idosal/git-mcp
GitMCP is a free, open-source remote MCP server that transforms any GitHub project into an AI-accessible documentation hub to eliminate code hallucinations and provide accurate, up-to-date project information.
Awesome AI Agents › Documentation & Testing Assistants
divar-ir/ai-doc-gen
ai-doc-gen is a Python tool that generates code documentation for a repository by running a team of LLM agents over it. Five specialized analysis agents work concurrently, each covering one facet of the codebase: overall structure, dependencies, data flow, request flow and APIs. Their findings are written as reusable analysis documents under .ai/docs/, and a second stage of generation agents turns those analyses into a README with configurable sections plus configuration files for AI coding assistants, namely CLAUDE.md, AGENTS.md and .cursor/rules/*.mdc entries. The repository doubles as a Claude Code plugin, installable from a marketplace entry, which exposes three skills: analyze-codebase, generate-readme and generate-ai-rules. Used that way it needs no API keys or Python setup because the host assistant performs the work. Run standalone it requires Python 3.13 and access to any OpenAI-compatible LLM endpoint, so OpenAI, gateways, OpenRouter or local models all work, and each agent can be pointed at a different model and endpoint. Concurrency is controlled by a worker pool that defaults to the CPU count. Configuration is layered from Pydantic defaults through a .ai/config.yaml file to command-line flags. Reliability features include agent-level retries and an HTTP client with exponential backoff that honours Retry-After headers for rate limits, and observability is provided through OpenTelemetry tracing with logfire and optional Langfuse integration. A GitLab cronjob mode discovers recently active projects, runs the analysis and opens merge requests with refreshed documentation, which is how the authors keep documentation from going stale across many repositories. It is built with pydantic-ai and aimed at engineering organizations facing onboarding and documentation debt.
https://github.com/divar-ir/ai-doc-gen
Also in Documentation & Testing Assistants
steipete/agent-rules
Agent Rules is a repository of reusable rules and knowledge documents designed to improve the effectiveness of AI coding assistants like Claude Code and Cursor in software development workflows.
truera/trulens
TruLens is a tool for systematic evaluation and tracking of large language model experiments, enabling developers to identify failure modes and iteratively improve their applications through fine-grained instrumentation and comprehensive feedback.
eli64s/readme-ai
ReadmeAI is a developer tool that automatically generates customizable README files using advanced language models and supports multiple AI providers and offline mode.
CodeBoarding/CodeBoarding
Python tool that combines static analysis with LLM reasoning to generate architecture diagrams and component documentation for a codebase, usable from a CLI, IDE extensions, a GitHub Action or CI.
samchon/nestia
Nestia is a powerful helper library suite for NestJS that enhances API development, testing, and AI chatbot integration with high performance and developer-friendly tools.
OpenBMB/RepoAgent
RepoAgent is an LLM-powered framework that automates repository-level code documentation generation to help developers quickly understand and maintain software projects.
Mintplex-Labs/anythingllm-docs
anythingllm-docs is a comprehensive and well-structured documentation repository for the AnythingLLM platform by Mintplex Labs, facilitating user and developer engagement through detailed guides and active maintenance.