v1.253shep tui is here

Open-source AI coding agent orchestrator

Run a fleet of coding agents.
Merge real PRs.

Shep runs parallel agents — Claude Code, Codex, Copilot, Cursor, Gemini, Kimi Code, Cline, or local models — each in its own git worktree, through implementation, CI, and review. Drive them from the web, the CLI, or your terminal. Open source, local-first, cross-platform.

npx @shepai/cli

Runs locally with Node 22+. Opens the dashboard at localhost:4050, or run shep tui in your terminal.

Free and MIT-licensed. Bring the agent subscription you already have.

app.shep.bot

describe → (spec) → agents → review → pull request

The whole loop, not just the coding.

Every feature moves through the same pipeline — you decide how much of it runs on its own.

  1. Describe

    One sentence in, one branch out.

    Type it in the dashboard, run shep feat new, or start an app with shep app new. Shep cuts a branch and a worktree.

    Shep New Feature drawer for the acme-store repo: a one-line product-search description, with approval-gate, evidence, skills, and git togglesShep New Feature drawer for the acme-store repo: a one-line product-search description, with approval-gate, evidence, skills, and git toggles
  2. Spec

    Optional gates for complex work.

    Enable spec-driven mode and Shep writes requirements, research, and a plan as YAML you approve before any code.

    # specs/003-add-pagination/spec.yaml
    name: add-pagination
    number: 003
    oneLiner: Cursor pagination for GET /todos.
    
    requirements:
    - page + limit query params, default limit 20
    - response includes total count
    
    tasks:
    - id: task-1   # cursor decode
    - id: task-2   # paginated query
    
    gate: awaiting your approval
    
  3. Run agents

    Parallel, isolated, yours.

    Each feature gets its own git worktree and agent session — Claude Code, Codex, Copilot, Cursor, Gemini, Kimi Code, Cline, or a local model. Pick the agent per feature.

    Shep Control Center: the acme-store repo with four features in parallel — plan review, requirements review, completed, implementing — under a fleet status bar reading 1 cruising, 3 need you, Triage (3)Shep Control Center: the acme-store repo with four features in parallel — plan review, requirements review, completed, implementing — under a fleet status bar reading 1 cruising, 3 need you, Triage (3)
  4. Review

    You hold the merge button.

    Shep commits, pushes, opens a draft PR, watches CI, and pushes fixes when it fails. When an agent needs you, it asks with a recommended answer.

    A blocking agent question in Shep: should GET /health also check the database? The recommended option is preselected, and if nobody answers by the deadline the agent continues with itA blocking agent question in Shep: should GET /health also check the database? The recommended option is preselected, and if nobody answers by the deadline the agent continues with it
  5. Merge

    Real PRs, your process.

    Features land as standard pull requests on named branches. Your CI, your reviewers, your merge — unless you flag --allow-merge.

    Openfeat: cursor pagination for GET /todos

    feat/add-paginationmain

    • lintpassed
    • typecheckpassed
    • test (unit)passed
    • test (int)passed
    • buildpassed

    all checks passed — awaiting your review

shep tui

Prefer the terminal?

shep tui is a live console of every feature. Whatever needs you is pinned to the top, and single keys approve, reject, stop, and resume. It reads the same local state as the dashboard and runs without it.

shep tui

Inside tmux, Zellij, WezTerm, or kitty, t and f open a feature's shell or live agent log in a split pane.

shep tui keys

a
approve
r
reject
s
stop
R
resume
t
shell pane
f
follow log
C
control center
ctrl+p
palette
o
chat

features

Everything around the agent, handled.

fleet

Run a fleet, not a tab farm

Launch three, five, ten features. Cap how many run at once, triage only what needs you, batch-approve low-risk gates, and retry the failures. A circuit breaker flags runs that keep failing.

worktree isolation

A worktree per feature

Each AI agent works in its own git worktree on its own branch. No clobbered files, no port collisions, no stash juggling. Your checkout stays untouched.

CI watch

CI watch and auto-fix

After push, Shep watches your pipeline. When it fails, the agent reads the logs and pushes a fix — up to three retries, configurable.

decisions

Agents ask. You decide.

Unsure agents ask instead of guessing, with a recommended answer and a deadline. Answer from the web, the CLI, shep tui, or chat.

checkpoints

Rewind any step

Shep snapshots the worktree after every agent step. Diff any two steps, or restore one: shep feat checkpoints, diff, restore.

web + CLI + TUI

Dashboard, CLI, and terminal UI

A chat-first dashboard at localhost:4050, with specs, previews, and plans inline in the conversation. Every action is also a shep command, and shep tui is a live console of the fleet that approves, rejects, and opens split panes.

agent-agnostic

Bring your own agent

Claude Code, Codex, Copilot, Cursor, Gemini, Kimi Code, Cline — or models through OpenRouter, Together AI, and Ollama. Swap per feature, per repo, anytime.

open source

Open source, local-first

MIT-licensed. State stays in ~/.shep/; code goes only to your agent. shep telemetry off stops usage metrics.

what is shep

The open-source control center for parallel AI coding agents

Shep is an AI coding agent orchestrator that lets you run multiple Claude Code, Codex CLI, Copilot CLI, Cursor CLI, Gemini CLI, Kimi Code, and Cline sessions in parallel — each in its own git worktree, through CI and review to a pull request. Manage the whole fleet from the web dashboard, the CLI, or the shep tui terminal console.

faq

Frequently asked questions

Free and MIT-licensed

Bring the agent subscription you already have.

Shep adds the workflow around your agent — worktrees, commits, CI watching, pull requests. No Shep account, no usage meter, no cut of your tokens. Your code goes only to the agent you pick; anonymous usage metrics are on by default and shep telemetry off turns them off. The source is on GitHub; read it before you run it.

npx @shepai/cli
View on GitHub

Works with Claude Code, Codex, Copilot, Cursor, Gemini, Kimi Code, Cline — or models through OpenRouter, Together AI, and Ollama.

stars on GitHub

Live count, straight from the API. We don't cache our own traction.

Open source
local-first · your code stays yours

Works with Claude Code, Codex CLI, Copilot CLI, Cursor CLI, Gemini CLI, Kimi Code, and Cline — or models through OpenRouter, Together AI, Ollama, or any OpenAI-compatible proxy.

CLI agents

  • claudeClaude Code
  • codexCodex CLI
  • copilotCopilot CLI
  • cursor-agentCursor CLI
  • geminiGemini CLI
  • kimiKimi Code
  • clineCline
  • *any agent CLI

Model providers

  • openrouterOpenRouter
  • together-aiTogether AI
  • ollamaOllama (local)
  • llmproxyOpenAI-compatible proxy

Pick the agent and model per feature, per repo, anytime.