Skip to content
Browse docs
On this page

Architecture comparison: self-hosted AI assistants vs. agent runtimes

If you are evaluating self-hosted AI assistants (including open-source alternatives to Grok Bot or OpenClaw) or comparing agent runtimes, most tools fall into three different architectural layers. Comparing them on surface features alone—such as whether they bundle voice or browser panels—hides the core question: who owns task execution, waits, isolation, and trust boundaries?

Three architectural layers

CategoryExamplesWho owns the agent loopPrimary strengthTrade-off
Self-owned agent runtimeHolon (Rust daemon)Holon itself (holon)Persistent WorkItems, event-driven wait/wake, linked git worktree isolation, explicit origin/trust boundaries, model-agnostic routingSmaller ecosystem connector surface today (no built-in MCP client, voice, or bundled browser)
Orchestration shells over external coding CLIsOpenMausBot, Codync, nightly-labs/OpenBotExternal CLIs (Claude Code, Codex, Cursor, OpenCode, etc.)Inherit existing CLI subscriptions, skills, and MCP servers; strong desktop/mobile/voice UX and shared chat surfacesExecution lifecycle, recovery, and permission boundaries depend on the wrapped CLI
Embedded-runtime apps & closed cloud botsRakazo (embeds Pi), Grok Bot (xAI closed cloud)Embedded JS runtime or vendor cloud hostFast consumer onboarding; cloud workspaces, built-in voice, or mobile per-action UISingle-vendor lock-in (cloud) or Docker/harness coupling without a Rust daemon

Where Holon differs in runtime behavior

Surface feature tables usually ask whether a tool has a desktop shell, mobile client, or scheduled routines. For long-running work on your own computer or server, the harder failures happen at the runtime layer:

  1. Work survives client disconnects and restarts. Clients (Web GUI, TUI, macOS menu bar app, iOS/Android remote clients) connect to one background holon daemon. Tasks (TaskHandle) and durable objectives (WorkItem) live in runtime-managed SQLite state rather than inside a browser tab or terminal multiplexer.
  2. Explicit wait and wake semantics. Agents pause cleanly on WaitFor conditions (task_result, timer, external, operator_input) instead of polling in a loop. An incoming webhook or schedule acts as a wake hint that triggers re-verification—external triggers do not automatically grant operator authority.
  3. Origin and trust separation. The runtime distinguishes operator instructions, agent-authored guidance, tool results, child agent reports, and external webhook/app payloads. Untrusted external text read during a task cannot self-escalate into operator commands.
  4. Workspace and parallel branch isolation. Each agent separates its persistent agent_home (identity, memory, notes, private state) from attached project workspaces. Parallel work on a repository uses registered linked git worktree roots (CreateWorktree / RemoveWorktree) with active occupancy checks so concurrent tasks do not overwrite each other.
  5. Model-agnostic local and cloud routing. Holon runs against OpenAI-compatible endpoints, Anthropic, Gemini, and local inference servers such as Ollama or llama.cpp, without requiring a specific vendor coding CLI subscription.

Surface capabilities and shipped boundaries

When comparing Holon with Grok Bot or CLI-orchestrated self-hosted assistants, evaluate both what is shipped and what is intentionally absent today:

DimensionHolon today (verified in repository)Notes for evaluators
Runtime & deploymentRust binary (holon), local daemon, Docker imageSingle-host daemon; Linux amd64, macOS arm64/amd64
ClientsWeb GUI, TUI, CLI, macOS menu bar (HolonMenu), iOS & Android remote appsMobile apps are remote clients connected to your daemon, not on-device agents
Multi-agent & templates25+ checked-in agent_templates, InvokeAgent supervised children, peer SendAgentMessageRole-scoped skills/, separate agent_home, explicit cleanup rules
Routines & external eventsPersistent timers (interval_ms / calendar_expression), webhook ingress, AgentInboxWaking an agent never bypasses trust or verification checks
Host executionWorkspace-scoped shell commands, patches, background command_tasksHost-local execution (host_local), not GUI desktop mouse/screen automation or VM-per-action
MCP supportNot built inExternal CLI tools are wrapped via skills/; no native MCP client or server yet
Live voice (TTS/STT)Not built inText/media/artifact workflows only
Integrated browserNot built inNo bundled headless browser engine inside the runtime; external browser skills are optional
Desktop shell coveragemacOS menu bar app + cross-platform Web GUI & TUINo native Windows or Linux Electron/desktop wrapper

Choosing the right fit

  • Choose Holon if you want a self-hosted, model-agnostic AI assistant workbench on your own machine or server where agents track multi-turn work items, wait on CI/timers/webhooks without burning loops, isolate parallel repo edits in git worktrees, and enforce explicit trust boundaries.
  • Choose a CLI orchestration shell (such as OpenMausBot, Codync, or nightly-labs/OpenBot) if your primary goal is putting a chat/voice/mobile UI over existing Claude Code, Codex, or Cursor CLI sessions and immediately reusing their MCP ecosystems.
  • Choose a hosted cloud bot (such as Grok Bot) if you prefer zero local setup and vendor-hosted execution over self-hosting, local repository access, and model choice.

How to verify these claims locally

You do not need a synthetic test harness to verify Holon's runtime behavior. Follow the regular user guides on your own machine and inspect the runtime state with read-only commands:

  1. Restart survival & zero-token waits: Follow Run a long-lived task. While a task is waiting, inspect active items and timers, then restart the daemon:
    holon work-item list --agent main
    holon timer list --agent main
    holon daemon stop && holon daemon start
    holon daemon status
    
    The same WorkItem and timer remain persisted across the restart and resume at fire time without polling loops.
  2. Physical Git worktree isolation: Follow Work in a project workspace or Git worktree and run git worktree list in your repository. Agent edits stay in the linked worktree branch while your primary working tree stays untouched.
  3. External wake & trust separation: Follow Connect external events. External webhook callbacks wake the agent as an untrusted wake_hint; they never grant operator authority or bypass ground-truth verification.

Scope note: Holon is a single-host daemon (not replicated HA), a parked wait means the agent is suspended rather than spinning, and an external wake confirms trigger delivery—not authenticity of third-party payload claims.

Next reading