cd /news/developer-tools/cadre-rocks-a-local-first-board-for-… · home topics developer-tools article
[ARTICLE · art-95788] src=cadre.rocks ↗ pub= topic=developer-tools verified=true sentiment=· neutral

Cadre.rocks A local-first board for orchestrating coding agents in Git worktrees

Cadre.rocks has launched a local-first board for orchestrating coding agents in Git worktrees, enabling parallel agent runs with human approval gates. The tool supports Claude Code by Anthropic, Codex by OpenAI, Grok by xAI, and Opencode by anomalyco, with no token markup and free local boards. It runs agents locally via CLI logins or BYOK, storing keys in the OS keyring, and offers optional online workspaces for team collaboration.

read5 min views1 publishedAug 13, 2026
Cadre.rocks A local-first board for orchestrating coding agents in Git worktrees
Image: source

3 agents running

Turn well-defined tasks into parallel agent runs. Route work to the right model, answer blockers, review plans and diffs, and approve every outcome from one workspace.

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

The whole agent workflow, in one place. #

Follow a task from brief to branch, blockers, plan, diff and approval—then take the same work across devices when your team grows.

01 / 09

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.

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.

claude

CLI · BYOKCO

Codex

OpenAI

OpenAI's agentic coding CLI.

codex

CLI · BYOKGR

Grok

xAI

xAI's assisted build CLI.

grok

CLI · BYOKOC

Opencode

anomalyco

Open-source, multi-provider coding agent.

opencode

CLI · BYOK**{ }**

OpenAI Compatible

Local profile

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

profile

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

MODELS & KEYS

Use the models you already pay for. No token markup. #

Every agent, in every column, runs one of two ways: through the CLI login you already have, or through your own API key. Requests leave your machine straight for the provider—cadre.rocks never sits in the middle of them.

Use the CLI login

No new billingPoint a column at a CLI that is already installed and authenticated. The run reuses that session.

  • Works with the subscription you already pay for
  • cadre.rocks detects which CLIs exist on this machine
  • Model and reasoning effort still chosen per column
  • No key to paste, nothing new to store

Bring your own key

Your provider, your billPrefer API billing, a self-hosted endpoint or a model the CLI does not expose? Save a key for that agent.

  • Stored in the OS keyring—never in config files, logs or browser storage
  • Scoped to one agent in one column, separate from Chat BYOK
  • Any OpenAI-compatible endpoint through a local profile
  • Remove the credential and the column falls back to the CLI

Tokens are billed by your provider. cadre.rocks charges for the orchestration layer—boards, parallel runs, approvals—never per token.

Choose your download Free local boards · Your CLI logins and keys stay on your machine

Agents execute. #

You keep the gates.

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

Needs input

How should board-wide approvals expire?

Plan ready for review

Implementation plan

  1. Validate repository paths at the service boundary.

  2. Refactor the import coordinator and add adversarial tests.

Review changes

command_policy.rs

+64 −12 approval_service.rs

+41 −18 command_policy.test.rs

+23 −4

Start local. Go shared when the work does. #

Begin with a private desktop board. Add online workspaces, cross-device sync, invites, and collaboration when the project becomes a team effort.

Local desktop

Boards, repositories, worktrees and agent runs stay on your machine by default. Credentials remain in your system's secure storage.

  • ✓Local boards
  • ✓Local agent adapters
  • ✓Human approval gates
  • ✓Offline by default

Online workspaces

Keep board activity in sync across computers and invite collaborators into the workspaces that need a shared view.

  • ✓Cross-device sync
  • ✓Workspace invites
  • ✓Shared board activity
  • ✓Team collaboration

Only the workspace data you choose is synced. Source repositories, worktrees and credentials remain local.

GUIDES

Pick the part you care about. See it running. #

Six deep dives into the workflow, each with a live replica of the app doing the thing it describes—parallel runs, approval gates, command policy, local-first execution.

6 GUIDES

1 CODING AGENT ORCHESTRATION

Agent orchestration

The full picture: boards, routing, parallel runs and approval gates in one operation.

  • 5
  • agent families in one queue
  • 16
  • concurrent runs on Team
  • 0%
  • markup on your tokens

2 MULTI-AGENT CODING WORKFLOW

Multi-agent workflow

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

  • 1 → 16
  • concurrent runs by plan
  • 1:1
  • run to isolated worktree
  • 100%
  • of diffs reviewed by a human

3 CLAUDE CODE WORKFLOW

Claude Code

Keep your Claude Code login. Add tasks, parallel runs, blockers and diff approval around it.

  • 0
  • new subscriptions required
  • 1 click
  • from question to resumed run
  • OS keyring
  • is where any key lives

4 CODEX CLI WORKFLOW

Codex CLI

Structured Codex runs with scoped command approvals, live logs and diff review.

  • 2 ways
- to execute: CLI or BYOK
- Per-run
  • branch and worktree
  • Backend
  • enforced command policy

5 HUMAN-IN-THE-LOOP

Human in the loop

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

  • 4
  • approval gates, not 400 prompts
  • Never
  • an automatic push or merge
  • Rust
  • backend enforces the policy

6 LOCAL-FIRST CODING AGENTS

Local-first agents

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

  • Offline
  • by default, no account needed
  • OS keyring
  • for every credential
  • Opt-in
  • sync, per workspace

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.

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

── more in #developer-tools 4 stories · sorted by recency
── more on @cadre.rocks 3 stories trending now
sponsored brought to you by zahid.host 4,200+ EU-deployed projects
reading about agents? ship yours in a single git push.

Run your AI side-project on zahid.host

EU-based hosting, git-push deploys, automatic HTTPS, no cold starts. Free tier with a custom domain — perfect for shipping the agent you just read about.

$git push zahid main
Live at https://your-agent.zahid.host
Get free account → Pricing
from €0/mo · no card required
LIVE [news/cadre-rocks-a-local-…] indexed:0 read:5min 2026-08-13 ·