Skip to content

Latest commit

 

History

History

Folders and files

NameName
Last commit message
Last commit date

parent directory

..
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

README.md

AI-Git-Bot Documentation

Welcome! The documentation is organized by who you are. Pick your role and start from there.


👤 Users — I work with the Git platform, a bot is already set up for me

You interact with AI-Git-Bot entirely through Gitea / GitHub / GitLab / Bitbucket — assigning issues, requesting reviews, and mentioning the bot in comments.

Document What it covers
Using the Bot Requesting reviews, talking to the bot with @mentions, slash commands, assigning issues to coding and writer bots, what the test workflows post on your PR

🛠️ Administrators — I set up and maintain the bot, its integrations, and workflows

You run the software, connect it to your Git hosts and AI providers, and configure bots and workflows through the admin web UI.

Install & operate

Document What it covers
Deployment Docker Compose deployment, environment variables, production setup
Admin Guide The admin web UI: creating bots, AI integrations, Git integrations, workflow configurations
Migration 1.0 → 1.1 · Migration 1.6 → 1.7 · Migration 1.12 → 1.13 Upgrade notes between releases

Connect a Git provider

Document What it covers
Gitea Setup Bot user, permissions, API tokens, webhooks for Gitea
GitHub Setup Bot user, permissions, PAT tokens, webhooks for GitHub / GitHub Enterprise
GitLab Setup Bot user, permissions, PAT tokens, webhooks for GitLab
Bitbucket Setup API tokens and webhook configuration for Bitbucket Cloud

Connect an AI provider

Cloud providers (Anthropic, OpenAI, Google AI / Gemini) only need an API key — see the Admin Guide. For local LLMs:

Document What it covers
Using Ollama Running with local LLMs via Ollama
Using llama.cpp Running with llama.cpp and GBNF grammar support

Configure bots & workflows

Document What it covers
Agents Coding agent and technical-writer agent — setup, configuration, security, limitations
PR Workflows Workflow configurations, trigger conditions, deployment targets
Agentic PR Workflows (concept) Feature overview and persona-driven user stories for the workflow subsystem
Unit-Test Author Workflow AI unit-test generation for PR diffs, supported runners, write-safety guards
Full-stack QA / E2E Workflow Per-PR preview environments, generated Playwright suites, teardown lifecycle
Agentic Review Workflow Read-only agentic PR review with repository and MCP tool access
CI Action Recipes CI_ACTION deployment recipes per Git provider
Webhook Recipes WEBHOOK deployment recipes (Jenkins, scripts, …)
MCP Server Handling Attaching remote MCP servers, tool whitelist selection, call transparency
Bot Tool Configurations Per-bot whitelist of built-in agent tools
Tool-Calling Troubleshooting What to do when a model misbehaves with tools, incl. the legacy tool-calling switch

🧪 Testers — I want to try out features without touching production

Document What it covers
Testing Guide Self-contained docker-compose system-test stacks, local LLM setups, and how to write useful bug reports
System-test recipes Laptop-runnable stacks: local Gitea, local GitLab, E2E sample app, deployment strategies

💻 Developers — I work with the code

Document What it covers
Local Development Building, testing, running natively, adding providers
Architecture The gateway concept and top-level system design
Contributing Contribution guidelines and coding conventions
Security Policy Vulnerability reporting

📚 Project meta

Document What it covers
Changelog Release notes and notable changes
Pitch Why this project exists and how it compares to alternatives
Code of Conduct Community standards
Citation Metadata · CodeMeta Citation and machine-readable software metadata
LLM Index · Full LLM Reference Entry points for LLMs and RAG systems