jigjoy-ai/baro

baro

Type a goal in your repo. Walk away. Come back to a pull request.

One prompt → a 33-story plan → 808 passing tests → a pull request. In 71 minutes.

No babysitting. No copy-paste. No "now do the next file." A fleet of coding agents planned the work, built it in parallel across isolated branches, reviewed each other, and opened the PR — from a single sentence.

▸ See what happened — 33-story DAG, 64 test suites, 83.5% branch coverage, +13,606 lines, zero phantom bugs filed.

npm install -g baro-ai
cd your-repo
baro "Add JWT authentication with role-based access control"

No machine, or no Claude/Codex subscription? Run the same fleet on baro's cloud — nothing to install, each run in an isolated sandbox, pay as you go. → app.baro.jigjoy.ai

<subbaro at the end of an actual run — one prompt → 33-story DAG → 32 files modified → PR opened. The summary panel shows wall time, parallel speedup (2.2×), token usage, and the PR URL.</sub

What happens when you run it

flowchart LR
    G([your goal]) --> C[Conversation<br/><sub>asks only what matters</sub>]
    C --> A[Architect<br/><sub>pins the design</sub>]
    A --> P[Planner<br/><sub>splits into a story DAG</sub>]
    P --> S[Story agents<br/><sub>parallel, isolated worktrees</sub>]
    S --> V[Critic + Verifier<br/><sub>reviews, repairs, tests</sub>]
    V --> PR([Pull Request])

• You describe the goal. A conversation agent confirms the scope, or asks only the questions that would change it.
• The Architect pins the design — file paths, schemas, API shapes, library choices — so dozens of agents don't each invent their own.
• The Planner splits it into a DAG of stories, with dependencies, so independent work can run at the same time.
• A fleet of agents builds it, each in its own git worktree — not one chat agent typing for an hour.
• It reviews and repairs itself. A tool-less Critic gates each story; a Surgeon replans the ones that get stuck.
• You get a pull request, build-verified, with a stories table and run stats.

The speedup scales with the width of your DAG, not the patience of a single session.

Quick start

npm install -g baro-ai

baro "Migrate the hardcoded category data to a backend dictionary"

baro --quick "fix the typo on line 42 of README.md"   # skip Architect/Critic/Surgeon
baro --parallel 3 "Add unit tests for the auth module"
baro --local-only "Your goal"                          # no pushes, no PR
baro --resume                                          # pick up an existing prd.json
baro --continue "…and add refresh tokens"              # follow-up onto the same PR
baro --doctor                                          # self-diagnostic

Full options, .barorc config and per-phase overrides: docs.baro.rs.

Execution modes

--mode decides how much runs at once. The default asks the intake to propose one and lets you confirm it.

| mode | what it does | |---|---| | auto (default) | intake proposes a mode from the goal; you confirm | | focused | a single story, start to finish | | sequential | one story at a time, in dependency order | | parallel | every ready story at once, up to --parallel |