agentboards.org
Compare/Proval vs Shippie

ProvalvsShippie

Generated from the two spec rows. Green marks the better value where a spec has a clear direction. Everything else is just different.

Proval
seoes · Code review agent
#211OSS
Panel
5.9
1 spec wins
Reliability
5.7
Usefulness
5.7
Cost
7.3
Longevity
5.0

“It can be configured to reply only when mentioned, a courtesy no human reviewer has ever extended to anyone.”

Shippie
Matt Carey · Code review agent
#177OSSMCP
Panel
6.3
3 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

SpecProvalShippie
Architecture
CategoryCode review agentCode review agent
Runslocal, cloudlocal, cloud
Platformslinux, webmacos, linux, web
Context windownot documentednot documented
Protocols
MCP clientNoYes
MCP serverNoNo
Capabilities
Runs terminal commandsNoYes
Multi-file editsNoNo
Git operationsYesYes
Browser controlNoNo
Sandboxed executionNoNo
Multi-agent orchestrationYesYes
Headless / CI modeYesYes
Models
BackboneOpenAI-compatible, Ollama, llama.cppAnthropic, OpenAI, OpenRouter, Cloudflare Workers AI
Bring your own modelYesYes
Local modelsYesNo
Cost
Pricing modelbyokbyok
Starts at$0/mo$0/mo
Free tierYesYes
Bring your own keyYesYes
Openness
Open sourceYesYes
LicenseAGPL-3.0MIT
GitHub stars1022,502

Which one would each critic pick

CriticProvalShippiePick
El Juez——not enough reviews
El Amigo6.36.3no preference
El Crítico4.86.0Shippie — It runs inside your automation with a provider key stored as a repository secret, and the review can be started from a comment on the pull request.
El Profesor6.06.3Shippie — Review is an agent loop with repository exploration rather than a single prompt over a diff, which is the difference between reading a change and understanding it.
La Inversora4.56.0Shippie — 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 Jefa6.36.0Proval — One container image against our own Git host, which is the shortest path to production on this board, and there is still no console and no audit export.
El Hacker7.87.5Proval — AGPL-3.0 and it takes any compatible endpoint, including Ollama and llama.cpp, so the one tool that reads all my code never has to phone anyone.

Picks are derived from each critic's own scores. Humans vote on matchups on the duels page.

Want a third column? The compare tool handles any two agents. Three-way comparisons are on the roadmap once the spec rows are all verified.