v1.20.64see what's new →

agi-cliagi-cli

The meta harness engineering system for agents.

The missing toolchain for CLI coding agents — run any agent on your existing subscription.

$curl -fsSL agi-cli.sh | sh

also available as ag.

PARALLEL SPEEDUPwall-clock1 claude (sequential)47 minagents teams × 318 minagents teams × 511 min4.3×Illustrative: an 8-file, 3-surface refactor split across teammateswith independent boundary contracts. Your task shape sets the ceiling.$ agents teams start my-feature --watch

Trusted by engineers at

GoogleMetaAmazonBlockTikTokY CombinatorActiveloopTuring
01

Run agents

Profiles resolve model, provider, version, and credentials before the underlying CLI starts.

Launch the right agent

One prompt surface for the CLIs you already use. Pin versions per project, swap models through profiles, rotate accounts when quota is tight, and keep the command shape stable. Run docs →

$ agents profiles add kimi
$ agents run kimi "refactor the queue worker"

Rotate, pipe, and pin

The harness keeps quota, model choice, and project defaults out of ad-hoc shell glue. Runs spread across your accounts with the balanced strategy, one agent pipes into another, and the project decides the installed version. Rotation docs →

$ agents run claude --balanced "run the full test suite"
$ agents run claude "Find auth bugs" | agents run codex "Patch them"
$ agents usage
02

Configure once

One config source syncs skills, MCP servers, commands, hooks, and rules into every harness's native format — edit once, every agent sees it.

Install once, sync everywhere

Skills, MCP servers, slash commands, hooks, and permissions install into ~/.agents/ and sync to every active agent version — no more claude mcp add, then codex mcp add, then editing Gemini's config by hand. Sync docs →

$ agents skills add gh:yourname/python-expert
$ agents install mcp:com.notion/mcp
$ agents commands add gh:yourname/commands

One config, every harness

Write one AGENTS.md and it becomes CLAUDE.md, GEMINI.md, and .cursorrules. Resources stack in four layers — system, you, team, project — and an agent sees the merged surface at spawn, highest layer winning. Config layers →

# ~/.agents/ is the canonical source
 system   built-in skills + commands
 you      ~/.agents/
 team     .agents/ (shared repo)
 project  ./.agents/

$ agents doctor
03

Coordinate work

Parallel work gets named teammates, boundary contracts, DAG dependencies, logs, and cloud dispatch — on one machine or across your fleet.

Split work into teammates

Teams add isolated worktrees, --after dependencies, live status, and a durable transcript trail. It is still git and shell underneath; the harness just keeps parallel work legible. Teams docs →

Claude CodeCodexCursorOpenCodeCopilotGrokKimiAntigravity
$ agents teams create checkout
$ agents teams add checkout codex "Owns: app/payments/*" --name payments
$ agents teams add checkout claude "Run Playwright" --name qa --after payments
$ agents teams start checkout --watch

Distribute teammates across machines

Teammates run on other machines over SSH. Declare a device pool and the scheduler places them, or pin a teammate to a specific box; agents doctor --devices shows agent readiness across the fleet. Teams docs →

$ agents teams create feat --devices yosemite-s0,yosemite-s1
$ agents teams add feat claude "Owns: api/*" --name api
$ agents teams start feat --watch
$ agents doctor --devices
04

Command the fleet

Running agents aren't fire-and-forget. Steer them mid-flight, unstick what stalls, and make every machine match — a 1,100-agent fleet reads as dozens of deliverables.

Steer running agents mid-flight

agents feed collapses the fleet under the outcome each agent serves — a Linear ticket, a PR, a worktree. agents message <target> reaches any live run, teammate, or cloud task by name, and the text lands at its next tool call. Fleet docs →

$ agents feed
$ agents message payments "switch to the v2 schema"

Unstick what stalls

agents watchdog detects a stalled session, resolves the exact terminal split it lives in — tmux, iTerm, VSCodium, or a raw pty — and injects a nudge. The fleet keeps moving without you babysitting it. Watchdog docs →

$ agents watchdog

Make every machine match

One machine is set up the way you like it; agents apply installs missing agents, upgrades the CLI, syncs config, and propagates logins — turning six hosts × eight harnesses = 48 OAuth flows into one. Fleet sync docs →

$ agents devices list
$ agents apply
05

Dispatch to the cloud

Some work shouldn't tie up your laptop. Hand it to a managed runner that clones the repo, plans, implements, tests, and opens a PR.

Hand off a task, get a PR

agents cloud run sends a task to Rush Cloud, Codex Cloud, a Factory droid, or Antigravity. It works the repo end-to-end and opens a pull request while your terminal stays free. Cloud docs →

$ agents cloud run "add rate limiting to the API" --provider rush
$ agents cloud list

Fire on GitHub events

Register a run as an event trigger with --on pull_request — also push, issue_comment, and workflow_run. Your repo gets an agent that reacts, with no CI glue to maintain. Event triggers →

$ agents cloud run "review this PR" --provider rush --on pull_request
06

Inspect history

Every transcript lands in one searchable store, so prior attempts are a command away.

Search the run history

Find the debugging trail, the abandoned attempt, or the one command that worked last week. Sessions can be searched, replayed as markdown, filtered by project, and tailed while agents are still running — and sessions focus drops you back into any of them, wherever it lives. Sessions docs →

$ agents sessions "stripe webhook signature"
$ agents sessions a7f3e2c1 --markdown
$ agents sessions --active
$ agents sessions focus a7f3e2c1
07

Extend

Package repeatable orchestration and executable surfaces into named, portable bundles that resolve project → user → system.

