The self-hosted AI workflow automation platform for Git repositories — PR reviews, test generation, issue refinement, coding agents, documentation and translation sync, inside Gitea, GitHub, GitLab, and Bitbucket.

Self-hosted AI workflow automation for Git repositories MIT license
📄 WHY.md better engineering hygiene through automation
📄 WORKFLOWS.md 10 event-driven workflows, all opt-in
📁 integrations/ 5 AI providers × 4 Git platforms via SPI
📁 screenshots/ reviews, inline comments & coding agents on 4 platforms
📄 INSTALL.md one docker run, up in 5 minutes
📄 SECURITY.md AES-256-GCM, tool whitelists, audit trail
README.md

⚡ AI-Git-Bot

licenseMIT platformsgitea · github · gitlab · bitbucket deploy1 docker image workflows10

The self-hosted AI workflow automation platform for Git repositories. AI-Git-Bot automates the engineering chores every team knows should happen — PR reviews, tests, docs, translations, issue refinement, coding — triggered by the Git events you're already producing. No new process. No migration. No vendor lock-in.

terminal — bash
$ docker run -p 8080:8080 tmseidel/ai-git-bot:latest

Then open http://localhost:8080 — create your admin account and wire the first bot

Every engineering team knows what should happen — careful PR reviews, regression tests for bugs, up-to-date documentation, consistent translation coverage. The problem isn't disagreement. It's that these tasks are uncomfortable, repetitive, and easy to postpone when deadlines get tight. AI-Git-Bot turns them into repeatable workflows that happen automatically.

No new development process

The bot works inside your existing Git platform. Your developers don't need to learn a new tool.

No migration project

Connect to your existing repositories via webhooks. Nothing needs to move.

No vendor lock-in

Mix any AI provider with any Git platform. Self-hostable end-to-end. Your code stays in your infrastructure.

Workflows — automation, not another coding assistant

AI-Git-Bot is not another tool to help developers write code faster. It's a self-hosted automation layer for the work around the code — every workflow below is triggered by an event your team already produces, and each one ships behind an opt-in flag.

PR Review enabled by default
on: pull_request.opened · review re-requested
Review comments and findings with inline feedback, posted straight into the PR thread.
Interactive Q&A
on: @bot mention in PR comments
Context-aware conversation in the PR thread — the bot remembers the diff and the discussion.
Issue → Code coding agent
on: issue.assigned to coding bot
Produces a pull request implementing the change, with commits on its own branch.
Issue → Better Issue refinement
on: issue.assigned to writer bot
Structured issue with background, requirements, acceptance criteria.
Issue Triage routing
on: issue.opened · assigned to triage bot
Agentic routing to the right owner (person, bot, or none) with a posted reason.
Unit Test Generation tests
on: pull_request.opened · command trigger
Generated tests committed straight to the PR branch.
Full-Stack QA (E2E) e2e
on: pull_request.opened
Playwright suite executed against the preview environment, report posted to the PR.
README Sync docs
on: pull_request.opened · command trigger
Documentation updated to match the code changes.
i18n Coverage translations
on: pull_request.opened · command trigger
Missing translations drafted across locale files.
PR Re-Review
on: force-push · review request
Updated analysis on the new head commit.
Note Copilot helps developers write code faster. AI-Git-Bot helps teams automate reviews, tests, issues and pull-request workflows. Many teams use both.

Who is AI-Git-Bot for?

Three reasons teams adopt it — many teams overlap across these concerns.

🏢 Running Gitea and missing modern AI tooling?

Many teams choose Gitea for ownership of their source code. Unfortunately, most AI products focus on GitHub. AI-Git-Bot brings AI code reviews, test generation, issue authoring, documentation upkeep and interactive PR discussions directly into Gitea — without forcing developers to leave their existing workflows.

"Copilot-style workflow automation for Gitea."

🔒 Need AI but cannot send source code to external services?

Many organizations cannot use cloud-only AI products due to compliance, privacy or contractual requirements. AI-Git-Bot supports Ollama, llama.cpp, self-hosted Git platforms, private networks and provider-independent architectures. Source code, prompts, credentials and models remain under your control.

"AI automation without handing your repos to a SaaS vendor."

🚀 Maintaining repositories with too much engineering overhead?

Every repository accumulates engineering chores: reviews, tests, documentation, acceptance criteria, follow-up fixes. AI-Git-Bot turns those into repeatable workflows triggered by events your team is already producing — PR opened, reviewer requested, issue assigned, @bot mentioned.

