Holon

Holon is a local workbench for agents doing continuous work.

Holon itself is not an agent. It provides a local working environment for multiple agents. Agents understand goals and drive execution; Holon treats work as the core unit, preserving state, organizing context, recording waits and wakes, so tasks that span sessions, commands, human confirmation, or external events can resume at the right time and eventually deliver results back to the operator.

What Holon provides

CapabilityWhat it means
Continuous agent workspaceEach agent has its own continuous working context in Holon, instead of restarting with every terminal, request, or client connection.
Work-first task modelHolon organizes tasks, waits, execution progress, and final delivery as explicit Work, instead of leaving them scattered across conversations.
Event-driven wait and wakeAgents can wait for task results, external events, or operator input, then return to the corresponding work when the condition is satisfied.
Explicit context and trust boundariesHolon distinguishes operator input, external events, tool results, and internal execution traces so information from different origins is not mixed together.
Local-first execution environmentHolon is built for local repositories, shell, worktrees, and development toolchains, letting agents execute tasks in the real working environment.

Keep agent work alive in your local workspace.

Try Holon

Install the latest release with Homebrew:

brew tap holon-run/tap
brew install holon
holon --help

Then configure a model provider, start the local daemon, and connect the TUI:

# Recommended: save an API key in a local credential profile
printf '%s' "$DEEPSEEK_API_KEY" \
  | holon config credentials set --kind api_key --stdin deepseek

holon config providers set deepseek \
  --credential-source credential_profile \
  --credential-kind api_key \
  --credential-profile deepseek

holon config set model.default "deepseek/deepseek-v4-pro"

# Or use a local Codex login session / Codex subscription
holon config set model.default "openai-codex/gpt-5.5"

holon config doctor

holon daemon start
holon daemon status
holon tui

Holon automatically provides a default main agent. You can also create a more specialized agent from a template:

holon agent create builder --template holon-developer
holon agent list

Holon supports built-in providers such as Anthropic, OpenAI, DeepSeek, OpenRouter, Qwen, GLM, Xiaomi, Kimi, and MiniMax. For a fuller setup path, see Getting started, the configuration reference, and supported models.

Core concepts

Holon breaks agent work into a few explicit runtime objects:

Together, these concepts solve one problem: agent work should not depend on a single chat or terminal connection. It should be observable, resumable, waitable, delegable, and deliverable.

Status and compatibility

The current recommended release is v0.15.1.

v0.15.0 is the baseline release where the Holon Rust runtime enters public compatibility maintenance. Starting from this version, the project maintains compatibility expectations for the CLI, daemon/API semantics, and local persistent storage.

Holon is still under active development. The current focus remains the Rust runtime: agent lifecycle, queues, WaitFor/wake, tasks, WorkItems, trust boundaries, local workspaces, and structured delivery.

Project boundaries

Holon focuses on runtime semantics: agent identity, work continuity, execution state, local workspace projection, and operator-visible results.

Adjacent Holon Run projects cover other layers:

When used together, AgentInbox delivers external events to wake Holon; Holon decides what those events mean inside the runtime.

Which docs should I read?