Loop Documentation
Loop is the autonomous improvement engine that closes the feedback loop for AI-powered development. It turns signals into prioritized, actionable work — and tells AI agents exactly what to do next.
Loop Documentation
Loop is the autonomous improvement engine — an open-source data layer and prompt engine that collects signals, organizes work into issues, and tells AI agents exactly what to do next.
It closes the feedback loop for AI-powered development by turning raw data (errors, metrics, user feedback) into prioritized, actionable work items.
Signals -> Triage -> Hypothesize -> Plan -> Execute -> Monitor
^ |
+-----------------------------------------------------------------+Loop has no AI
Loop is a fully deterministic data system with a prompt layer. There are zero LLM calls inside Loop — no embeddings, no inference, no token costs, no model dependencies. AI agents pull work from Loop over HTTP. When a better model ships, every Loop installation gets better overnight without changing a single line of code.
How It Works
- Signals arrive — webhooks from PostHog, Sentry, GitHub, or any HTTP source create issues for triage
- Agents triage — an AI agent picks up the signal, decides if it is real or noise
- Hypotheses form — the agent creates a hypothesis with confidence level and validation criteria
- Plans break down — the hypothesis becomes concrete, scoped tasks
- Agents execute — tasks are dispatched one at a time with rich context and instructions
- Outcomes feed back — monitoring tasks watch for results, creating new signals that restart the loop
The issue queue is the orchestration layer. One unified system, one priority system, full auditability, and human override at any point.
Explore the Docs
Getting Started
Install Loop, configure your database, and create your first signal in under five minutes.
Concepts
Understand the core building blocks: issues, signals, dispatch, prompt templates, projects, and goals.
Guides
Step-by-step walkthroughs for the dashboard, writing prompt templates, and more.
Integrations
Connect Loop to GitHub, Sentry, PostHog, and other tools via webhooks.
API Reference
Complete reference for every REST endpoint — issues, signals, templates, dispatch, and dashboard.
CLI Reference
Manage issues, signals, triage, templates, dispatch, and system status from the command line.
Agent Integration
Choose the right integration surface for your AI agent — Claude Code, Cursor, Windsurf, OpenHands, or custom.
MCP Server
Zero-code IDE integration via the Model Context Protocol. Install in one command, get 9 agent tools.
TypeScript SDK
Programmatic access to Loop for custom applications, scripts, and agent frameworks.
Agent Skill
Contextual instructions that teach AI agents how to use Loop effectively in your project.
Self-Hosting
Deploy Loop on your own infrastructure with environment configuration and deployment guides.
Contributing
Set up the development environment, learn the codebase conventions, and submit your first pull request.
Key Principles
- Agent-agnostic — any AI agent that can make HTTP calls works with Loop. Swap agents or models without touching Loop.
- Pull architecture — agents poll for work on a schedule. Loop never needs to know how to connect to your agent platform.
- Self-improving instructions — agents rate the prompts they receive. When quality drops, Loop creates an issue to improve them.
- Everything is an issue — signals, hypotheses, plans, tasks, and monitors all live in the same priority queue.
- Open source — MIT licensed, fully on-premises capable, no vendor lock-in.