Now inviting Beta testers · Public waitlist open

The control plane for AI software development.

Direct AI workers from a Kanban board — they build, review, and run your software on your hardware and your models, with every queue, session, and runtime visible in one place.

Join the Beta waitlist See what you'll need

Already invited? Open Beta on GitHub →

Runs on your stack:Docker ComposeOpenAI-compatibleAnthropic-compatibleLM StudioOllamaClaude Code

The problem

AI-assisted development is fragmented and opaque.

You juggle an editor, a chat window, a stack of terminals, model endpoints, and docker commands — with no shared place to see what's queued, running, or done.

Work is scattered

Editors, terminals, chats, and docs — context lost between them.

Agents are opaque

No central queue — you can't see what an agent is doing, or why.

Chat is a poor surface

Ephemeral and single-threaded — bad for structured, repeatable work.

Parallel work is hard

Everything shares one environment, so running many efforts collides.

Running it is a chore

You drop into terminals to spin up servers and track which port is what.

Review is unstructured

No first-class place for one agent to build and another to review.

One control plane

Replace the scatter with one operating surface.

LStack separates three planes so work is defined, routed, observed, reviewed, and completed in one place — and the software it produces is something the platform knows how to run.

Projects, tickets, queue — structured, persistent, reviewable.
Managed workers & providers — your models, policy-governed.
Project runtimes — start, inspect, and open what gets built.

Control planedashboard

Projects · tickets · queue · workers · providers · runtimes

↓

Worker runtime planecontainers

Long-lived workers running Claude Code, writing your code

↓

Project runtime planelocalhost

Per-project containers running the software each project produces

How it works

From models to running software in three moves.

Connect your models

Add a provider — a model endpoint with a concurrency cap — and create workers from it.

Direct work on the board

Describe work as tickets. Statuses double as execution signals across five columns.

Watch it build, review & run

A worker builds, a reviewer checks before merge, then start the result at localhost.

Capabilities

Everything you need to operate AI development.

Working today on the local Docker-Compose build. Tagged honestly.

Kanban-native workflow NOW

Five-column flow where statuses double as execution signals. Tickets carry type, priority, and worker assignment.

Managed AI workers NOW

First-class execution units the platform provisions and routes — with shared, project-limited, assigned, and specialized policies.

Bring your own models NOW

Local or compatible endpoints with concurrency caps you set. OpenAI- and Anthropic-compatible providers.

Builder + reviewer NOW

One worker builds, another reviews before merge. Project-scoped roles, review packets, guarded merge.

Isolated workspaces NOW

Every project is a real folder; every session pinned to one path. On-disk docs and per-ticket git worktrees.

Managed runtimes NOW · NEWER

Run what you build — CLI, service, site, or stack — from the dashboard. Logs, run history, localhost URLs.

Queue & visibility NOW

See what's queued, running, blocked, and done across projects. Reorder, prioritize, watch throughput trends.

Local-first control NOW

Code, data, infrastructure, and models stay with you. Loopback-only exposure; encrypted per-project secrets.

Local-first & yours

Your machine. Your models. Your board.

The code, the project data, the infrastructure, and the model endpoints stay under your control. LStack runs against local or compatible model servers — not locked to a single hosted platform.

Ownership

Project context lives as real files on disk that move with the project.

Isolation

Each session runs in its own worker container pinned to one project path.

Model flexibility

Bring compatible endpoints; set concurrency caps that fit your hardware.

your machine

models

local · compatible

workers

isolated

projects

on disk

runtimes

127.0.0.1

↑ nothing leaves without you

Early, on purpose

Now inviting Beta testers. Public release is next.

Today LStack runs as a local Docker-based control plane. It already runs real work — projects, workers, builder/reviewer flow, queues, and project runtimes. A downloadable desktop app and one-line install are on the way.

You are here · Beta

Private Beta

We invite selected testers directly from the waitlist — no access codes. Approved testers are added to our private GitHub Beta repository for the release, issues, and discussion.

Next · Release

Public release

A polished, downloadable release. Join the waitlist to be first in line and help shape it.

Later · Direction

Desktop & headless

A desktop app and one-line server install — native core on the host, Docker for execution.

Get on the list

Join the public Beta waitlist.

Be first to know when LStack opens. No spam — just launch news and your Beta invite.

Double opt-in, unsubscribe anytime

Already invited? Open Beta on GitHub →