Stop babysitting terminals. Start orchestrating agents.

One board routes every task to the right coding agent, runs them in parallel on isolated worktrees, and brings each blocker, plan and diff back to you before anything ships.

Choose your download Watch it work
  • Free local boards
  • Windows, macOS & Linux
  • Your CLI logins, your keys
5
agent families in one queue
16
concurrent runs on Team
0%
markup on your tokens

SEE IT RUN

From brief to approved diff, without a single terminal.

This is the real interface, at app scale. Watch a task get a brief, pick up an agent, run in parallel, and come back for review.

01 / 05

Give agents a real brief.

Create tasks with descriptions, acceptance criteria, images and tags—then move them through the workflow your team already understands.

  • Custom sections and columns
  • Agent, tag and role routing
  • Context stays attached to the task

Showing Payments: Give agents a real brief.

CodexClaude CodeGrokOpenCodeOpenAI-compatible

Why orchestration beats more terminal tabs

One coding agent in a terminal is fast. Four of them are chaos: overlapping edits, questions nobody sees, finished work with no review path, and no way to answer "what is running right now?" without alt-tabbing through sessions.

cadre.rocks turns that into an operation. Every task carries its brief, repository, agent, model and state. Runs happen in isolated Git worktrees so they cannot collide. Questions, plans, commands and diffs come back to one surface — and nothing merges until you say so.

WHAT YOU GET ON DAY ONE

1

One queue for every agent

Route work by column, role or tag instead of remembering which terminal had which context.

  • Claude Code, Codex, Grok, Opencode, OpenAI-compatible
  • Model and reasoning effort chosen per column
  • Automatic agent selection by task tag
2

Parallel work that never collides

Each run gets its own branch and worktree, with a visible queue when you hit your concurrency limit.

  • One isolated Git worktree per run
  • Live logs, duration, model and token counters
  • Queue positions instead of silent contention
3

Approval where it matters

Agents execute freely between gates — and stop cold at the decisions that change scope, permissions or shipped code.

  • Structured questions with recommended options
  • Plan review before implementation starts
  • File-by-file diff review, then a local merge you trigger

HOW IT RUNS

From a defined task to an approved result.

  1. 01

    Define the task

    Title, description, acceptance criteria, tags and context images — the brief the agent actually needs.

  2. 02

    Pick the agent

    Assign a CLI and model to the column, or let the tag routing choose for you.

  3. 03

    Run in parallel

    Watch live logs and status while every run stays in its own worktree and branch.

  4. 04

    Approve, then merge

    Answer blockers, approve the plan, review the diff, and merge locally when you are ready.

SUPPORTED AGENTS

Bring the agents you already use.

cadre.rocks detects the coding CLIs installed on your machine and routes each task to the one you picked for that column. Same agents, same logins—now with a board, a queue and approval gates around them.

CC

Claude Code

Anthropic

Anthropic's engineering agent in the terminal.

claudeCLI · BYOK
CO

Codex

OpenAI

OpenAI's agentic coding CLI.

codexCLI · BYOK
GR

Grok

xAI

xAI's assisted build CLI.

grokCLI · BYOK
OC

Opencode

anomalyco

Open-source, multi-provider coding agent.

opencodeCLI · BYOK
{ }

OpenAI Compatible

Local profile

Endpoint and model defined by a local OpenAI-compatible profile.

profileBYOK

Agents run locally through their own CLI or through your key. Adding a model never requires a new account with us.

Agents execute.
You keep the gates.

Questions, plans, commands and code changes return to one decision surface before the workflow can continue.

Choose your download
?Needs input
Question 1 of 2

How should board-wide approvals expire?

When the board closesAfter 24 hours Recommended
✦Plan ready for review
Claude Code · just now
Implementation plan

1. Validate repository paths at the service boundary.

2. Refactor the import coordinator and add adversarial tests.

✓Review changes
4 files · +128 −34
✓ command_policy.rs +64 −12 approval_service.rs +41 −18 command_policy.test.rs +23 −4

COMMON QUESTIONS

Questions, answered.

What is a coding agent orchestration platform?

It is the workflow layer around your coding agents: tasks with real briefs, agent routing, parallel execution in isolated worktrees, live run state, and human approval gates for questions, plans, commands and diffs.

Does cadre.rocks replace Claude Code or Codex?

No. It drives the coding CLIs you already have installed and authenticated, using your existing subscription or your own API key.

How many agents can run at the same time?

Free keeps one active run and queues the rest, Pro runs up to 4 concurrently, and Team runs up to 16. The queue is always visible on the board.

Do I need an account to start?

No. Local boards work offline on your machine with no account. Sign in only when you want online workspaces, sync or collaborators.

KEEP READING

Related guides.

See all guides →

MULTI-AGENT CODING WORKFLOW

Multi-agent workflow

Run several agents at once with isolated worktrees, a visible queue and ordered subtasks.

Read the guide

HUMAN-IN-THE-LOOP

Human in the loop

The four gates: questions, plans, commands and diffs — each with its context attached.

Read the guide

LOCAL-FIRST CODING AGENTS

Local-first agents

Offline by default, keys in the OS keyring, and sync you opt into workspace by workspace.

Read the guide

Put your agents to work.
Keep the final say.

Download cadre.rocks and move from scattered agent chats to tasks you can direct, inspect and approve.

Choose your download
Windows x64 macOS Universal Linux AppImage Linux .deb

Free local boards · No credit card · Windows, macOS & Linux