Code Fundi vs Shebe
Code Fundi
codefundi.appShebe
github.comSide by side
| Figure | Code Fundi | Shebe |
|---|---|---|
| Price from | $21/mo | Free |
| Free plan | — | Yes |
| Free trial | — | — |
| Open source | — | — |
| Web | Yes | — |
| Windows | — | Yes |
| macOS | — | Yes |
| Linux | — | Yes |
| API | Yes | Yes |
| Self-hosted | — | Yes |
| Plans published | 4 | 1 |
| Spec score · Code Search Tools | 7.8 (#10) | 7.8 (#12) |
| Integrations | Code Fundi provides a web app, an MCP server, a VS Code and Cursor extension, and an HTTP API. | The installation guide documents MCP setup and a Zed editor configuration, and points to the organization for VS Code and other editor extensions. |
| Intended users | The maker describes the product as infrastructure for AI agents, teams, and applications, with use cases including agent RAG, legacy modernization, engineering velocity, and technical due diligence. | The project positions Shebe for developers and AI coding agents working with large codebases and says it complements structural tools such as Serena MCP. |
| Search | It supports semantic search, documentation-aware grep, and code grep across indexed repositories. | Code search supports ranked results, phrases, Boolean queries, and literal matching. |
| Support | The Free plan includes email support, Dev and Startup include priority support, and Pro includes dedicated support. | The project provides installation, configuration, troubleshooting, and MCP setup guides in its repository. |
Plans
Code Fundi
- Dev$21 a month
- Startup$62 a month
- Pro$210 a month
- FreePrice not published
In their own words
Code Fundi
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.
Shebe
Shebe is a local code-search tool that uses BM25 full-text search across code repositories. It ranks results and supports phrase searches, Boolean queries, and literal matching. Fourteen MCP tools serve coding agents with functions including search, repository indexing, file reading, and reference finding. Shebe runs without embeddings, a GPU, or a cloud service, but repositories must be cloned locally before indexing; remote repository URLs are not supported. Its text-based search does not provide semantic similarity, so related words such as “login” and “authenticate” may not match. Prebuilt binaries are listed for Linux x86_64 and macOS on Apple Silicon and Intel; Linux ARM64 is planned. Windows users need to build it from source. The installation guide covers MCP setup and Zed configuration and points to the organization for VS Code and other editor extensions. Shebe is free and licensed under Apache-2.0. The README reports 2 ms query latency and indexing rates from 1,928 to 11,210 files per second in its listed benchmarks.