# Portia

> Portia turns an epic into failing acceptance tests you sign off, runs Claude Code workers in parallel until every one passes on the rebased head, and hands you one pull request with the evidence for each scenario. It never merges to main.

Portia: prove the feature first, then let the agents build it. A Claude Code skill plus a small CLI that takes one Jira epic or GitHub issue to one reviewed pull request. Free; runs on your machine or a build box, on your own Claude Code subscription.

## Docs

- [Home](https://www.portia.run/): what Portia does, how a run works, and the questions people ask first
- [Full text for LLMs](https://www.portia.run/llms-full.txt): every fact, question and comparison on this site as one Markdown file
- [Reference](https://github.com/mousedown/portia/blob/main/docs/reference.md): every profile field, the plan block format, the gates, the CLI and the safety rules
- [Example profile](https://github.com/mousedown/portia/blob/main/examples/profile.example.ts): every option, including a database, Docker services and design checks

## Comparisons

- [Every comparison](https://www.portia.run/compare): agent workspaces, hosted agents and orchestrators, and where Portia sits
- [Portia vs Claude Code on its own](https://www.portia.run/compare/claude-code): Claude Code already has worktrees and subagents. Portia adds the plan, the tests-first spine, the gates and the single PR for an epic.
- [Portia vs Conductor](https://www.portia.run/compare/conductor): Conductor gives each task a workspace with its own worktree, terminal, diff and PR, and lets you run Claude Code, Codex, Cursor and OpenCode side by side. You plan, review and merge each one.
- [Portia vs Superset](https://www.portia.run/compare/superset): Superset runs any CLI agent in parallel worktrees on machines you own, with diff review, PRs, a browser and remote access. It is a desk to run agents from; the plan and the merge are yours.
- [Portia vs Claude Squad](https://www.portia.run/compare/claude-squad): Claude Squad keeps several agent sessions apart with a tmux session and a worktree each, behind one TUI. It is the lightest tool in this list, and it does nothing else on purpose.
- [Portia vs Vibe Kanban](https://www.portia.run/compare/vibe-kanban): Vibe Kanban is an open-source board where each card runs an agent in its own worktree and merges back with one click. The company behind it closed in April 2026; the project continues in the community.
- [Portia vs Bernstein](https://www.portia.run/compare/bernstein): Bernstein is the closest in spirit: a goal decomposed into tasks, a worktree each, lint, type and test gates, and a merge queue. It merges to main itself; Portia leaves that to you, and keeps the plan in your tracker.
- [Portia vs GitHub Copilot coding agent](https://www.portia.run/compare/github-copilot-coding-agent): Assign an issue to Copilot and it returns a PR from an Actions environment. GitHub's own guidance says it suits low-to-medium complexity tasks in well-tested codebases, one at a time.
- [Portia vs Devin](https://www.portia.run/compare/devin): Devin takes tickets from Linear, Jira, GitHub or Slack into a cloud sandbox and returns a PR. MultiDevin fans one task across up to ten workers. It is hosted end to end and billed in compute units.
- [Portia vs OpenAI Codex](https://www.portia.run/compare/openai-codex): Codex runs each task in its own cloud environment, many at once, and proposes a PR for each. It needs nothing of yours to run; Portia runs on your machine and lands one feature as one PR.
- [Portia vs Cursor cloud agents](https://www.portia.run/compare/cursor-cloud-agents): Cursor's cloud agents each run in their own VM and come back with a PR, screenshots and video. They start from the editor, the web, Slack, Linear or a phone. Portia is the planned, gated, one-PR counterpart on your own machine.

## Optional

- [Source](https://github.com/mousedown/portia)