Spin up a self-managing AI agent team in minutes.
One CLI + built-in web console. Agents that plan, execute, and talk to each other — while you sleep.

中文文档  |  Quick Start  |  Install  |  Commands  |  Workspace Layout

agencycli is a lightweight CLI for building and operating teams of AI agents. You define the org chart once — teams, roles, projects, skills — and agents assemble their own context, pick up tasks, and run autonomously on a heartbeat schedule.

The killer feature: agents can hire, message, and coordinate with each other. Your PM agent can create a task for the dev agent, the dev agent can ask a human for confirmation before merging, and the QA agent wakes up every 30 minutes to scan for open PRs — all without you lifting a finger.

Context composes from two axes — role (horizontal) and project (vertical). Every agent gets agency → team → role → project context merged automatically at hire time. Change a role prompt once; every agent with that role gets it on the next sync.

Agents wake up on a schedule, drain their task queue, then — when the queue is empty — execute a wakeup routine (wakeup.md) to proactively find new work. Time windows, active days, cron schedules — all configurable. Startup jitter prevents thundering herd when the scheduler restarts.

Every participant (agent or human) has an inbox. Messages are non-blocking and async — unread messages are auto-injected at the top of every wakeup prompt. confirm-request creates a blocking gate: the task pauses until you decide.

Bundle your whole agency setup — teams, roles, skills, agent playbooks, project blueprints — into a single .tar.gz. Share it. Apply it to a new project in one command.

Agents run inside isolated Docker containers. No accidental host damage, no credential leaks, no runaway processes. The workspace and agencycli binary are mounted read-write; credentials are mounted read-only.

Skills are a SKILL.md (YAML frontmatter + Markdown prompt) plus optional scripts, deployed into every agent that has the skill bound. Define once, attach to a role, propagate automatically on sync.

The easiest way — send this to Claude Code or any AI coding agent, and it will handle the entire installation and configuration for you:

Follow https://raw.githubusercontent.com/chenhg5/agencycli/refs/heads/main/INSTALL.md to install and configure agencycli.

npm install -g @agencycli/agencycli      # npm, no Go required

go install github.com/chenhg5/agencycli/cmd/agencycli@latest  # Go

# From source (includes web console)
git clone https://github.com/chenhg5/agencycli && cd agencycli && make install

git clone https://github.com/chenhg5/agencycli
cd agencycli
make build          # builds web frontend + Go binary → dist/agencycli
make install        # builds and installs to $GOPATH/bin

# 1. Create a workspace (generates .gitignore + agency-prompt.md)
agencycli create agency --name "MyAgency"
cd MyAgency

# 2. Apply a project blueprint — hires all agents + configures heartbeats + installs playbooks
agencycli create project --name "my-service" --blueprint default
agencycli project apply  --project my-service

# 3. Start the scheduler — agents wake up and run autonomously
agencycli scheduler start

# 4. Open the web console — manage everything from the browser
agencycli start                   # http://127.0.0.1:27892
agencycli start --addr 0.0.0.0:8080 --open   # custom port + auto-open browser

# 5. Check in (CLI)
agencycli inbox list              # task confirmations waiting for your decision
agencycli inbox messages          # async messages from agents
agencycli task list --project my-service --agent pm

The web console is embedded in the binary — no separate process or Node.js required. One command to launch:

agencycli start                          # default: 127.0.0.1:27892
agencycli start --addr 0.0.0.0:8080     # custom address
agencycli start --api-key my-secret     # with auth

Capabilities: workbench (messages + tasks), team/role management, project members, schedule (heartbeat/cron/runtime), run history & token costs, session management, agent run, prompt editing, skills — all with i18n (English / 中文 / 繁體中文 / 日本語) and dark mode.

For local development with hot-reload: agencycli api serve + cd web && pnpm dev.

agencycli is a runtime layer, not an SDK. Agents are whatever CLI tool you already use:

Mix models freely — your PM can run on Claude, your dev agents on Codex, your writer on Gemini. Each gets its context in the exact format its runtime expects.

agencycli
├── start                                  # launch web console (API + frontend)
├── overview                               # CLI dashboard
├── create agency / team / role / project  # scaffold your org
├── hire / fire / sync                     # manage agents
├── task add / list / done / confirm-request # task queue (7-state lifecycle)
├── run / exec                             # manual agent execution
├── inbox send / messages / reply / fwd    # async messaging
├── scheduler start / stop / status        # heartbeat scheduler
├── session show / set / reset             # agent session management
├── cron add / list / delete               # scheduled tasks
├── template pack / info                   # share your setup
├── api serve                              # JSON API only (for dev)
└── --dir <path>                           # work on any agency from anywhere

→ Full command reference
→ Workspace layout
→ Docker sandbox
→ HTTP / OpenAI-compatible agent

Those are frameworks — you write Python to wire agents together. agencycli is infrastructure — you write Markdown and YAML. Agents are whatever CLI tool you already use. No SDK, no lock-in, no server to run.

MIT