Code Fundi vs Sourcebot

Code Fundi turns indexed repositories into searchable maps of a codebase for AI agents, teams, and applications. Search combines semantic search with documentation-aware and code grep; research adds AI synthesis grounded in repository search results. Its blast-radius analysis maps dependents, data flows, entry points, and call edges, and requires a DEV plan or higher. Users can access it through a web app, MCP server, HTTP API, or extensions for VS Code and Cursor; the maker also lists Windsurf support. The versioned API covers search, research, indexing, blast-radius analysis, Markdown blueprints, file documentation, history, and account utilities. Private repositories require a linked GitHub account with access. The maker says proprietary code is not used to train public models and describes its approach as zero-data retention. Plans set credit allowances, private repository caps, usage-log retention, and Markdown detail levels; research and chat can add model usage on top of base credit costs. Free includes 500 credits and email support; paid plans are Dev at $21 a month, Startup at $62 a month, and Pro at $210 a month.

Sourcebot is a self-hosted tool for searching, navigating, and understanding complex enterprise codebases. Search covers repositories and branches, with regular expressions, filters, boolean logic, and suggestions. Symbol navigation includes go to definition and find references. Its MCP server gives coding agents tools to search code, read files, and resolve symbols across an organization's repositories.

Supported code hosts include GitHub, GitLab, Bitbucket, Azure DevOps, Gerrit, and Gitea, both cloud and self-managed. Ask Sourcebot connectors communicate over MCP and use the connected user's permission boundaries; documented examples include Linear and Jira. Ask Sourcebot requires at least one language model provider configured, with documented providers including OpenAI, Anthropic, Bedrock, Vertex, and Mistral. Sourcebot runs as a single Docker container on customer infrastructure, on-premises or in the cloud. The company says code, indexes, queries, and AI inputs and outputs remain within the customer's environment. Basic is free; Pro costs $20 a month billed per user and includes a 14-day free trial.