Open-source · git-native · zero database

Mission control for teams of AI coding agents.

See every agent at a glance, keep them on-process with built-in guardrails, and get a git-native audit trail across Claude Code, Codex and Cursor.

Star on GitHub

Time to first dashboard < 2 min · no account, no database, runs on your machine.

localhost:4443
Filter agents, tickets, tools…

Blocked · action required (1)

agent-devops BLOCKED OPS_003
guardrail · approval required
Commit on agent/devops/active touched .env (secrets). Push held, needs Owner approval to proceed.
Claude Code sonnet-4.6 04/06 14:12

Working (1)

agent-ui WORKING UI_014 2
Building the comparison table + pricing cards from the launch-plan content.
Claude Code sonnet-4.6 04/06 15:03
a11y responsive evidence
awaiting your input
Use the warm-amber accent or the etcsec blue→green gradient for primary CTAs?

Review pending (1)

agent-analyzer REVIEW PENDING CONTENT_007
Codex gpt-5.1 04/06 13:40 6/9 tickets
seo fact-check

Standby (1)

agent-lead STANDBY
Coordinator on main · 2 tickets drafted, awaiting transmission.
Claude Code opus-4.6

One deck across every coding agent

Claude Code Codex Cursor Gemini CLI Aider Kimi OpenCode Amp Claude Code Codex Cursor Gemini CLI Aider Kimi OpenCode Amp
The problem

Run 3–5 agents in parallel and you lose the thread.

Spawning agents is the easy part: it's free and commoditized. Keeping track of them is where it falls apart.

Who's stuck?

An agent hit a wall ten minutes ago and is silently burning tokens, and you have no idea which one.

Who's waiting on you?

Three agents need a decision to continue. The answers are buried in terminals across four worktrees.

Who shipped what?

Something merged to main. No audit trail, no review record, no idea what guardrail did or didn't run.

How it works

A ticket-driven loop, recorded in git.

Every agent runs the same governed loop. State lives as YAML in the repo; the audit trail is git log.

Coordinator
drafts a ticket
Ticket
scoped + skills
Executor
works on a worktree
Review
human approval
Merge
to main
Changelog
git-native record
Why agents-deck

Not another way to run agents in parallel, but a way to keep them honest.

The parallel-agents race is commoditized and free. We win on the layer above it.

Observability

One live dashboard across every agent, tool and project: states, tickets, who's stuck, who shipped.

Safety & human-in-the-loop

Approvals, awaiting-input alerts, and no --dangerously-skip-permissions by default.

Process governance

Validators enforce skills + evidence, status read-confirms and message banners. Almost no one does this.

Git-native audit · zero-DB

State is YAML in the repo, audit is git log. SOC2 / ISO-42001-friendly evidence for free.

Cross-tool, cross-project

Claude Code + Codex + Cursor + Kimi, many repos, one deck.

Honest comparison

Where we actually win.

The category is crowded and mostly free. This is the table we're happy to be measured on.

Capability
agents-deck
Conductor
Vibe Kanban
Agent Teams
Live observability dashboard
macOS only
kanban
limited
Cross-tool (Claude · Codex · Cursor…)
2 tools
Claude-only
Human approval, not --yolo
--yolo default
Process guardrails / governance
Git-native audit · zero database
Cross-session memory & handoff
ephemeral
Self-hosted
local app
in-process
Price
Free OSS
Free
Free
Bundled

Conductor · Vibe Kanban · Claude Code Agent Teams, as of May 2026. Corrections welcome via PR.

Governance & compliance

Built for the EU AI Act era.

Your agents shouldn't run with --yolo. agents-deck gives every action a reviewer, a guardrail and a git-native record: the evidence trail regulated teams need, generated for free.

EU AI Act · 2026-08-02 ISO 42001 SOC 2 evidence NIST AI standards
Join the Team / Governance waitlist
git log · agents-deck/audit
a1f3c9 approve OPS_003 · owner override on .env guard
7b20e1 block OPS_003 · guardrail: secret in commit
3c8a44 review CONTENT_007 · agent-analyzer → pending
d90f02 skills UI_014 · a11y ✓ responsive ✓ evidence ✗
5e1b7a merge UI_013 · agent-ui → main
$
Quickstart

From zero to a live dashboard in two minutes.

No database to provision, no account to create. It's npx, then your browser.

01

Scaffold

One command writes project.yml, folders, hooks and MCP config into your repo.

02

Add a team

Per-role agent templates (backend, frontend, qa, security, devops), ready to go.

03

Open the deck

Watch every agent live at localhost:4443. Time to first dashboard < 2 min.

Pricing

The core is free, forever.

Individuals never pay. Teams who get outsized value fund development through governance.

Free / OSS
0€ forever
Individuals, self-host
Star on GitHub
  • Full dashboard, tickets, messages, changelog, roadmap
  • CLI + MCP
  • Guardrails & human-in-the-loop
  • Single user · self-hosted
  • Community support
Most popular
Team
19€ / seat / mo
Small & medium teams
Join the waitlist
  • Everything in Free
  • Multi-user & roles
  • SSO (Google / GitHub)
  • Multi-project org dashboard
  • Policy & guardrail packs
  • Hosted option · email support
Enterprise
Custom from ~2 500€/yr
Regulated & security-conscious
Talk to us
  • Everything in Team
  • SAML / SCIM · SOC 2
  • Audit & compliance export (EU AI Act, ISO 42001)
  • On-prem / air-gapped
  • SLA & dedicated support
  • Custom policy packs

agents-deck is free, and will stay free. Use it 100%, without paying a cent. If it earns its keep, back the project: pay what it's worth to you.

0€19€49€199€ · back the project
Team / Governance tier

Get early access, and early-adopter pricing.

The first ~20 teams get −50% for life. Tell us what you need; we'll reach out before launch.

No spam. One email when we open the tier.