LeIndex

Free plan APILinuxMacSelf-hostedWebWindows

What LeIndex is

LeIndex is a code search and analysis tool for developers who need to find code by meaning and explore relationships across repositories. Its retrieval combines TF-IDF keyword matching with Program Dependence Graph structure, and can add neural scoring from local ONNX models. It can index and search multiple repositories together, and its five-phase analysis pipeline examines codebase structure and relationships.

LeIndex can run as a local CLI, an MCP server for AI coding tools, or an HTTP/WebSocket server. Its 20 MCP tools cover search, analysis, indexing, reading, editing, renaming, and impact analysis. The README provides setup instructions for tools including Zed, Cursor, VS Code, Claude Code, and Gemini CLI. Embeddings can use local Qwen3 ONNX models or remote OpenAI, Cohere, and custom OpenAI-compatible endpoints. Local models keep data on the user's machine and do not incur API costs; remote providers require network access and API keys. Without an embedding backend, search falls back to offline TF-IDF and does not provide semantic understanding. LeIndex is free, open source under the MIT license, and has installation paths through Cargo, npm, PyPI, a release script, or source builds. An optional Bun and React dashboard displays project metrics and graph telemetry.

Who it suits

LeIndex suits developers exploring unfamiliar or legacy code and teams searching across multiple repositories. It also fits AI coding tool users who want code search and analysis through an MCP-compatible agent.

What it does well

Search combines lexical matching with code structure.
Can index and search multiple repositories together.
Offers 20 MCP tools for code tasks.
Local ONNX embeddings keep data on the machine.
Free and distributed under the MIT license.

What to know first

Without an embedding backend, search lacks semantic understanding.
Model files must be downloaded separately with leindex setup.
Remote embedding providers require network access and API keys.

Limits

The README says model files are not included in release artifacts and must be downloaded using leindex setup. Without an embedding backend, LeIndex falls back to offline TF-IDF keyword search, which lacks semantic understanding.

Getting started

Choose an installation path: Cargo, npm, PyPI, the release install script, or a source build.
Install LeIndex for Windows, macOS, or Linux.
Run leindex setup to download the model files.
Configure local or remote embeddings, or use the offline TF-IDF fallback.
Connect an AI coding tool using the README instructions, or run LeIndex as a CLI or server.

Verdict

Choose LeIndex if you want repository search that combines keyword matching, structural analysis, and optional local neural scoring. It is also suited to AI coding workflows through its MCP server. Look elsewhere if you need semantic search without configuring an embedding backend, since the fallback is offline keyword search.

Questions

How much does LeIndex cost?

LeIndex is free and open source under the MIT license.

Which platforms does it support?

The listed platforms are API, Linux, macOS, self-hosted, web, and Windows. The README includes Windows, macOS, and Linux installation references.

Can it connect to AI coding tools?

Yes. It runs as an MCP server, and the README provides setup instructions for tools including Claude Code, Cursor, VS Code, and Gemini CLI.

Does LeIndex offer local embeddings?

Yes. The README lists local Qwen3 ONNX embeddings. It also supports optional remote embeddings through OpenAI, Cohere, and custom OpenAI-compatible endpoints.

Can I use search without an embedding backend?

Yes. LeIndex falls back to offline TF-IDF keyword search, which does not provide semantic understanding.

What does the optional dashboard provide?

The Bun and React dashboard provides project metrics and graph telemetry.

Facts from LeIndex's own pages

AI tools: LeIndex runs as an MCP server for AI coding tools, including Claude Code, Cursor, and other MCP-compatible agents. · github.com, 4 Oct 2026
Analysis: LeIndex includes a five-phase codebase analysis pipeline and structural analysis of code relationships. · github.com, 8 Oct 2026
Cloud embeddings: OpenAI, Cohere, and custom OpenAI-compatible embedding endpoints are supported and require network access and provider API keys. · github.com, 4 Oct 2026
Cross-project: It can index and search multiple repositories together. · github.com, 4 Oct 2026
Dashboard: An optional Bun and React dashboard provides project metrics and graph telemetry. · github.com, 4 Oct 2026
Deployment: LeIndex provides Cargo, npm, PyPI, and release-script installation paths, and can run as a local CLI, MCP server, or HTTP/WebSocket server. · github.com, 8 Oct 2026
Embedding providers: The README lists local Qwen3 ONNX embeddings and optional remote embeddings through OpenAI, Cohere, or a custom OpenAI-compatible endpoint. · github.com, 8 Oct 2026
Fallback: Without an embedding backend, LeIndex falls back to offline TF-IDF keyword search, which the README says lacks semantic understanding. · github.com, 4 Oct 2026
Fallback behavior: Without an embedding backend configured, LeIndex falls back to offline TF-IDF keyword search, which the README says lacks semantic understanding. · github.com, 8 Oct 2026
Install paths: The README documents installation through Cargo, npm, PyPI, a release install script, or building from source. · github.com, 4 Oct 2026
Integrations: The README documents MCP integrations for Claude Code, Cursor, VS Code, Zed, Amp, OpenCode, Qwen CLI, Gemini CLI, iFlow CLI, Droid, and Claude Desktop. · github.com, 8 Oct 2026
License: The repository lists the project under the MIT license. · github.com, 8 Oct 2026
Local privacy: The README says local ONNX models keep data on the user's machine, and that fragment embeddings remain local unless a remote provider is selected. · github.com, 8 Oct 2026
MCP tools: The README lists 20 MCP tools for functions such as search, project mapping, reading, editing, renaming, and impact analysis. · github.com, 8 Oct 2026
Notable setup limit: The README says model files are not included in release artifacts and must be downloaded by running leindex setup. · github.com, 8 Oct 2026
Operating systems: The README includes Windows, macOS, and Linux installation references and runtime library formats. · github.com, 8 Oct 2026
Product: LeIndex is a semantic code search engine that searches code by meaning rather than only by keywords. · github.com, 8 Oct 2026
Search: It combines TF-IDF lexical matching, Program Dependence Graph structure, and optional local ONNX neural scoring. · github.com, 4 Oct 2026
Search methods: Its core retrieval combines TF-IDF lexical matching with Program Dependence Graph structure, and it can add local ONNX neural scoring. · github.com, 8 Oct 2026
Security: The README says database discovery is opt-in, sensitive directories such as .ssh and .aws are automatically excluded, and SQL operations use parameterized queries. · github.com, 8 Oct 2026
Who it is for: The project describes itself as built for developers and AI coding tools, including use for onboarding, legacy code exploration, and cross-project search. · github.com, 8 Oct 2026

Where LeIndex stands on Freedom251

Code Search Tools#14 of 42