Skip to content
SPECIFICTION
Get listed

LeIndex

github.com

WebWindowsmacOSLinuxAPISelf-hosted
Visit github.com
Spec score 7.5 #22 of 42 in Code Search Tools

Spec sheet

Product
LeIndex is a semantic code search engine that searches code by meaning rather than only by keywords.Read 8 Oct 2026 · github.com
Deployment
LeIndex provides Cargo, npm, PyPI, and release-script installation paths, and can run as a local CLI, MCP server, or HTTP/WebSocket server.Read 8 Oct 2026 · github.com
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.Read 8 Oct 2026 · github.com
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.Read 8 Oct 2026 · github.com
License
The repository lists the project under the MIT license.Read 8 Oct 2026 · github.com
AI tools
LeIndex runs as an MCP server for AI coding tools, including Claude Code, Cursor, and other MCP-compatible agents.Read 4 Oct 2026 · github.com
Analysis
LeIndex includes a five-phase codebase analysis pipeline and structural analysis of code relationships.Read 8 Oct 2026 · github.com
Cloud embeddings
OpenAI, Cohere, and custom OpenAI-compatible embedding endpoints are supported and require network access and provider API keys.Read 4 Oct 2026 · github.com
Cross-project
It can index and search multiple repositories together.Read 4 Oct 2026 · github.com
Dashboard
An optional Bun and React dashboard provides project metrics and graph telemetry.Read 4 Oct 2026 · github.com
Embedding providers
The README lists local Qwen3 ONNX embeddings and optional remote embeddings through OpenAI, Cohere, or a custom OpenAI-compatible endpoint.Read 8 Oct 2026 · github.com
Fallback
Without an embedding backend, LeIndex falls back to offline TF-IDF keyword search, which the README says lacks semantic understanding.Read 4 Oct 2026 · github.com
Fallback behavior
Without an embedding backend configured, LeIndex falls back to offline TF-IDF keyword search, which the README says lacks semantic understanding.Read 8 Oct 2026 · github.com
Install paths
The README documents installation through Cargo, npm, PyPI, a release install script, or building from source.Read 4 Oct 2026 · github.com
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.Read 8 Oct 2026 · github.com
MCP tools
The README lists 20 MCP tools for functions such as search, project mapping, reading, editing, renaming, and impact analysis.Read 8 Oct 2026 · github.com
Notable setup limit
The README says model files are not included in release artifacts and must be downloaded by running leindex setup.Read 8 Oct 2026 · github.com
Operating systems
The README includes Windows, macOS, and Linux installation references and runtime library formats.Read 8 Oct 2026 · github.com
Search
It combines TF-IDF lexical matching, Program Dependence Graph structure, and optional local ONNX neural scoring.Read 4 Oct 2026 · github.com
Search methods
Its core retrieval combines TF-IDF lexical matching with Program Dependence Graph structure, and it can add local ONNX neural scoring.Read 8 Oct 2026 · github.com
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.Read 8 Oct 2026 · github.com

Where Specifiction places it

Alternatives to LeIndexAll alternatives →