Multiple projects. Multiple AI agents per project. Desktop & mobile.
Watch every agent work in real time, drive the roadmap and dispatch tasks from one screen. Free.
A graphical, real-time view over every project and every agent. No CLI, no SSH.
The Architect turns a planned roadmap into an execution engine. Press Run all on the top-right of the roadmap view and the cockpit spawns a dedicated Roadmap Architect agent — a real Claude Code subprocess with a comprehensive system prompt that lets it read the cluster's initiatives, plan the order (parallel where modules don't collide, sequential where they do), and dispatch sub-agents one after another: coding, deploy, db, testing, docs, review. The architect narrates every move in its own chat. You watch a project execute itself.
The roadmap follows a three-piece model — Initiative (a coherent work-stream), Task (≈ one week of work), and an optional Cycle (a 1–2 week timebox that cuts across initiatives). It's the Linear primitive set, mapped onto plain markdown files under .meshkore/. Cycles are opt-in: skip them and the cockpit behaves exactly as before.
The Roadmap Architect is not a cockpit-side queue — it's a Claude Code agent with the full project context and the daemon's HTTP API at its fingertips. It reads .meshkore/roadmap/, decides what runs in parallel, and posts /chat/dispatch calls itself.
"Started task DEMO3 on A007 (general coder). Started OPS1 on A008 (deploy) in parallel. A007 done — DEMO3 ✓. Moving to next initiative." The chat fills with that. When it hits a blocker it stops and asks you for a single specific input, then resumes.
Every sub-agent the architect launches is a daemon-side ChatSession with its run record persisted to .meshkore/.runtime/runs.json. The cockpit hydrates from /health.chat_active_convs on attach, so a refresh — even mid tool-call — never lies about who is working on what.
No commands, no scripts. The cockpit walks you through the whole setup in under two minutes.
The cockpit detects whether the Architect is installed in your repo. If not, it shows the exact snippet you need to paste in your AI agent (Claude Code, Cursor, GitHub Copilot, Codex, …). Your agent reads the URL, adds the .meshkore/ standard to the repo, starts the local daemon — and the cockpit lights up. Done.
If you have Claude Code, Cursor, GitHub Copilot, Codex or Cline open in your repo, skip the cockpit — paste the install prompt and let the agent do the whole thing. (Click to show the snippet.)
Implement the MeshKore Architect in this repo. Read https://meshkore.com/standard and follow it end-to-end: adopt the standard, start the daemon, confirm the cockpit is reachable.
The agent reads the URL, applies the standard, starts the local daemon, and tells you when you can open architect.meshkore.com. You don't touch a thing — this is exactly the snippet the cockpit would have given you in step 1.
The stuff people ask before they hit install. If yours isn't here, open an issue at github.com/meshkore.
Yes — fully. Local mode and cloud mode are both free in v1. No invites, no waitlist, no paid tiers, no payment info. Encryption, audit log and team viewers — all included.
No. Claude Code, Cursor, Codex, Cline, DeepSeek, Qwen — anything that can read a URL and edit files works. Mix and match.
It reads the MeshKore standard — a tiny .meshkore/ folder convention for organising projects and orchestrating agents — applies it to your repo and starts the local daemon that the cockpit connects to. ~5 minutes, fully autonomous.
Yes. The cockpit reads your local filesystem; the daemon never pulls from GitHub. Cloud mode mirrors events outbound only — never inbound to your code.
architect.meshkore.com talk to my local daemon?Via a public DNS trick: daemon.meshkore.com is a Cloudflare A record that resolves to 127.0.0.1 — your own loopback. The daemon serves HTTPS+WSS on its ports (5570-5589) with a Let's Encrypt wildcard cert for *.daemon.meshkore.com. The cockpit at architect.meshkore.com connects to https://daemon.meshkore.com:<port> — same as if it were talking to a public server, except it never leaves your machine. No mixed-content blocks, no Chrome Local Network Access prompts. Same pattern Plex uses with *.plex.direct.
Every daemon keeps a complete local copy. If the cloud is unreachable, one daemon is auto-elected coordinator and the others sync from it. Work continues uninterrupted.
Tell your AI agent the setup URL. Open the cockpit. Done.