pullfrog vs squid
Open-source, model-agnostic GitHub bot: tag @pullfrog on any issue or PR and your own coding agent (BYOK) runs the task inside GitHub Actions, context via an internal MCP server. — versus — Claude Code plugin that turns a feature spec into a reviewed PR through a 5-agent pipeline — PA → SWE → Tester → PR-Reviewer → On-Call — with exactly two human gates.
Both turn repo intent into reviewed changes: squid pipelines spec→PR inside Claude Code; pullfrog embeds the agent in GitHub itself — tag a comment and Actions does the rest, any model.
| pullfrog | squid | |
|---|---|---|
| Stars | 822 | 136 |
| Forks | 45 | 20 |
| Language | TypeScript | Shell |
| License | MIT | Apache-2.0 |
| Last activity | yesterday | 4 days ago |
| Topics | coding | coding, orchestration |
| Curated connections | 2 | 6 |
pullfrog — the curator's take
The missing GitHub-native surface for coding agents: instead of copying issues into a terminal session, tag the bot and the work happens where the work lives — Actions runners, your keys, your choice of model, automated triggers for recurring flows. NOT for latency-sensitive interactive coding (Actions cold-starts apply), and 'agent with repo write access via bot' deserves the same permission audit you'd give any CI credential. Young (~800 stars) but moving fast.
squid — the curator's take
Squid is for people who already live in Claude Code and are tired of re-explaining team conventions every session: markdown specs + five adversarial agents (no agent both writes code and judges it) turn a spec into a PR while you only show up to approve the plan and merge. When NOT: you don't use Claude Code (it's a plugin, not a standalone tool), your stack is Rust/Java/mobile (specs are Python/TS/Go for now), or you already trust an in-house pipeline. Early days and opinionated by design — adopt the opinions or skip it.