LeIndex review
A capable self-hosted choice for semantic search, code navigation, and impact analysis.
Reviewed by iTechGuides Editors · Editorial team · Updated Oct 2026
LeIndex is an open-source code search engine and code-intelligence tool for developers and AI coding tools working with large codebases. It indexes repositories using semantic retrieval, TF-IDF lexical retrieval, program-dependence relationships, and optional local ONNX neural embeddings. The result is a tool focused on more than text matching: users can search by meaning and intent, find symbols and their callers or callees, map projects, examine impact, and rename symbols across files. It is available for web, Windows, macOS, Linux, and API-based workflows, with deployment centered on self-hosting.
Its strongest fit is an engineering environment that needs deeper repository understanding across multiple projects. LeIndex supports cross-project indexing, Program Dependence Graph analysis, dashboard metrics, and graph telemetry. The MCP server can operate through CLI, HTTP, and WebSocket modes, while integrations include Claude Code, Cursor, VS Code, Zed, Amp CLI, OpenCode, Qwen CLI, and iFlow CLI. Optional local embeddings also keep the neural-search component within a local deployment model. These capabilities make it more suitable for code navigation, architectural analysis, and AI-assisted development than for a narrow search-only workflow.
LeIndex is distributed as open-source software under the MIT license through GitHub releases, Cargo, npm, and PyPI, with installers for Linux, macOS, and Windows. There are no paid tiers to compare, so the main trade-off is operational: teams must handle a self-hosted tool and choose how to connect it to their editors or coding agents. The workflow is particularly compelling for teams that value repository control, semantic analysis, and programmable access. Teams seeking a managed service or a vendor-provided IDE extension should consider a different category fit.
LeIndex pros and cons
- Where it wins
- Combines semantic, TF-IDF, and dependency-graph analysis
- Supports callers, callees, impact analysis, and cross-file renaming
- Works with multiple repositories and major AI coding tools
- Where it doesn't
- Self-hosted deployment puts installation and operation on the team
- Advanced workflows may require CLI, MCP, HTTP, or WebSocket use
- Its language parser coverage is not defined in the published details
LeIndex fact sheet, pricing and score →
Advertiser disclosure: iTechGuides is reader-supported. Vendors can pay for top positions in our rankings and for a place on other products' pages, and we may earn a commission when you click some links. Bought places stand at the number bought; this page and our disclosure say so. Paying vendors may get a fuller, more detailed review from our editors, and that review can change their score. How we rank.
Last updated · How we research and update