Worca
Get started
Deterministic multi-agent pipeline

Your AI agents,
on rails.

Describe the work, get back a reviewed pull request. A deterministic engine runs the agents, loops until the work passes its quality gates, and stops only to ask you what matters.

Get started How it works
web UICLIany modelisolated worktreesbuilt for teams
worca — running
Worca live cockpit: flow graph of a running pipeline with streaming log
live cockpitflow graph + streaming log
spent vs savedhours of work, minus the cost
Why Worca

Eight things a chat
window can't do.

A five-minute narrated deck on what a pipeline does that a harness can't: human on the gates, graph engineering, auditable costs, cloud/on-prem/local models, chat control, run-level guardrails, contained runs, and Ask Worca.

Watch the deck Get the .deck

Plays in the browser. The .deck opens in the OpenDeck app on iPhone, iPad and Mac.

worca.dev/why-worca
Title slide of the Why Worca deck: eight things a chat window with a model can't do
narratedfive minutes
How a run works

Describe the work.
Approve the result.

Agents do the creative work; the engine does the control flow. Pick a workflow, or let Auto build one for the task. Every step, verdict and file is recorded.

Step 1Clarify

Hidden decisions become questions before any code is written.

Step 2Plan

The planner explores the codebase and writes a concrete plan.

Step 3Refine

The refiner rewrites the plan until no major issues remain.

Step 4Implement

The implementer follows the approved plan, test first.

Step 5 → 4Review

The reviewer sends blocking findings back until the diff is clean.

A finished run ends on its own branch, one click from a pull request. See the whole pipeline →

What's inside

Everything
a run needs.

Any model, schedules, a record of every run, limits you set outside the agent, and a whole team working in one place.

How it works
Workflows you can see and change.

Auto picks the workflow, or build one in the Composer: agents, script cards and bounded loops. Every step files what it wrote.

The pipeline →
Models & costs
Any model. Every dollar accounted.

Claude, GitHub Copilot, Ollama or LM Studio on your desk, free OpenRouter models. Caps, budgets, and the hours each run saved.

Models & costs →
Automation
Runs that start while you sleep.

Schedule a run for tonight or every weekday, chain runs onto each other's branches, and answer from Slack or Telegram.

Automation →
Ask Worca
An assistant that knows your runs.

Ask what the reviewer flagged, attach a screenshot, let it read the docs page, or have it schedule the next run.

Ask Worca →
Teams
One Worca for the whole team.

Metrics and a delivery timeline, a team policy kept in git, a shared server behind sign-in, and each person pays with their own key.

Teams →
Security
Autonomy, with limits.

Guardrail policies that repo settings can't undo, a disposable container, and agents that never see a model key.

Security →
Runs where you need it

From your laptop
to your team's server.

The same Worca everywhere. Start on your own machine and move to a shared server when the team joins, keeping your workflows and history.

Laptop
One npm install

macOS, Linux or native Windows. npm i -g @worca/app

Container
A disposable Linux box

Agents run inside it, and your home folder isn't mounted. worca container up

Shared server
One Worca, behind sign-in

Any container host, behind the sign-in you already use. Worca records who started, paused and approved each run.

Team
Metrics and policy in git

Spend, a delivery timeline and team caps, stored on branches in your own repo. No extra server.

Pick your way in →

Built for real work

The rest of
the toolbox.

Isolated worktreesEach run gets its own git worktree and branch. Your checkout is never touched; parallel runs don't collide.
Runs pause, they don't dieA 500, a rate limit or an expired login pauses the run with its worktree intact. Resume picks up where it stopped.
Mock modeThe whole pipeline runs offline with a deterministic mock: no agents, no tokens. For demos, development and CI.
Plugins & marketplacesTask sources, agents, scripts, skills, workflows, models and chat channels. Each install shows what it adds and asks you first.
WorkspacesGroup related repos. One run fans out across all of them with a single cross-project review verdict.
One-click PRsA finished run shows its diff and opens a pull request, even from a fork, and reports back to the issue it came from.
Nothing in your repoRun state lives in one SQLite database in your home directory. Your checkout stays clean.
Simple to ExpertNew installs start with a short sidebar and a Getting started checklist. Switch to Advanced or Expert when you want everything.
Free and open source · MIT

Ship work you
didn't babysit.

One npm install on macOS, Linux or Windows. Or a container, or a shared server for the team.

Get started Star on GitHub