microsoft/multilspy

multilspy is a lsp client library in Python intended to be used to build applications around language servers.

What it solves

multilspy is a Python library that simplifies the process of interacting with various language servers via the Language Server Protocol (LSP). It removes the complexity of manually managing server binaries, JSON-RPC communication, and language-specific configurations, providing a unified API for static analysis of code repositories across multiple programming languages.

How it works

The library acts as a client that communicates with language servers (such as JDTLS for Java or Rust Analyzer for Rust). It automatically handles the downloading of platform-specific binaries and the setup/teardown of the servers. By providing a common interface, it allows users to perform queries like finding symbol definitions, references, and type-based completions regardless of the underlying language server being used.

Who it’s for

It is primarily designed for developers building AI-driven coding tools, such as those implementing Monitor-Guided Decoding (MGD) to ensure LLM-generated code is syntactically and semantically correct, or developers creating repository-level coding agents.

Highlights

  • Multi-language support: Supports a wide range of languages including Java, Python, Rust, C#, TypeScript, JavaScript, Go, Dart, Ruby, Kotlin, PHP, and C++.
  • Unified API: Provides a simple interface for common LSP requests like request_definition, request_completions, and request_hover.
  • Async Support: Offers both synchronous and asyncio-based APIs for integration into different execution contexts.
  • Automated Management: Handles the lifecycle of language server binaries and server-specific configuration parameters.

Related

  • Project
    graniet/llm

    A Rust library providing a unified API to interact with multiple LLM backends, enabling multi-step chains, agentic workflows, and a standardized REST API.

  • Project
    simonw/llm

    A CLI tool and Python library for interacting with multiple LLMs, both via remote APIs and local installations, featuring built-in logging and structured data extraction.

  • Project
    andrewyng/aisuite

    A lightweight Python library providing a unified Chat Completions API and an Agents API to build AI agents across multiple LLM providers with minimal code.

  • Project
    ahyatt/llm

    An Emacs Lisp library that provides a unified interface for interacting with various LLM providers, enabling developers to build AI-powered packages that work across different models.

  • Project
    oOo0oOo/lean-lsp-mcp

    An MCP server that enables LLM agents to interact with the Lean theorem prover via LSP, providing tools for proof state analysis and theorem searching.