# Shep

> Open-source, local-first orchestrator that runs parallel AI coding agents in isolated git worktrees and drives each feature through CI to a pull request.

Shep is an open-source orchestrator from Shep AI that runs multiple AI coding agents in parallel, each in its own git worktree. It takes a feature from a one-line description through optional spec gates, implementation, commit, push, CI watching, and a draft pull request. It is MIT-licensed, local-first, and works from a CLI or a local web dashboard.

## What It Is

Shep is an AI coding agent orchestrator: a control layer around agent CLIs such as Claude Code, Cursor CLI, and Gemini CLI. The README also lists built-in support for Kimi Code, Codex CLI, Copilot CLI, and Cline, plus HTTP-based providers like OpenRouter, Together AI, Ollama, and OpenAI-compatible proxies. Shep handles the git workflow around the agent: branch, worktree, commit, push, PR creation, and CI monitoring. Engineers who already use coding agents can run several features at once without agents touching the same checkout.

## How the Workflow Runs

A feature starts with a sentence, entered in the dashboard or with `shep feat new`. Shep creates a branch and worktree, runs the chosen agent, then commits, pushes, and opens a draft PR. After a push it watches CI; if checks fail, the agent reads the logs and pushes a fix, with three retries by default (configurable). For complex work, the `--no-fast` flag enables spec-driven mode, where requirements, research, and a plan are written as YAML artifacts and pause at approval gates before code is written. Nothing merges without approval unless `--allow-merge` is passed.

## Dashboard, Apps, and Configuration

The web control center at localhost:4050 shows a live graph of repositories and features with status, diff review, chat, and one-click open in an IDE; the CLI exposes the same actions. Shep can also start new apps (`shep app new`) with either a plan-first flow or a Vite + React quick-prototype starter. Per-feature flags control pushing, PR creation, model choice, target repo, attachments, and gate auto-approval, and `shep settings` sets global defaults.

## Local-First and Safety Model

All state is stored in `~/.shep/` as SQLite, and code goes only to the agent you configure. The README notes that Shep passes permission-bypass flags to agents by default, relying on worktree isolation, draft PRs, and your CI as safeguards, and that it is not a security scanner. Anonymous usage metrics are on by default and can be disabled with `shep telemetry off`.

## Features
- Parallel AI coding agents, each in its own git worktree
- Agent-agnostic: Claude Code, Cursor CLI, Gemini CLI, Codex CLI, Copilot CLI, Kimi Code, Cline, or any agent CLI
- Automatic commit, push, and draft PR creation
- CI watch with agent auto-fix and configurable retries
- Optional spec-driven mode with YAML requirements, research, plan, and approval gates
- Local web dashboard and full CLI
- Multi-repo support and app scaffolding
- Audit logs and emergency stop for agent runs
- Local-first SQLite state storage

## Integrations
Claude Code, Cursor CLI, Gemini CLI, Codex CLI, Copilot CLI, Kimi Code, Cline, OpenRouter, Together AI, Ollama, GitHub CLI

## Platforms
WINDOWS, MACOS, LINUX, WEB, API, CLI

## Pricing
Open Source

## Version
v1.242.0

## Links
- Website: https://shep.bot
- Documentation: https://shep.bot/docs
- Repository: https://github.com/shep-ai/shep
- EveryDev.ai: https://www.everydev.ai/tools/shep