Choose theme
AI Resources
cabinet
Cabinet is a knowledge base and agent workspace whose content lives in ordinary files on disk.
Its runtime serves a cabinet directory containing the content, agent definitions, and scheduled jobs; the app installs separately. 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
A file-based AI workspace
A cabinet directory holds Markdown pages and the definitions for its agents and jobs. The CLI can create a new directory or serve one you already have.
Why it stands out
Page edits have a history
Saves become Git commits, with a diff viewer and page restoration. You can inspect a changed research note and return to an earlier version.
Availability
Run a cabinet directory
The public project provides a runtime CLI and desktop packages. The CLI downloads the app bundle separately from your knowledge-base directory.
Why it matters
What makes it useful
For project context that needs to survive individual chats, Cabinet gives the work its own directory of content, agents, and job definitions. The CLI can serve that directory again without creating a new knowledge base.
What to know
Where it fits
Agent tasks and scheduled runs use provider adapters with persisted conversations. The current local adapters run Claude Code or Codex CLI; a local adapter does not mean the selected model runs locally.
Notable points
What stands out
A skill can be attached to an agent or mentioned with @ in the composer for one task. That lets a reader choose between a recurring skill and one needed only for the current request.
Before using
What to review
The source setup requires Node.js 22+ and a supported CLI provider.
Authentication is off when KB_PASSWORD is empty. Setting it enables the shared password gate; it does not create separate user accounts.
Usage telemetry is enabled by default. The telemetry documentation also describes server-side IP and approximate-location collection; Settings > Privacy or CABINET_TELEMETRY_DISABLED can turn emission off.
App updates and cabinet content are separate. The CLI uninstall command removes cached app versions, while cabinet directories remain on disk.
Reader fit
Who may find it relevant
Builders keeping project content and agent work in a directory they can manage.
Readers choosing how to install, update, and run a self-hosted knowledge base.
Plan for a workspace runtime and a CLI provider, rather than a Markdown folder alone.
Editorial note
Why LifeHubber lists it
A knowledge-base page can also contain a tool: Cabinet renders an index.html file placed in a folder as an embedded app. For a small HTML calculator or interactive reference, that gives the reader a way to use it inside the workspace, with its files kept in Git alongside the notes.
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.
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.
Universal Modder
rehan-remade/universal-modder
Agent skills and a Python CLI for PC game modding, with engine research, generated assets, in-game checks, and shared field notes. Setup and compatibility depend on the game and workflow; fal generation requires a separate API key.
Agency Agents
msitarzewski/agency-agents
Reusable specialist instruction files, including design roles for image prompts, UI components and visual specifications, with installers and converters for AI coding tools.
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.
