop distribution and source development
The official download releases live in holaOS-releases. The source repository documents desktop development and runtime preparation. The project labels its licence modified Apache 2.0; use the main repository for the current terms.
Why it matters
What makes it useful
HolaApps pairs an app interface with its agent. A person can work in the interface directly and synchronize that live UI context with the agent, rather than describing every change again in a chat message.
What to know
Where it fits
Use holaOS as the desktop workspace around ongoing projects, agents and their files. Claude Code, Codex and the built-in agent can share that workspace; the selected model and integration connections still determine what is sent to outside services. The desktop shell does not replace those providers.
Notable points
What stands out
The README describes shared memory as plain files that people can read and edit. That gives someone maintaining project context a direct way to correct the stored notes, rather than relying only on an agent to remember the correction.
Before using
What to review
Official desktop downloads live in the separate holaOS-releases repository. Source development has different runtime preparation steps.
The project labels its licence modified Apache 2.0. Refer to the main repository for the current terms before choosing a distribution or deployment path.
Local project files and memory are separate from model and integration traffic. Choose the model-access route and connected accounts according to what those services will receive.
For a source build, follow the repository instructions for the desktop environment file and runtime bundle rather than assuming a binary release has the same setup.
Check the current desktop downloads, supported platforms and edition choices, including the documented enterprise path. Decide which model-access route and setup instructions fit the intended work.
Reader fit
Who may find it relevant
People who want ongoing projects, memory, tools, skills, and apps available to more than one coding agent.
Builders comparing local-first desktop workspaces with separate agent applications.
Less relevant for readers looking mainly for a model checkpoint, a small chatbot, or a narrow browser automation helper.
Editorial note
Why LifeHubber lists it
Builders changing the agent runtime can use the local preparation path to try those changes through holaOS's desktop workspace, alongside the project's files and interface. When building the desktop app from source, holaOS offers two runtime preparation paths. desktop:prepare-runtime:local builds from the local runtime source for active development; desktop:prepare-runtime fetches a published runtime bundle. Choose the local path when changing runtime code, and the published path when the desktop build should use the released bundle.
Source links
Source materials
Reader note
Before relying on this entry
LifeHubber lists entries to help readers inspect AI projects, not to endorse them or prove they are safe, suitable, accurate, maintained, or right for a specific use. We do not verify every entry in depth. Before relying on anything listed, review the original materials, terms, privacy practices, limits, and risks that matter for your situation.
What to explore next
Compare where ongoing agent work should live.
holaOS brings people, coding agents, memory, files, skills, apps, and integrations together in one local-first desktop workspace, while selected models and integrations may still call outside services.
More in AI Agents
Keep browsing this category
Explore more AI agent projects.
Paperclip
paperclipai/paperclip
A self-hosted server and dashboard for coordinating agent teams through companies, goals, roles, issues, heartbeats, budgets, approvals, and persistent activity records.
Harness²
google-research/harness2
A Google Research framework for recursively refining the prompts, tools, memory and other components around a fixed model, with parallel and sequential experiments, saved harnesses and a credential-free local demo.
Open Science
aipoch/open-science
A local desktop workbench that connects research projects, AI agents, files, code execution, scientific data connectors, artifacts, previews, and an inspectable activity history.
For project maintainers
Listed here? You can use the badge.
If you maintain a project with a current LifeHubber listing, you may add the optional “Listed on LifeHubber AI Resources” badge to its README, docs, or website. No introduction or permission request is needed.
