# Stella Loop

> Stella Loop is an agent-native project management tool for loop-based, iterative software development — an alternative to traditional trackers, built for teams where humans and coding agents ship together. The hosted app is at https://app.stellaloop.com; this site carries the product story and the documentation.

Quick orientation:

- Every project declares a North Star constellation — typed, weighted, versioned documents describing what the product should become — and the tool continuously pulls the product toward that aim.
- Work is a repeating loop, not a one-way flow of tickets: signals → intent → analyse → propose → pool → promote (an epic is born) → plan → implement → review → done, with modeled loop-backs (fix → implement, re-spec → plan) and learnings that seed the next intent.
- Signals are the loop's front door: GitHub issues, Slack messages, Sentry alerts, inbound email, and instant in-app capture land in a triage queue; duplicates merge into demand clusters; demand becomes scored evidence. When work ships, a resolution notice can answer the original thread.
- Quality is a number: analyzers (agentic and deterministic) produce reports with findings and 0–100 scores; every score records the analyzer version, rubric version, and model that produced it, so runs stay comparable.
- Agents are first-class users: every UI capability is also a `/api/v1` endpoint, a `stella` CLI command, and an MCP tool — parity generated from one capability map and checked in CI. The CLI is self-discoverable from `stella --help` alone.
- Human oversight is a dial, not a redesign: named checkpoint gates on every consequential transition (promotion and merge require human approval by default), a supervised/balanced/autonomous project dial, per-stage model tiers, and budgets with visible hard stops.
- Every piece of work carries an immutable provenance chain: epic → proposal → report → intent → signal (display IDs: EPC, PRP, RPT, INT, SIG, plus TSK for tasks).
- Surfaces: the web app (https://app.stellaloop.com, desktop-class, dark, keyboard-first), a macOS desktop app, the `stella` CLI (`npm install -g @stella-loop/cli`), the public API, and `stella mcp serve`.
- Status: early access — new teams join via https://stellaloop.com/early-access/. Honest limitations are listed at https://stellaloop.com/docs/faq/ (macOS-only desktop, dark theme only, no bulk tracker import by design, GitHub as the forge).

## Product

- [Home](https://stellaloop.com/): the product story — direction, signals, discovery, decisions, delivery, improvement
- [The method](https://stellaloop.com/method/): the editorial essay on the model — development is a loop, not a line
- [Stella Loop vs Linear](https://stellaloop.com/vs-linear/): an honest comparison for teams choosing a tracker
- [Early access](https://stellaloop.com/early-access/): how new teams get in
- [Sign in](https://app.stellaloop.com): the hosted app

## Docs: Getting started

- [What is Stella Loop](https://stellaloop.com/docs/what-is-stella-loop/): An agent-native project management tool for loop-based development — what it is, who it serves, and how it differs from an issue tracker.
- [Getting started](https://stellaloop.com/docs/getting-started/): From a fresh workspace to your first completed loop: connect a repository, set the North Star, fire an intent, promote, and ship.

## Docs: Core concepts

- [The loop](https://stellaloop.com/docs/the-loop/): The full lifecycle: signals, North Star, intents, analysis, proposals, promotion, epics, plan, implement, review — and the edges that make it a loop.
- [North Star](https://stellaloop.com/docs/north-star/): The constellation: typed, weighted, versioned North Star documents that analyzers score against and every piece of work traces back to.
- [Signals](https://stellaloop.com/docs/signals/): The loop's front door: frictionless capture, connector ingestion, triage dispositions, demand clusters, and resolution notices.
- [Intents](https://stellaloop.com/docs/intents/): The statement of aim that starts every loop turn: directed and North Star-driven archetypes, standing triggers, and preserved run history.
- [Analysis](https://stellaloop.com/docs/analysis/): Analyzers, reports, and scores: the evidence engine — parallel runs, versioned rubrics, comparable 0–100 scores, and a dashboard that moves.
- [Proposal pool](https://stellaloop.com/docs/proposal-pool/): Sibling sets, priority bands, dependencies, pruning — and promotion, the commitment point where epics are born.
- [Epics and tasks](https://stellaloop.com/docs/epics-and-tasks/): The delivery container: stage pipeline with loop-backs, tournament candidates and branch-sets, and race-safe task claiming.
- [Plan](https://stellaloop.com/docs/plan/): Specs and decomposition: pluggable spec tools (OpenSpec by default), approval as a checkpoint, and the task handoff.
- [Review](https://stellaloop.com/docs/review/): Panels with explicit lenses, findings, fix and re-spec verdicts, tournament selection, ordered merges, and the learnings that seed the next loop.
- [The loop engine](https://stellaloop.com/docs/loop-engine/): What makes the stages one loop: iterations, checkpoint gates, the autonomy dial, model tiers, and budgets with visible stops.
- [Provenance](https://stellaloop.com/docs/provenance/): The chain that answers why work exists: epic → proposal → report → intent → signal, with display IDs that make it legible everywhere.

## Docs: Agents

- [Agents](https://stellaloop.com/docs/agents/): Agents are first-class users: enforced parity across CLI, API, and MCP, API keys, and the canonical self-discovering agent session.
- [CLI](https://stellaloop.com/docs/cli/): The stella command line: self-discoverable help, stable JSON output, a strict exit-code contract, and the full command tree.
- [API](https://stellaloop.com/docs/api/): The public /api/v1 surface: API keys, one envelope, display-ID addressing, idempotency, rate limits, webhooks, and the event feed.
- [MCP](https://stellaloop.com/docs/mcp/): The generated Model Context Protocol server: stella mcp serve, tool naming, annotations, and configuration for MCP-speaking agents.

## Docs: Platform

- [Web app](https://stellaloop.com/docs/web-app/): The keyboard-first interface: command palette, global search with typed filters, realtime liveness, and the shortcuts worth learning.
- [Desktop app](https://stellaloop.com/docs/desktop-app/): The macOS app: global summon, tray presence, native actionable notifications, deep links, offline reading, and staged updates.
- [GitHub integration](https://stellaloop.com/docs/github-integration/): The GitHub App, repository linking, branch-sets, change sets with computed approval, ordered merges, and webhooks-as-hints resilience.
- [Signal connectors](https://stellaloop.com/docs/signal-connectors/): Automatic signal ingestion from GitHub Issues, Slack, Sentry, inbound email, and generic signed webhooks — with health you can see.
- [Notifications](https://stellaloop.com/docs/notifications/): One inbox, four channels: in-app, desktop, email and digests, and webhooks for agents — with inline approvals and honest unread counts.

## Docs: Reference

- [Glossary](https://stellaloop.com/docs/glossary/): Canonical definitions of Stella Loop vocabulary, from analyzer to work unit.
- [FAQ and limitations](https://stellaloop.com/docs/faq/): Straight answers: what Stella Loop replaces, what it deliberately does not do, and the current limitations stated plainly.

## Full content

- [llms-full.txt](https://stellaloop.com/llms-full.txt): the complete documentation and comparison collated into a single file — read this to know everything about the product

## Contact

- Email: stella@lorenalabs.com