- Claude Code
- Codex
- OpenCode
- Cursor CLI
- Hermes
- Custom CLI
- More CLIs coming
Run reusable coding-agent teams from one visible workspace.
Bring the CLI agents and model access you already use, define roles and handoffs once, and relaunch comparable runs while local terminal sessions stay visible.
- CONFIGURED BY YOU
- BRING YOUR OWN ACCESS
- EVALUATE RUNS ON THE SAME BRIEF
- SHARE REPEATABLE SETUPS
Example configured tools only. AgentsCommander does not include third-party CLIs, accounts, subscriptions, API keys, or model/API access. OpenCode, Cursor CLI, Hermes, and similar labels are user-configured examples.
Free and open source coordination for real CLIsKeep CLI power. Make the team reusable.
AgentsCommander runs configured coding-agent CLIs as local terminal sessions, then lets users define repeatable agent teams for roles, repos, handoffs, review, and comparable runs on real software tasks.
Example configured tools only. You bring third-party CLIs, accounts, subscriptions, API keys, and model/API access; AgentsCommander coordinates local processes you provide.
AgentsCommander is free and open source under the MIT license. Bring your own coding-agent CLIs, accounts, and model access.
First-class tuned integrations cover Claude Code and Codex. OpenCode and other terminal agents can be added through the custom coding-agent path when they run from the shell in your environment. AgentsCommander spawns the local CLI processes you provide. It does not bundle third-party tools, models, subscriptions, API keys, accounts, or provider access.
Share the team setup, not a prompt snippet.
AgentsCommander fits teams that need the same multi-agent setup again and again. Define the coordinator, worker roles, repo access, and launch settings once, then activate matching workgroups for each new task.
Treat your agent setup as part of the engineering codebase.
Turn role prompts, team definitions, agent skills, and reusable agent loops into local project files your team can review, reuse, version, and share when safe.
- 01
Define the team once
Set the coordinator, worker roles, repo access, and launch settings a single time.
- 02
Activate a workgroup
Spin up a matching workgroup the moment a new task needs that same team.
- 03
Review and reuse
Reuse the same setup across features, reviews, refactors, and test loops.
Briefs, replies, and role handoffs stay visible.
A coordinator can send markdown briefs to configured worker sessions, collect replies, and move the task forward through explicit handoffs you can inspect while each local terminal session remains visible.
Example setup: user-provided CLIs and models. Accounts, API keys, model availability, and pricing are managed with the respective vendors.
- coordinatorCodex profile, GPT 5.5 xhigh
- dev-rustOpenCode custom-command example, GLM 5.2
- dev-uiClaude Code profile, Opus 4.8 max
- reviewerHermes custom-command example, DeepSeek V4 Pro
Concrete capabilities, not abstractions.
Every step of multi-agent work stays visible: real terminals, explicit handoffs, and plain files you can read with the tools you already have.
Define the team once
Create a coordinator plus specialist workers once. Reuse the same Team for features, reviews, refactors, documentation passes, or test/fix loops.
Launch a clean workgroup for each task
Activate a Team as a Workgroup when work starts. Each Workgroup includes its own
TASK.md,messaging/folder, agent replicas, and separate repo/work state.Run real coding agents in real terminals
AgentsCommander coordinates the CLI tools developers already use instead of hiding them behind a framework abstraction. Each session runs in a real PTY, so prompts, failures, logs, and progress stay visible.
Delegate through a coordinator
Give the coordinator a goal. It can draft assignments, send markdown briefs to worker agents, collect replies, and move the task through explicit handoffs you can inspect.
Inspect every handoff
Every inter-agent message is a timestamped markdown file on disk. Read it, diff it, archive it, or debug it with normal developer tools.
Clear context with a handoff
For long-running agent work, an agent can write an explicit handoff, clear its own context, and resume from the important task state captured in that file.
Compare roles, skills, and profiles
Rerun the same brief with different role prompts, agent skills, CLI profiles, or launch config, then compare the visible terminal output, handoffs, tests, and diffs.
Watch parallel work in one place
Track coordinator and worker sessions side by side in the desktop UI, see running/waiting/exited states, and keep parallel agent outputs visible while they happen.
Add optional phone control for long runs
For long-running work, attach a Telegram bot to an AC-managed local terminal session, monitor progress from your phone, reply when input is needed, dictate prompts through Gemini voice transcription, and send screenshots or report images when visual confirmation matters. Optional and user-configured: Telegram traffic goes through Telegram; voice audio goes to the Gemini API; provider terms, pricing, privacy, and availability apply.
Put a repeatable team on real work.
The same setup drives many jobs. You stay in the loop at every handoff.
Parallel feature development
Two coding agents work the same repo, each owning a different module. The coordinator routes the work and brings the results together for you to review.
Code-review swarm
One agent opens a pull request while two others review it independently. You read each review in its own terminal before you merge.
Refactor across workers
A coordinator splits a multi-file refactor across worker agents and tracks each branch as the workers finish, with every change visible on disk.
Test and fix loops
Run a build or test pass, route the failures to a worker to fix, then repeat the loop with each step visible in a real terminal.
Agent setup comparison
Run the same repo task with two role, skill, or CLI-profile setups, then compare terminal output, handoffs, tests, and diffs before you standardize on one.
Phone check-ins for long runs
Attach a Telegram bot to an AC-managed session, keep an eye on long-running local agent work from your phone, reply when input is needed, dictate prompts through Gemini voice transcription, and send screenshots or report images when visual confirmation matters.
Every handoff is a file on disk.
Agents talk to each other through timestamped markdown in a messaging/ folder. It is an inspectable local markdown trail, so you can read it, diff it, or archive it with the tools you already use. No hidden state, no database to query.
- cat a message to see exactly what one agent told another.
- git diff the folder to watch the coordination evolve.
- grep the trail when you need to debug a run.
Your project state stays on your machine.
AgentsCommander keeps project state and inter-agent messages on disk as plain JSON, TOML, and markdown. It does not collect telemetry, analytics, or usage data.
Optional features are user-configured. Telegram traffic goes through Telegram; voice audio goes to the Gemini API; provider terms, pricing, privacy, and availability apply. AgentsCommander does not provide Telegram accounts, bot tokens, Gemini API keys, model access, uptime, delivery guarantees, provider pricing, or third-party privacy promises.
- WindowsPrimary platform, where most development happens.
- LinuxSupported, testing is underway.
- macOSNot yet validated.
Windows code signing is in progress with SignPath. Current Windows release artifacts may be unsigned until the release workflow is fully connected; download from GitHub Releases and review the Code signing policy.
Create your first team.
Install the CLI, open a project, add a coordinator and a worker, then launch them in real terminals. The quickstart walks the whole path.
$ npm install -g @mblua/agentscommander
$ agentscommanderThe published npm package is @mblua/agentscommander. The installed command is agentscommander.
Prefer a desktop install? Get Windows, Linux AppImage, or macOS builds from GitHub Releases. Windows code signing is in progress; review the Code signing policy before installing unsigned artifacts. You bring and authenticate your own coding agent CLIs.