Skip to main content

Turn your entire codebase into a single prompt-ready text file.

Project description

LLM Context Packer (Repomix)

"Stop manually opening 15 files and copy-pasting them one by one. Repomix packs your entire codebase into a single AI-ready prompt in <1 second."

Turn your entire codebase into a single prompt-ready text file.

🚀 Why?

When working with LLMs (ChatGPT, Claude, Gemini), context is everything. You often need to paste multiple files to get a good refactor or answer. Manually copying file content, adding filenames, and formatting is a pain.

LLM Context Packer does it for you:

  1. Traverses your project.
  2. Respects .gitignore (no node_modules, .env, or secrets).
  3. Formats everything into an LLM-friendly structure.
  4. Copies the result strictly to your clipboard.
  5. Counts the tokens so you know if you fit the context window.

📦 Installation

# Clone the repository
git clone
cd llm-context-packer

# Install locally
pip install .

🛠 Usage

You can use either llm-context-packer or the shorter alias repomix.

Basic Usage

Run in your project root. It automatically copies to clipboard.

repomix .

Options

# Don't copy to clipboard, just print to stdout
repomix . --no-copy

# Write to a file instead of clipboard
repomix . --output context.txt

# Verbose mode (see what files are being packed)
repomix . --verbose

📝 Output Format

The tool generates a clean Markdown format that LLMs understand perfectly:

🛡 Security

  • Strictly follows .gitignore: If you ignore it in git, it won't be packed.
  • Hidden files ignored: Skips .git directory automatically.

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

llm_context_packer-0.1.0.tar.gz (6.2 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

llm_context_packer-0.1.0-py3-none-any.whl (6.4 kB view details)

Uploaded Python 3

File details

Details for the file llm_context_packer-0.1.0.tar.gz.

File metadata

  • Download URL: llm_context_packer-0.1.0.tar.gz
  • Upload date:
  • Size: 6.2 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.10.11

File hashes

Hashes for llm_context_packer-0.1.0.tar.gz
Algorithm Hash digest
SHA256 f429b2983959357c1fc5f18c3e645f1f87e96c2712582c730ee413a02fe04062
MD5 0985bb2a987a406dd323b201cf475a45
BLAKE2b-256 a72ff4414cbd70310c40412876d052d0339d5eea825fe2aebedea57b5663626d

See more details on using hashes here.

File details

Details for the file llm_context_packer-0.1.0-py3-none-any.whl.

File metadata

File hashes

Hashes for llm_context_packer-0.1.0-py3-none-any.whl
Algorithm Hash digest
SHA256 5a0cd9a2e7b5e8576afcedea2c1bd8755f90afea8b64671ad9863ecb810f480e
MD5 a8a845ed530343f97286d4e1f87aa42c
BLAKE2b-256 8f5d596c634077ffdd847a2aa4b7b8a2c1d691406124bf86fa95879ea8ef2253

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page