Skip to the content
Know your tech before you buy it. Makers: get listed from $49/mo

LeIndex

github.com

  • Free plan
  • Windows
  • macOS
  • Linux
  • Web
  • API
  • Self-hosted
7.8 Club score Visit github.com

What LeIndex is

LeIndex is a free, open-source semantic code search engine for developers and AI coding tools. It searches repositories by combining TF-IDF lexical matching, Program Dependence Graph structure, and optional local ONNX neural scoring. Multiple repositories can be indexed and searched together. LeIndex runs as an MCP server for tools such as Claude Code, Cursor, and other compatible agents, with 20 MCP tools for search, analysis, indexing, reading, editing, renaming, and impact analysis. Local ONNX models and fragment embeddings keep processing on the user’s machine unless a remote provider is selected. OpenAI, Cohere, and custom OpenAI-compatible embedding endpoints require network access and API keys. Without an embedding backend, LeIndex uses offline TF-IDF search without semantic understanding. Installation options include Cargo, npm, PyPI, a release script, or source builds. It can run as a CLI, MCP server, or HTTP/WebSocket server, with an optional Bun and React dashboard.

Who it suits

LeIndex suits developers exploring codebases, onboarding to legacy projects, or searching across repositories. It also fits teams using MCP-compatible AI coding tools.

Good to know, and what to watch

  • Searches code by meaning and keywords
  • Indexes multiple repositories together
  • Offers 20 MCP tools
  • Local models avoid API costs
  • Runs on Windows, macOS, and Linux
  • Model files require a separate setup download
  • Semantic search needs an embedding backend
  • Remote embeddings require network access and API keys

The verdict

LeIndex combines structural, lexical, and optional neural code retrieval with MCP access for AI coding tools. Its offline fallback remains keyword-based, and model setup requires an additional download.

What the maker publishes

AI tools
LeIndex runs as an MCP server for AI coding tools, including Claude Code, Cursor, and other MCP-compatible agents. source
Analysis
LeIndex includes a five-phase codebase analysis pipeline and structural analysis of code relationships. source
Cloud embeddings
OpenAI, Cohere, and custom OpenAI-compatible embedding endpoints are supported and require network access and provider API keys. source
Cross-project
It can index and search multiple repositories together. source
Dashboard
An optional Bun and React dashboard provides project metrics and graph telemetry. source
Deployment
LeIndex provides Cargo, npm, PyPI, and release-script installation paths, and can run as a local CLI, MCP server, or HTTP/WebSocket server. source
Embedding providers
The README lists local Qwen3 ONNX embeddings and optional remote embeddings through OpenAI, Cohere, or a custom OpenAI-compatible endpoint. source
Fallback
Without an embedding backend, LeIndex falls back to offline TF-IDF keyword search, which the README says lacks semantic understanding. source
Fallback behavior
Without an embedding backend configured, LeIndex falls back to offline TF-IDF keyword search, which the README says lacks semantic understanding. source
Install paths
The README documents installation through Cargo, npm, PyPI, a release install script, or building from source. source
Integrations
The README provides setup instructions for Zed, Cursor, VS Code, Claude Code, Amp, OpenCode, Qwen CLI, iFlow CLI, Droid, Gemini CLI, and Claude Desktop. source
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. source
License
The repository states that LeIndex is distributed under the MIT license. source
License
The repository lists the project under the MIT license. source
Local privacy
The README says local ONNX models keep data on the user's machine and incur no API costs; fragment embeddings are also local unless a remote provider is chosen. source
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. source
MCP tools
LeIndex lists 20 MCP tools for search, analysis, indexing, reading, editing, renaming, and impact analysis. source
MCP tools
The README lists 20 MCP tools for functions such as search, project mapping, reading, editing, renaming, and impact analysis. source
Notable setup limit
The README says model files are not included in release artifacts and must be downloaded by running leindex setup. source
Operating systems
The README includes Windows, macOS, and Linux installation references and runtime library formats. source
Product
LeIndex is a semantic code search engine that searches code by meaning rather than keywords. source
Product
LeIndex is a semantic code search engine that searches code by meaning rather than only by keywords. source
Search
It combines TF-IDF lexical matching, Program Dependence Graph structure, and optional local ONNX neural scoring. source
Search methods
Its core retrieval combines TF-IDF lexical matching with Program Dependence Graph structure, and it can add local ONNX neural scoring. source

Checked against the maker's pages on 8 Oct 2026.