tree-sitter-language-pack
<!-- Project Info -->
<a href="https://github.com/xberg-io/tree-sitter-language-pack/blob/main/LICENSE">
<img src="https://img.shields.io/badge/License-MIT-007ec6" alt="License" />
</a>
<a href="https://docs.tree-sitter-language-pack.xberg.io">
<img src="https://img.shields.io/badge/Docs-tree--sitter--language--pack-007ec6" alt="Documentation" />
</a>
Parse and understand source code in 372 languages, from the language you already work in — with one dependency and no grammars to compile.
What and Why?
Add one package and you can parse any of 372 languages, walk their syntax trees, pull out functions, classes, imports, and symbols, and split code into chunks an LLM can use. It works the same whether you call it from Python, Node.js, Go, Java, C#, Ruby, PHP, Elixir, and eight more, or from the shell via the CLI and MCP server.
tree-sitter gives fast, incremental parsers for individual languages, but wiring up hundreds of grammars — and reaching them from a non-C ecosystem — is the hard part. tree-sitter-language-pack does that work for you: it bundles the most comprehensive set of grammars available behind a single API, ships native bindings for 15 languages, and downloads each parser on first use so the install stays small.
Reach for it whenever you need to process, inspect, or analyze code — building developer tooling, feeding a RAG pipeline, or giving an agent structural understanding of a codebase.
Features
| Feature | Description |
|---|---|
| 372 languages | Pre-compiled parsers at ABI 14 (backwards compatible with tree-sitter 0.21–0.26) |
| Code intelligence | Extract functions, classes, imports, docstrings, and symbols from source |
| Data extraction | Hierarchical key-value trees from 17 config/data formats (JSON, YAML, TOML, XML, CSV, …) |
| Host-native language API |
get_language() returns native Language objects in Python, Node.js, Go, Java, C#, Kotlin, Swift, Zig, and C |
| On-demand downloads | Parsers are fetched on first use and cached locally for fast, offline reuse |
| Prefetch & warming |
prefetch() loads (and downloads) every grammar you need up front, so hot loops only parse |
| Bundled queries |
highlights, injections, locals, tags, indents, and folds .scm queries per language, with a process-wide compiled-query cache (Rust) |
| Selective installation | Download only the languages you need; unused parsers are never downloaded |
| Polyglot bindings | Native bindings across 15 languages, including a C ABI for everything else |
| CLI & MCP server |
ts-pack download to pre-fetch parsers; MCP integration for AI agents |
Supported Languages
This pack includes 372 languages. See the full language list for every supported grammar with extensions and repository links.
Grammars & Bundled Queries
Each grammar bundles a subset of the six standard tree-sitter query types. The table below shows which .scm queries ship with every grammar.
⭐ Star this repo to show your support — it helps others discover tree-sitter-language-pack.
Quick Start
Language Packages
cargo add tree-sitter-language-packSee Rust README for full documentation.
pip install tree-sitter-language-packSee Python README for full documentation.
npm install @xberg-io/tree-sitter-language-packSee Node.js README for full documentation.
go get github.com/xberg-io/tree-sitter-language-pack/packages/goSee Go README for full documentation.
Available on Maven Central as io.xberg.treesitterlanguagepack:tree-sitter-language-pack. See Java README for the dependency snippet and current version.
dotnet add package XbergIo.TreeSitterLanguagePackSee .NET README for full documentation.
gem install tree_sitter_language_packSee Ruby README for full documentation.
composer require xberg-io/tree-sitter-language-packSee PHP README for full documentation.
Add {:tree_sitter_language_pack, "~> 1.0"} to your mix.exs dependencies. See Elixir README for full documentation.
npm install @xberg-io/tree-sitter-language-pack-wasmSee WebAssembly README for full documentation.
dart pub add tree_sitter_language_packSee Dart README for full documentation.
Available on Maven Central as io.xberg.tslp.android:tree-sitter-language-pack-android. See Kotlin Android README for the dependency snippet and current version.
Available via Swift Package Manager. See Swift README for the SwiftPM package URL and current version.
zig fetch --save <release tarball url>See Zig README for full documentation.
Build from source as part of this workspace. See FFI README for full documentation.
cargo install ts-pack-cli# Or install the prebuilt binary via cargo-binstall:
cargo binstall ts-pack-clibrew trust xberg-io/tap
brew install xberg-io/tap/ts-packWindows users can install the same binary through Scoop:
scoop bucket add xberg https://github.com/xberg-io/scoop-bucket
scoop install ts-packOr run without a persistent install (the proxy package fetches the native binary):
npx @xberg-io/ts-pack-cli parse <file>See CLI README for full documentation.
