sourcebot-dev/sourcebot

Sourcebot is a self-hosted tool that helps humans and agents understand your codebase.

What it solves

Sourcebot is a self-hosted tool designed to help developers understand complex codebases. It eliminates the difficulty of navigating and querying large amounts of code across multiple repositories and branches, providing a centralized way to search and reason about code.

How it works

Sourcebot indexes repositories from various code host platforms. It combines a fast code search engine (supporting regex and boolean logic) with IDE-level code navigation (go-to-definition and find references). For its AI capabilities, it allows users to connect language model providers to enable a natural language interface where reasoning models can search the code, follow navigation references, and generate answers with inline citations and navigable snippets.

Who it’s for

Developers who need to operate across multiple repositories and branches and want a self-hosted solution for codebase understanding and AI-assisted querying.

Highlights

  • Ask Sourcebot: Natural language querying of codebases with grounded answers and inline citations.
  • Cross-Repo Search: High-speed search across all connected repositories and branches with advanced filtering.
  • IDE-level Navigation: Ability to jump to definitions and find references across the entire indexed codebase.
  • Built-in File Explorer: A modern UI featuring syntax highlighting and a file tree for exploring all indexed files.

Related

  • Project
    giancarloerra/SocratiCode

    An open-source codebase context engine that gives AI assistants deep semantic understanding of large repositories through hybrid search and dependency graphs.

  • Project
    defendend/Claude-ast-index-search

    A structural, AST-aware code navigation CLI that builds a local index of symbols and references to help humans and AI agents navigate large codebases efficiently.

  • Project
    study8677/repobrain

    A cross-IDE repository knowledge engine that creates a grounded Q&A system for codebases, allowing AI agents to provide accurate answers with file paths and line numbers.

  • Project
    FSoft-AI4Code/CodeWiki

    CodeWiki is an open‑source Python tool that uses large language models to automatically generate comprehensive, architecture‑aware documentation (markdown + Mermaid diagrams) for whole codebases across ten languages. It hierarchically decomposes a repository, runs a recursive multi‑agent LLM pipeline, and outputs ready‑to‑publish docs, with support for many LLM providers and a rich CLI.

  • Project
    vfarcic/dot-ai

    An npm‑published Node library that adds LLM‑driven assistants to Kubernetes/DevOps workflows. It provides a CLI and a managed platform (MCP) for natural‑language cluster queries, deployment recommendations, automated remediation, policy‑driven prompt libraries, and semantic doc search, all packaged for easy installation on a Kubernetes cluster.