I already use an IDE like Cursor, is this for me?

AO is designed to work with your existing tool. We natively support deep-linking to IDEs like Cursor so you can open your workspaces and files in your IDE. AO sits above individual tools, use whatever agent you like, AO keeps the workflow the same.

Which AI coding agents are supported?

AO works with any CLI-based coding agent including Claude Code, OpenCode, OpenAI Codex, Cursor, Aider, Goose, and 18 more. If it runs in a terminal, it runs in AO. 23 harnesses total, with per-project agent choice.

How does the parallel agent system work?

Each agent runs in its own isolated Git worktree, which means they can work on different branches or features simultaneously without conflicts. AO's orchestrator spawns workers, routes CI failures and review feedback to the right session, and lets you monitor the entire fleet from one board.

Is Agent Orchestrator free to use?

Yes. AO is free and open source under Apache 2.0. It runs as a local daemon on your machine, your code never leaves localhost. No account, no cloud, no credit card required.

Can I use my own API keys?

Absolutely. AO doesn't proxy any API calls. You use your own API keys directly with whatever AI providers you choose. This means you have full control over costs and usage.

Stop babysitting agents. Start merging real work.

Run a fleet of coding agents while keeping branches, reviews, and CI failures manageable.

Download for Mac Star on GitHub8.8k

Use the agents you already trust.

Delegation

Tell the orchestrator what you need

Every project gets a main agent that runs the fleet for you. Describe the outcome, it plans the work, spawns workers into their own worktrees, keeps them moving, and escalates only what needs a human.

Agent Orchestrator

Projects

Settings

solkit-ui· Orchestrator

TERMINAL Orchestrator

11px

Claude Code v2.1.204

Opus 4.8 (1M context) · Claude Team

~/ao/solkit-ui/orchestrator

orchestrator ❯ Ship GitHub sign-in, cover the callback flow, update setup docs.

· planning — splitting the outcome into 3 tracks

Visibility

The whole fleet, at a glance

Every session flows across one board, working, needs you, in review, ready to merge, with its agent, branch, and PR state on the card. You see what needs attention and ignore the rest.

Pending Work

Confirm download labels are platform-aware

landing/platform-copy

Editing copy14m ago

Port Figma board mock into the hero preview

landing/figma-board

#318

Editing component8m ago

Iterating

Run integration tests on webhook handler

webhooks/integration-tests

18/50 passed22m ago

Migrate auth tokens to short-lived JWTs

auth/jwt-rotation

#331

22/60 passed34m ago

In Review

Preload GitHub stars before hydration

landing/preload-stars

#324

2 cmt

Awaiting review1h ago

Ready to merge

Stabilize Vercel framework detection

deploy/vercel-next-config

#327

0 cmt

Merge PR

3h ago

Feedback Loop

CI fails. The right agent fixes it.

AO watches every PR it opens. Failed checks and review comments route back to the session that owns the branch, with the context to fix them, until the PR is approved.

github-auth

12px

❯Add GitHub OAuth callback handling.

⏺Search(pattern: "oauth", path: "src")

⎿Found 4 files

⏺Read(src/auth/session.ts)

⎿Read 54 lines

⏺Read(src/auth/index.ts)

⎿Read 88 lines

⏺Write(src/auth/callback.ts)

⎿Wrote 96 lines

⏺Write(src/auth/callback.test.ts)

⎿Wrote 61 lines

⏺Bash(npm test -- auth)

⎿Tests 11 passed (11)

⏺Bash(git push origin feat/github-auth)

⎿4c1d0ab pushed to feat/github-auth

⏺Bash(gh pr create --fill)

⎿.../agent-orchestrator/pull/2481

⏺Opened PR #2481. Watching checks.

·AO routed GitHub feedback here

PR #2481 · check "test / web" failed

FAIL src/auth/callback.test.ts

● rejects an expired state param

expected 401, received 500

Coverage

Use the agent you already trust

23 harnesses supported, with per-project agent choice. Claude Code, Codex, Cursor, OpenCode, Aider, Goose, and more, AO keeps it running the way you already run it while the tools underneath evolve.

agent-orchestrator

Pending Work1

Remove stale generated icon imports

cleanup/stale-icon-imports

Deleting file14m ago

Iterating1

Tighten hero window border alignment

landing/window-border-pass

#320open

14/44 passed1h ago

Mobile companion

Your fleet goes where you go

Pair the AO mobile app with your desktop over LAN or Tailscale. Watch every session, open a terminal, and get notified when an agent needs you - while execution and code stay on your machine.

9:41

Agents

192.168.88.3

working

need you

mergeable

Projects

Needs you1

Working4

Ready to merge1

See it in action

Watch AO run a fleet of agents end to end on a single repo, from task to merged PR.

In the wild

Real posts from builders, researchers, and early users, pulled straight from X.

Teknium

@Teknium

It can orchestrate agents but this looks a bit more advanced.

FacitoO

@facito0

Me with @aoagents lately!

Buchi Reddy B

@buchireddy

I really loved the building blocks present in @aoagents, hence we went all-in on that pretty early. Happy to share more details if it helps others.

Adi

@addddiiie

I just hired a few software devs to work for free cc, @aoagents

Maria Garcia

@maria_garcia_dev

We run 50+ agents a day through AO. The feedback loop, CI fails go back to the agent that wrote the code, saves us hours every week.

Luke Tanaka

@luke_tanaka

The board view alone is worth the download. I can see every session, every PR, every CI status across all my repos in a single glance.