Vibe Coding Discover

AI Coding

open-code-review

View on GitHub

Fast, efficient, battle-tested at Alibaba's scale. Hybrid architecture code review tool: deterministic pipelines + LLM Agent, precise line-level comments, built-in multi-language ruleset (NPE, thread-safety, XSS, SQL injection), OpenAI & Anthropic compatible.

★ 43K3,057 forksGoApache-2.0alibaba

Alibaba's AI code review CLI in Go: a deterministic pipeline (file selection, bundling, rule matching) plus an LLM agent with tool use produces precise line-level review comments. Works on git diffs, branch ranges or full-file scans, supports OpenAI/Anthropic-compatible endpoints and plugins for Claude Code, Codex, Cur

Use Cases

Automated pull request code reviewCI/CD pipeline review gatingDetecting NPEsthread-safety issuesXSS and SQL injectionFull-file scanning of unfamiliar codebasesPosting line-level review comments on GitHub ActionsResuming interrupted large-changeset reviewsEmbedding review skills into Claude CodeCodexCursor and Kimi CodeReviewing branch ranges or single commitsDelegating review to a host AI coding agent without LLM configExtending the review agent with external tools via MCP

Built With

Language
Go
Frameworks
MCP Go SDK · OpenAI Go SDK · Anthropic Go SDK · Cobra · Bubble Tea · OpenTelemetry · tiktoken-go · Claude Code plugins · Codex plugins · Cursor plugins

Tags

code-review · cli · llm-agent · static-analysis · diff-review · security-rules · github-actions · ci-cd · mcp-server · agent-skills · go · multi-language · line-level-comments · pull-request · tool-use

open-code-review — Vibe Coding Discover