"The AI teammate that never forgets the boring but important work."

Integrations — mix & match any AI provider with any Git platform

AI-Git-Bot is a gateway, not a script. Every Git platform plugs in through a RepositoryApiClient SPI. Every AI provider plugs in through an AiClient SPI. One admin UI, one PostgreSQL database, one set of encrypted credentials.

🤖 AI Providers

5 ship today — cloud providers need only an API key; local LLMs run on your own hardware.
Anthropic (Claude)
cloud · api key
Claude models. First-class review & coding workflows.
OpenAI + Compatible
cloud · api key
GPT models and any OpenAI-compatible endpoint.
Google Gemini
cloud · api key
Gemini models via API key.
Ollama
self-hosted · air-gapped
Local LLMs on your own hardware — nothing leaves your infrastructure.
llama.cpp
self-hosted · air-gapped
GGUF models served locally via llama.cpp server.

🔗 Git Platforms

4 ship today — manage several simultaneously from a single admin UI.
Gitea
self-hosted · webhook
Full reviews, inline comments, coding agents — Copilot-style automation for Gitea.
GitHub + Enterprise
cloud / self-hosted · webhook
github.com and GitHub Enterprise Server.
GitLab CE/EE
cloud / self-hosted · webhook
Merge request reviews and coding agents.
Bitbucket Cloud
cloud · webhook
PR reviews on Bitbucket Cloud workspaces.

Screenshots across every Git platform

AI-Git-Bot works the same way everywhere — reviews, inline comments, E2E test reports, and coding agents across Gitea, GitHub, GitLab, and Bitbucket.

Gitea code review
Gitea — PR code review
GitHub code review
GitHub — Code review with comment
GitLab merge request review
GitLab — Merge request review
Bitbucket code review
Bitbucket — Code review
Gitea inline comment conversation
Gitea — Inline review conversation
Gitea PR with E2E test run
Gitea — Full-stack QA / E2E report
GitHub coding agent
GitHub — Coding agent implements an issue
GitLab coding agent
GitLab — Coding agent implements an issue

Getting started — up and running in 5 minutes

One Docker image, one PostgreSQL database, one admin UI. No Kubernetes required.

1

Run the container

docker run -p 8080:8080 tmseidel/ai-git-bot:latest

2

Open the Admin UI

Navigate to http://localhost:8080 and create your administrator account.

3

Connect AI & Git

Create an AI Integration (Anthropic, OpenAI, Ollama, …) and a Git Integration (Gitea, GitHub, GitLab, Bitbucket). API keys are encrypted at rest (AES-256-GCM).

4

Create a Bot

Create a bot combining one AI integration with one Git integration. Enable the workflows you want. Copy its unique Webhook URL.

5

Wire the Webhook

Configure the webhook in your Git provider. Done. Assign the bot as a reviewer on a PR — watch it post its first review.

Designed for production from day one

Adoption risk is the #1 reason AI-in-the-SDLC pilots die. Every design choice below exists to keep that risk near zero.

Opt-In Everywhere

Every workflow ships behind a prworkflow.<name>.enabled flag. Only review defaults to true. Nothing changes for repos you don't touch.

Encrypted at Rest

Every credential, webhook secret, and deployment-target config is encrypted with AES-256-GCM. API keys never appear in logs.

Operator-Owned Tool Whitelists

Per-bot built-in tool whitelist + per-MCP-config tool whitelist. The admin decides what the agent can do — not the LLM, not the prompt.

No Silent Deploys

The bot triggers your existing CI — it never invents a deploy path. Four interchangeable DeploymentStrategy implementations keep deployment under your control.

Fully Auditable

Every workflow run, step, and tool call is persisted. Micrometer meters (prworkflow.run_total, prworkflow.run_duration_seconds) exposed at /actuator/prometheus.

Cost-Bounded

Workflow params expose hard caps (maxTestCases, maxRetries) and the agent loop honours the shared agent.budget.* token budget.

Suite Promotion

Generated E2E tests don't evaporate on PR close. Four lifecycle modes (ephemeral, commit-to-pr, offer-as-pr, promote-on-merge) let tests graduate into the codebase under operator control.

Backwards Compatible

Every new column on bots is nullable. Existing bots without a WorkflowConfiguration keep running the legacy review workflow only. No migration drama.

Not another coding assistant

It's a self-hosted automation layer for software delivery workflows. If your team already knows what good engineering practices look like — but struggles to do them consistently — AI-Git-Bot was built for exactly that problem. Wire one bot. Let the chores take care of themselves.