The CLI bundles an MCP server for integration with AI agents. Start it with:
ts-pack mcpThe server runs over stdio by default. For HTTP transport:
ts-pack mcp --transport http --host 127.0.0.1 --port 8011Register with Claude Code:
claude mcp add tree-sitter-language-pack -- ts-pack mcp --transport stdioOr add to your Claude Desktop config at ~/Library/Application Support/Claude/claude_desktop_config.json:
{
"mcpServers": {
"tree-sitter-language-pack": {
"command": "ts-pack",
"args": ["mcp", "--transport", "stdio"]
}
}
}The MCP server exposes 8 tools: parse, process, detect_language, list_languages, info, download, cache_dir, and clean_cache. It also provides resources for the available language catalog and a prompt for code analysis.
The marketplace plugin from xberg-io/tree-sitter-language-pack auto-registers the server — see AI Coding Assistants below to install it instead of manual registration.
For detailed setup, transport options, and tool reference, see the MCP Server guide.
AI Coding Assistants
Install the tree-sitter-language-pack plugin from xberg-io/tree-sitter-language-pack. It ships the tree-sitter-language-pack agent skills (parse and extract code intelligence from 372 languages) — select your runtime below.
The bundle targets Claude Code, Codex, Cursor, Gemini CLI, Kimi, OpenCode, Factory Droid, Hermes, Pi, Agent Plugins and GitHub Copilot CLI. Read the plugin guide for runtime resources, CLI prerequisites and configuration. MCP-capable adapters expose the product's tools; Hermes uses a local stdio bridge and explicitly selected skills. Pi loads skills and prompt templates and requires the product CLI for executable operations.
Install only the public Agent Skills, without a plugin or MCP registration, using the skills CLI:
npx skills add xberg-io/tree-sitter-language-pack --list
npx skills add xberg-io/tree-sitter-language-packChoose the skills and target agents interactively. Installing instructions does not install the product CLI or configure provider credentials.
/plugin marketplace add xberg-io/tree-sitter-language-pack
/plugin install tree-sitter-language-pack@tree-sitter-language-pack
/plugins add https://github.com/xberg-io/tree-sitter-language-pack
Then search for tree-sitter-language-pack and select Install Plugin.
Settings → Plugins → Add from URL → https://github.com/xberg-io/tree-sitter-language-pack, then select tree-sitter-language-pack.
From a checkout of this repository:
gemini extensions install ./pluginThe manifest is inside plugin/. See the Gemini extension reference
for local installation and updates.
droid plugin marketplace add https://github.com/xberg-io/tree-sitter-language-pack
droid plugin install tree-sitter-language-pack@tree-sitter-language-pack
copilot plugin marketplace add https://github.com/xberg-io/tree-sitter-language-pack
copilot plugin install tree-sitter-language-pack@tree-sitter-language-pack
Add the package to opencode.json:
{
"$schema": "https://opencode.ai/config.json",
"plugin": ["@xberg-io/opencode-tree-sitter-language-pack"]
}Documentation
Full guides, the host-native language API, data extraction, the CLI and MCP server, and the complete language list live at docs.tree-sitter-language-pack.xberg.io.
Part of Xberg
- Xberg — document intelligence: text, tables, metadata from 101 formats with optional OCR.
- Xberg Enterprise — managed extraction API with SDKs, dashboards, and observability.
- crawlberg — web crawling and scraping with HTML→Markdown and headless-Chrome fallback.
- html-to-markdown — fast, lossless HTML→Markdown engine.
- liter-llm — universal LLM API client with native bindings for 14 languages and 165 providers.
- tree-sitter-language-pack — tree-sitter grammars and code-intelligence primitives.
- alef — the polyglot binding generator that produces every per-language binding across the 5 polyglot repos.
Contributing
Contributions are welcome! See CONTRIBUTING.md for guidelines.
Join our Discord community for questions and discussion.
License
MIT — see LICENSE for details.
All included tree-sitter grammars are permissively licensed (MIT, Apache-2.0, BSD, ISC, or similar). Copyleft licenses (GPL, AGPL, LGPL, MPL) are not accepted. See CONTRIBUTING.md for grammar inclusion criteria.