Reusable multi-agent pipelines

Workflows bundle an orchestrator prompt with subagents, skills, and plugins into one named invocation. WORKFLOW.md is the orchestrator's system prompt; files under subagents/ dispatch by name, in parallel. Workflow docs →

$ agents run deep-research "compare vector databases"

One bundle, every version

Plugins carry skills, commands, hooks, MCP servers, and permissions under a single manifest, mirrored into every installed version automatically. Switch versions with agents use and the plugin re-syncs — no reinstall. Plugin docs →

$ agents plugins install gh:yourname/security-suite
$ agents plugins list
08

Operate machines

Browser, secrets, routines, PTY, computer, and devices are command surfaces under the same harness.

Reach the environment

The harness reaches the parts agents usually lose: logged-in browser profiles, Keychain bundles, scheduled runs, remote devices, native apps, and interactive terminals. agents run --host puts a whole run on another machine over SSH. Devices docs →

$ agents browser start --profile work --url https://linear.app
$ agents secrets exec prod -- npm run deploy
$ agents pty start -- npm run dev
$ agents run claude --host mac-mini

Schedule background work

Routines turn repeatable agent work into a schedule. Standups, weekly digests, nightly audits, and one-shot follow-ups stay tied to the same agent profiles and logs. Schedule docs →

$ agents routines add standup \
    --schedule "0 9 * * 1-5" \
    --agent claude \
    --prompt "Draft a standup from yesterday's git log"

File a ticket or start a fix from the menu bar

On macOS, press Command-Shift-O (⌘⇧O), describe the problem, add screenshots, and choose File Ticket or Fix. A ticket agent carries every selected file into the issue wherever it fits best. Fix sends the same context to every selected agent. Menu bar docs →

⌘⇧O
describe  checkout email is blank
mode      File Ticket
agent     Claude
files     3 screenshots attached
Why

Use a harness when the same mistakes keep repeating.

Free

The tool is entirely free — the best tools should be in every developer's hands.

No telemetry

The CLI binary has no built-in telemetry or phone-home path.

Your subscription

Run on your own subscription or API key. No Rush account, no upsell.

vs every other way to run agents

Most tools give you one piece. agents gives you all of them.

Capabilityagi-cliClaude Code aloneCursorRun CLIs by handOpenCode
Pin versions per project (.nvmrc-style)
Run multiple agents (Claude + Codex + Grok) from one CLI~
Swap underlying model (Kimi, GLM, DeepSeek via OpenRouter)~
Rotate across multiple accounts to dodge rate limits
Parallel teams with DAG dependencies
Distribute teammates across machines over SSH~
Steer & auto-nudge running agents mid-flight
Managed cloud run that opens a PR~
Reusable multi-agent workflow bundles
Local browser via CDP (drive any site)
Cross-agent session search & replay~~
Cron / scheduled routines~
Keychain-backed secrets (no .env files)
Sync skills/MCP/commands across all installed agents~~
Local-first and open-source — cloud dispatch optional
Pin versions per project (.nvmrc-style)
  • agi-cli
  • Claude Code alone
  • Cursor
  • Run CLIs by hand
  • OpenCode
Run multiple agents (Claude + Codex + Grok) from one CLI
  • agi-cli
  • Claude Code alone
  • Cursor
  • Run CLIs by hand~
  • OpenCode
Swap underlying model (Kimi, GLM, DeepSeek via OpenRouter)
  • agi-cli
  • Claude Code alone
  • Cursor~
  • Run CLIs by hand
  • OpenCode
Rotate across multiple accounts to dodge rate limits
  • agi-cli
  • Claude Code alone
  • Cursor
  • Run CLIs by hand
  • OpenCode
Parallel teams with DAG dependencies
  • agi-cli
  • Claude Code alone
  • Cursor
  • Run CLIs by hand
  • OpenCode
Distribute teammates across machines over SSH
  • agi-cli
  • Claude Code alone
  • Cursor
  • Run CLIs by hand~
  • OpenCode
Steer & auto-nudge running agents mid-flight
  • agi-cli
  • Claude Code alone
  • Cursor
  • Run CLIs by hand
  • OpenCode
Managed cloud run that opens a PR
  • agi-cli
  • Claude Code alone
  • Cursor~
  • Run CLIs by hand
  • OpenCode
Reusable multi-agent workflow bundles
  • agi-cli
  • Claude Code alone
  • Cursor
  • Run CLIs by hand
  • OpenCode
Local browser via CDP (drive any site)
  • agi-cli
  • Claude Code alone
  • Cursor
  • Run CLIs by hand
  • OpenCode
Cross-agent session search & replay
  • agi-cli
  • Claude Code alone~
  • Cursor
  • Run CLIs by hand
  • OpenCode~
Cron / scheduled routines
  • agi-cli
  • Claude Code alone
  • Cursor
  • Run CLIs by hand~
  • OpenCode
Keychain-backed secrets (no .env files)
  • agi-cli
  • Claude Code alone
  • Cursor
  • Run CLIs by hand
  • OpenCode
Sync skills/MCP/commands across all installed agents
  • agi-cli
  • Claude Code alone~
  • Cursor
  • Run CLIs by hand
  • OpenCode~
Local-first and open-source — cloud dispatch optional
  • agi-cli
  • Claude Code alone
  • Cursor
  • Run CLIs by hand
  • OpenCode

Supported agents

Claude CodeCodexCursorOpenCodeOpenClawCopilotGrokKimiAntigravityAmpKiroGooseDroidGemini · deprecated

Install

# via curl
$ curl -fsSL agi-cli.sh | sh

# via bun
$ bun install -g @phnx-labs/agi-cli

# via npm
$ npm install -g @phnx-labs/agi-cli
Part of the open stack for AI coding agents. Open source, Apache-2.0, no telemetry.