LLM Context

What is LLM Context about?

LLM Context enables developers to quickly share selected portions of a codebase or document collection with an LLM chat, either by copying the generated context to the clipboard or by serving it through the Model Context Protocol (MCP). It automatically respects .gitignore rules, provides rule‑based profiles for different workflows (e.g., code review, documentation), and can generate high‑level outlines of source files.

How to use LLM Context?

1. Install – the tool is distributed as a Python package and can be installed with the uv tool:

   uv tool install "llm-context>=0.3.0"
   

2. Initialize a project (run once): lc-init.
3. Select files you want to share: lc-sel-files (or lc-sel-outlines for outline generation).
4. Generate context and copy it to the clipboard: lc-context. Add -p to include prompt instructions, -u for user notes, or -f <file> to write to a file.
5. Interact with an LLM – paste the clipboard content into a chat, or configure Claude Desktop (or any MCP‑compatible client) to call the MCP server (see Server Configuration below).
6. When the LLM requests additional files, run lc-clip-files with the file list to fetch and paste the contents back to the model.

Key features of LLM Context

• Smart file selection using .gitignore patterns.
• Rule‑based profiles (lc-set-rule) for switching between tasks such as code review, documentation generation, or custom prompts.
• CLI workflow with a small set of intuitive commands (lc-init, lc-sel-files, lc-context, lc-clip-files, etc.).
• MCP server that can be invoked directly from Claude Desktop or other MCP clients.
• Code outlining (lc-outlines) and implementation extraction (lc-clip-implementations).
• Configurable templates for prompts and system messages.
• Cross‑language support (leverages tree‑sitter queries from Aider Chat).

Use cases of LLM Context

• Rapid code reviews – generate a concise context dump and feed it to an LLM for feedback.
• Documentation assistance – provide the LLM with selected source files and let it produce documentation snippets.
• Debugging sessions – share only the files relevant to an error without exposing the whole repository.
• Knowledge transfer – onboard new team members by allowing an LLM to answer questions about the project's structure using generated outlines.
• Custom GPT integrations – paste the generated context into the knowledge section of a Custom GPT for persistent project awareness.

FAQ

Q: Do I need to version‑control the .llm-context folder? A: Yes. Configuration files prefixed with lc- may be overwritten on updates, so keeping them in VCS prevents loss.

Q: Can I use LLM Context with non‑Claude models? A: Absolutely. The CLI/clipboard workflow works with any chat interface; the MCP server can be called from any client that implements the Model Context Protocol.

Q: How does the tool handle large projects? A: It limits the generated context to fit within an LLM’s context window. Smart selection and rule‑based filtering keep the payload manageable. Large‑project support is under active development.

Q: Is there a way to automatically include only changed files? A: Yes. Use lc-changed to list files modified since the last context generation and feed them to lc-context.

Q: What languages are supported for outline generation? A: The tool relies on tree‑sitter queries; most popular languages are covered, though C/C++ implementation extraction is not currently supported.

Q: How do I configure the MCP server for Claude Desktop? A: Add the following JSON snippet to claude_desktop_config.json (see Server Configuration below).

---

Server Configuration (MCP server entry for Claude Desktop):

{
  "mcpServers": {
    "CyberChitta": {
      "command": "uvx",
      "args": ["--from", "llm-context", "lc-mcp"]
    }
  }
}

LLM Context

LLM Context is a tool that helps developers quickly inject relevant content from code/text projects into Large Language Model chat interfaces. It leverages .gitignore patterns for smart file selection and provides both a streamlined clipboard workflow using the command line and direct LLM integration through the Model Context Protocol (MCP).

Note: This project was developed in collaboration with several Claude Sonnets - 3.5, 3.6 and 3.7 (and more recently Grok-3 as well), using LLM Context itself to share code during development. All code in the repository is human-curated (by me 😇, @restlessronin).

Why LLM Context?

For an in-depth exploration of the reasoning behind LLM Context and its approach to AI-assisted development, check out our article: LLM Context: Harnessing Vanilla AI Chats for Development

To see LLM Context in action with real-world examples and workflows, read: Full Context Magic - When AI Finally Understands Your Entire Project

Current Usage Patterns

• Direct LLM Integration: Native integration with Claude Desktop via MCP protocol
• Chat Interface Support: Works with any LLM chat interface via CLI/clipboard
  • Optimized for interfaces with persistent context like Claude Projects and Custom GPTs
  • Works equally well with standard chat interfaces
• Project Types: Suitable for code repositories and collections of text/markdown/html documents
• Project Size: Optimized for projects that fit within an LLM's context window. Large project support is in development

Installation

Install LLM Context using uv:

uv tool install "llm-context>=0.3.0"

To upgrade to the latest version:

uv tool upgrade llm-context

Warning: LLM Context is under active development. Updates may overwrite configuration files prefixed with lc-. We recommend all configuration files be version controlled for this reason.

Quickstart

MCP with Claude Desktop

Add to 'claude_desktop_config.json':

{
  "mcpServers": {
    "CyberChitta": {
      "command": "uvx",
      "args": ["--from", "llm-context", "lc-mcp"]
    }
  }
}

Once configured, you can start working with your project in two simple ways:

1. Say: "I would like to work with my project" Claude will ask you for the project root path.

2. Or directly specify: "I would like to work with my project /path/to/your/project" Claude will automatically load the project context.

Preferred Workflow: Combining Project UI with MCP

For optimal results, combine initial context through Claude's Project Knowledge UI with dynamic code access via MCP. This provides both comprehensive understanding and access to latest changes. See Full Context Magic for details and examples.

CLI Quick Start and Typical Workflow

1. Navigate to your project's root directory
2. Initialize repository: lc-init (only needed once)
3. Select files: lc-sel-files
4. (Optional) Review selected files in .llm-context/curr_ctx.yaml
5. Generate context: lc-context (with optional flags: -p for prompt, -u for user notes)
6. Use with your preferred interface:

• Project Knowledge (Claude Pro): Paste into knowledge section
• GPT Knowledge (Custom GPTs): Paste into knowledge section
• Regular chats: Use lc-context -p to include instructions

7. When the LLM requests additional files:
   • Copy the file list from the LLM
   • Run lc-clip-files
   • Paste the contents back to the LLM

Core Commands

• lc-init: Initialize project configuration
• lc-set-rule <n>: Switch rules (system rules are prefixed with "lc-")
• lc-sel-files: Select files for inclusion
• lc-sel-outlines: Select files for outline generation
• lc-context [-p] [-u] [-f FILE]: Generate and copy context
  • -p: Include prompt instructions
  • -u: Include user notes
  • -f FILE: Write to output file
• lc-prompt: Generate project instructions for LLMs
• lc-clip-files: Process LLM file requests
• lc-changed: List files modified since last context generation
• lc-outlines: Generate outlines for code files
• lc-clip-implementations: Extract code implementations requested by LLMs (doesn't support C/C++)

Features & Advanced Usage

LLM Context provides advanced features for customizing how project content is captured and presented:

• Smart file selection using .gitignore patterns
• Multiple rule-based profiles for different use cases
  • System rules (prefixed with "lc-") provide default functionality
  • User-defined rules can be created independently or extend existing rules
• Code Navigation Features:
  1. Smart Code Outlines: Allows LLMs to view the high-level structure of your codebase with automatically generated outlines highlighting important definitions
  2. Definition Implementation Extraction: Paste full implementations of specific definitions that are requested by LLMs after they review the code outlines, using the lc-clip-implementations command
• Customizable templates and prompts

See our User Guide for detailed documentation of these features.

Similar Tools

Check out our comprehensive list of alternatives - the sheer number of tools tackling this problem demonstrates its importance to the developer community.

Acknowledgments

LLM Context evolves from a lineage of AI-assisted development tools:

• This project succeeds LLM Code Highlighter, a TypeScript library I developed for IDE integration.
• The concept originated from my work on RubberDuck and continued with later contributions to Continue.
• LLM Code Highlighter was heavily inspired by Aider Chat. I worked with GPT-4 to translate several Aider Chat Python modules into TypeScript, maintaining functionality while restructuring the code.
• This project uses tree-sitter tag query files from Aider Chat.
• LLM Context exemplifies the power of AI-assisted development, transitioning from Python to TypeScript and back to Python with the help of GPT-4 and Claude-3.5-Sonnet.

I am grateful for the open-source community's innovations and the AI assistance that have shaped this project's evolution.

I am grateful for the help of Claude-3.5-Sonnet in the development of this project.

License

This project is licensed under the Apache License, Version 2.0. See the LICENSE file for details.