#330 · Primary category: AI Coding Assistants
multilspy
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
superpowers
An agentic skills framework & software development methodology that works.
ECC
The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.
skills
Skills for Real Engineers. Straight from my .agents directory.
opencode
The open source coding agent.
andrej-karpathy-skills
A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls.