PR-AgentvsShippie
Generated from the two spec rows. Green marks the better value where a spec has a clear direction. Everything else is just different.
PR-Agent
PR-Agent community (formerly CodiumAI/Qodo) · Code review agent
#131OSS
Panel
6.62 spec wins
- Reliability
- 6.5
- Usefulness
- 6.7
- Cost
- 8.5
- Longevity
- 4.8
“The original open-source pull request reviewer, now gold-sponsored by the company selling the reviewer that replaced it.”
Shippie
Matt Carey · Code review agent
#177OSSMCP
Panel
6.33 spec wins
- Reliability
- 6.0
- Usefulness
- 6.2
- Cost
- 8.0
- Longevity
- 5.2
“You summon the reviewer by typing /shippie review, which is the first code review process anyone has ever voluntarily started.”
Spec by spec
| Spec | PR-Agent | Shippie |
|---|---|---|
| Architecture | ||
| Category | Code review agent | Code review agent |
| Runs | local, cloud | local, cloud |
| Platforms | macos, linux, windows | macos, linux, web |
| Context window | not documented | not documented |
| Protocols | ||
| MCP client | No | Yes |
| MCP server | No | No |
| Capabilities | ||
| Runs terminal commands | No | Yes |
| Multi-file edits | No | No |
| Git operations | Yes | Yes |
| Browser control | No | No |
| Sandboxed execution | No | No |
| Multi-agent orchestration | No | Yes |
| Headless / CI mode | Yes | Yes |
| Models | ||
| Backbone | any | Anthropic, OpenAI, OpenRouter, Cloudflare Workers AI |
| Bring your own model | Yes | Yes |
| Local models | Yes | No |
| Cost | ||
| Pricing model | byok | byok |
| Starts at | n/a | $0/mo |
| Free tier | Yes | Yes |
| Bring your own key | Yes | Yes |
| Openness | ||
| Open source | Yes | Yes |
| License | MIT | MIT |
| GitHub stars | 13,226 | 2,502 |
Which one would each critic pick
| Critic | PR-Agent | Shippie | Pick |
|---|---|---|---|
| El Juez | — | — | not enough reviews |
| El Amigo | 7.0 | 6.3 | PR-Agent — Pick PR-Agent if you want review commands you invoke on demand and nobody to bill you; pick CodeRabbit when you want a hosted product with someone answering the phone. |
| El Crítico | 6.0 | 6.0 | no preference |
| El Profesor | 6.8 | 6.3 | PR-Agent — The interesting engineering is compression: patches are fitted to the token budget adaptively, context is expanded dynamically, and the model is asked to rank its own suggestions. |
| La Inversora | 5.5 | 6.0 | Shippie — Formerly Code Review GPT, still one maintainer, still no price, and now competing with vendors that have raised money specifically to win this category. |
| La Jefa | 7.0 | 6.0 | PR-Agent — It installs as a workflow file and authenticates as the repository's own token, so there are no accounts to provision and no seats to multiply by sixty. |
| El Hacker | 7.5 | 7.5 | no preference |
Picks are derived from each critic's own scores. Humans vote on matchups on the duels page.