Skip to main content

A comprehensive combination of all agentic CLI at one place with 🦜🔗!

Project description

LangCode Logo

LangCode

The only CLI you'll ever need!

LangCode Demo

PyPI version PyPI Downloads Python Versions License Docker Build Docker Pulls Code style: black

LangCode is the "one-key" developer CLI that unifies Gemini, Anthropic Claude, OpenAI, and Ollama with ReAct & Deep modesΓÇöfully inline, right in your terminal.


Get Started

Installation:

pip install langchain-code

Launch the Interactive Launcher:

Just type langcode in your terminal and hit Enter. This opens a user-friendly interactive menu where you can easily configure your session and access various functionalities without needing to remember specific command-line arguments. See the image shown above.


Interactive Mode

The interactive mode serves as the central hub for all your coding tasks. It allows you to:

  • Choose a Command: Select what you want to do: chat, feature, fix, or analyze.
  • Configure the Engine: Pick between react (fast and efficient) and deep (for complex tasks).
  • Enable Smart Routing: Let LangCode automatically select the best LLM for each task.
  • Set the Priority: Optimize for cost, speed, or quality when using smart routing.
  • Manage Autopilot: Enable fully autonomous mode for the Deep Agent (use with caution!).
  • Toggle Apply Mode: Allow LangCode to automatically write changes to your file system.
  • Select an LLM: Explicitly choose between Anthropic and Google Gemini, or let LangCode decide.
  • Specify the Project Directory: Tell LangCode where your codebase is located.
  • Edit Environment Variables: Quickly add or modify API keys and other settings in your .env file.
  • Customize Instructions: Open the .langcode/langcode.md file to add project-specific guidelines.
  • Configure MCP Servers: Set up Model Context Protocol (MCP) servers for advanced tool integration.
  • Edit Language Code: Modify the core language code directly from the main window.
  • Specify MCP Servers: Configure Model Context Protocol (MCP) servers for advanced tool integration.
  • Define a Test Command: Specify a command to run after making changes (e.g., pytest -q).
  • Access Help: Press h to toggle help and q or Esc to quit.

Core Commands

While the interactive launcher is the recommended way to use LangCode, you can also use the following commands directly from the terminal:

  • langcode chat: Starts an interactive chat session.
  • langcode feature: Implements a new feature.
  • langcode fix: Fixes a bug.
  • langcode analyze: Analyzes the codebase.
  • langcode instr: Opens the project instructions file.

Install & Run

pip install langchain-code
langcode

Contributing

Issues and PRs are welcome. Please open an issue to discuss substantial changes before submitting a PR. See CONTRIBUTING.md for guidelines.


License

MIT. See LICENSE.


Acknowledgments

LangCode draws inspiration from the design and developer experience of Google's Gemini CLI and Anthropic's Claude Code, unified into a single, streamlined tool.

Project details


Download files

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

Source Distributions

No source distribution files available for this release.See tutorial on generating distribution archives.

Built Distribution

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

langchain_code-0.1.6-py3-none-any.whl (97.7 kB view details)

Uploaded Python 3

File details

Details for the file langchain_code-0.1.6-py3-none-any.whl.

File metadata

  • Download URL: langchain_code-0.1.6-py3-none-any.whl
  • Upload date:
  • Size: 97.7 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.11.5

File hashes

Hashes for langchain_code-0.1.6-py3-none-any.whl
Algorithm Hash digest
SHA256 c9d3d38053168a8cec88807903a2b9dba584168ca5042767ee2d1bdf5ca76393
MD5 2e33fc15a711a7857f2bddf81e4051fd
BLAKE2b-256 936e065354d2890333e45ef401a0ad63d9dedf726d8c01d373dfe75a2af8135f

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