pr-agent vs shippie
pr-agent is much bigger: 12.9k stars against 2.5k. Over the days we have tracked them pr-agent moved +11.9% and shippie +5.3%, so pr-agent is growing faster right now.
Neither one leads on the six capability axes, so the choice comes down to which of them fits the way you already work.
Stars and commit dates come from our own daily tracking. The six axes are read off each project's documentation by our review pipeline, so they describe what a project says about itself, not what we measured in its code.
Where they stand today
An open-source, community-maintained, self‑hostable PR reviewer that compresses and adapts PR context and exposes JSON-configurable prompts for team customization.
- Stars
- 12.9k
- Tracked growth
- +11.9%
- Maturity
- ●●●●●
- Last commit
- 2h ago
- Language
- Python
- License
- MIT
- Cost to run
- Uses your API key (OpenAI/other providers)
Provides an extendable agent loop built on flue/pi with Model Context Protocol (MCP) support to explore the repo using real developer tools and integrate external tools.
- Stars
- 2.5k
- Tracked growth
- +5.3%
- Maturity
- ●●●●●
- Last commit
- 1d ago
- Language
- TypeScript
- License
- MIT
- Cost to run
- Your API key, per-PR
Six axes, head to head
Each axis runs 0 to 5. The label under a score is what that project's own docs claim, not a category average.
| Axis | pr-agent | shippie |
|---|---|---|
Context depth How much of your codebase it sees before it answers: the open diff, the diff plus related files, or the whole repository. | ●●●●● PR + related files | ●●●●● Repo exploration |
Noise control How it keeps output volume down — severity thresholds, deduplication, incremental runs over new commits only. | ●●●●● Configurable prompts | ●●●●● Configurable filters |
Customization How far it bends to your team: custom rules, prompts, style guides, per-path config. | ●●●●● Config files & prompts | ●●●●● Rules & prompts |
Privacy Whether your code stays on your own infrastructure: fully local, self-hostable, or cloud API only. | ●●●●● Self-hostable | ●●●●● API-key cloud |
Model freedom Whether you can point it at any provider, or it is wired to one. | ●●●●● Multiple providers | ●●●●● Multiple providers |
Setup ease What it takes to get a first useful run out of it. | ●●●●● One-step setup | ●●●●● Quick start |
Which one to pick
Pick pr-agent if…
Pick PR-Agent when you need a self‑hosted, highly customizable PR reviewer that supports multiple Git providers and scales to large pull requests.
Pick shippie if…
Extensible — pick Shippie when you want a provider-agnostic, extendable code-review workflow that can run locally or in CI and integrate external tools via MCP.
What people want from each one
The-PR-Agent/pr-agent
mattzcarey/shippie
Questions people ask
Is pr-agent better than shippie?
Neither one leads on the six capability axes, so the choice comes down to which of them fits the way you already work. pr-agent is worth picking when pick PR-Agent when you need a self‑hosted, highly customizable PR reviewer that supports multiple Git providers and scales to large pull requests.
Which of pr-agent and shippie keeps my code private?
pr-agent: Self-hostable (4/5). shippie: API-key cloud (3/5).
What does each one cost to run?
pr-agent: Uses your API key (OpenAI/other providers). shippie: Your API key, per-PR.
Full profiles: The-PR-Agent/pr-agent and mattzcarey/shippie. Everything else in Code review agents.