# sunmh207/AI-Codereview-Gitlab

基于大模型(DeepSeek,OpenAI等)的 GitLab 自动代码审查工具；支持钉钉/企业微信/飞书推送消息和生成日报；支持Docker部署；可视化 Dashboard。

Repository: https://github.com/sunmh207/AI-Codereview-Gitlab
Canonical: https://ross.abutalabs.com/products/ai-codereview-gitlab
Language: Python
License: Apache-2.0
License Family: permissive
Topics: ai, codereview, gitlab, gpt, llm, deepseek
Last push: 2026-07-23T05:45:52+00:00

## Health v2 (maintenance only)
Score: 83/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 94, release rhythm 90, longevity 46
- inputs: {"age_days": 657, "days_push": 41, "days_rel": 66, "gap_med": 26, "n_releases_24m": 12}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1826, forks 403 (observed 2026-08-28T04:05:41.318196+00:00)

## What it is
A self-hosted automated code review application that uses large language models (DeepSeek, OpenAI, Anthropic, ZhipuAI, Qwen, Ollama) to review GitLab merge requests and pushes via webhooks. It posts review comments back to GitLab, pushes results to DingTalk/WeCom/Feishu, generates daily commit reports, and includes a Streamlit dashboard with review statistics.

## Use cases
- automate code review on gitlab merge requests
- ai code review with deepseek or openai
- send code review results to dingtalk or feishu
- generate daily development reports from git commits
- self-host an llm code review bot with docker
- track code review statistics across developers and projects

## When to choose
- your team uses GitLab (or GitHub/Gitea) and wants automated LLM-based review on every MR or push
- you want review notifications in DingTalk, WeCom, or Feishu plus daily reports
- you prefer a self-hosted Docker deployment with a visual dashboard

## When to avoid
- you need deep static analysis or security scanning rather than LLM-generated review comments
- you use a platform other than GitLab/GitHub/Gitea
- you cannot send code to third-party LLM providers due to privacy constraints

## Facets
- artifact type: application
- maturity: active
- function: code-review, llm-inference, webhook, agent-framework, analytics
- domain: developer-tools, version-control, large-language-models
- platform: python, self-hosted
- tags: gitlab, code-review, llm, deepseek, dingtalk, wechat-work, feishu, daily-report, dashboard, streamlit, automation, docker, web-server

## Member repositories
- sunmh207/AI-Codereview-Gitlab (main) score 83

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:05:41.318196+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T03:19:35.079978+00:00, confidence not recorded.
  - readme: https://github.com/sunmh207/AI-Codereview-Gitlab (fetched 2026-08-28T04:05:41.318196+00:00, sha 5e4c14e5422e)
- Data as of 2026-08-30T08:39:29.467469+00:00.