open-code-review vs pullfrog
Alibaba's battle-tested AI code-review CLI: deterministic pipelines + LLM agent, line-level comments, tuned rulesets (NPE, XSS, SQLi) — higher precision than general agents at ~1/9 the tokens. — versus — 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.
Both put an AI agent on your GitHub PRs. pullfrog is the generalist — @mention it and your own agent runs any task in Actions; Open Code Review is the specialist — reviews only, hybrid deterministic+LLM, precision-tuned line comments.
| open-code-review | pullfrog | |
|---|---|---|
| Stars | 11k | 827 |
| Forks | 755 | 47 |
| Language | Go | TypeScript |
| License | Apache-2.0 | MIT |
| Last activity | today | 7 days ago |
| Topics | coding | coding |
| Curated connections | 1 | 3 |
open-code-review — the curator's take
Two years as Alibaba's internal review assistant before open-sourcing, and it shows: the hybrid architecture (deterministic checks + tool-using LLM agent) is tuned for precision over recall — fewer, better line-level comments instead of noise — and their 200-PR benchmark honestly reports the trade-off, including losing to general agents on recall. `ocr scan` reviews whole files, useful for auditing unfamiliar code with no diff. Bring your own endpoint (OpenAI/Anthropic-compatible). NOT a replacement for your coding agent's judgment on architecture — it's a defect-finder (NPE, thread-safety, XSS, SQLi rulesets), strongest on the bug classes it was fine-tuned for; the deliberate low-recall bias means a clean review is not a clean PR.
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.