#330 · Primary category: AI Coding Assistants

multilspy

ai ai4code artificial-intelligence code-analysis code-completion code-generation codegen huggingface-transformers language-server-client language-server-protocol large-language-model large-language-models llm lsp lsp-client neurips neurips-2023 program-synthesis transformer

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

Project last updated:08/27/26

GitHub Stars

603

Forks

109

Contributors

33

License

MIT

Why we included this project

multilspy is a Python library that wraps the Language Server Protocol, so you can pull static-analysis results like type-aware completions, symbol definitions, references, and hover signatures from language servers without writing your own JSON-RPC client. It handles the fiddly setup work: downloading the right server binary for your platform, starting and stopping the server, and passing the per-language configuration, which keeps your application code focused on what it wants to do with the analysis. Teams building code-completion features or repository-aware tooling, and researchers prototyping code generation with LLMs, will find it a practical foundation. The library grew out of Microsoft's Monitor-Guided Decoding work, where static analysis steers LLM output, a good hint at the kind of applications it was designed for. Both sync and asyncio APIs are available, and it supports a range of language servers, so it drops into an existing Python project without much friction.

Articles for this project

No articles for this project yet.

To suggest a topic or contribute an article, contact us.

Related projects in this category