MCPcopy Index your code
hub / github.com/llm-workflow-engine/llm-workflow-engine

github.com/llm-workflow-engine/llm-workflow-engine @v0.22.23 sqlite

repository ↗ · DeepWiki ↗ · release v0.22.23 ↗
960 symbols 3,612 edges 88 files 228 documented · 24%
README

Test status CodeQL

lwe-logo-small

LLM Workflow Engine

LLM Workflow Engine (LWE) is a Power CLI and Workflow manager for LLMs.

Read the documentation

WATCH INTRO VIDEO

Welcome!

What would you like to do?

What happend to the original ChatGPT Wrapper project?

See CHATGPT_WRAPPER.md

ChatGPT Wrapper was an amazing tool for its time, thank you to its original creator mmabrouk for all your hard work, it lives on in a new form :)

Highlights

🤖 LWE lets you use the powerful ChatGPT/GPT4 bot from the command line.

💬 Runs in Shell. You can call and interact with ChatGPT/GPT4 in the terminal.

💻 Supports official ChatGPT API. Make API calls directly to the OpenAI ChatGPT endpoint (all supported models accessible by your OpenAI account)

🔌 Simple plugin architecture. Extend LWE with custom functionality

🗣 Supports multiple LLM providers. Provider plugins allow interacting with other LLMs (GPT-3, Cohere, Huggingface, etc.)

🔄Build workflows. Easily integrate calls to an LLM into larger workflows via Ansible Playbooks

🔧 Tool use. (for supported providers)

🐳 Docker image. LWE is also available as a docker image. (experimental)

🐍Python API. LWE also has a Python library that lets you use ChatGPT/GPT4 in your Python scripts.

Projects built with the original ChatGPT Wrapper

Contributing

We welcome contributions to LWE! If you have an idea for a new feature or have found a bug, please open an issue on the GitHub repository.

License

This project is licensed under the MIT License - see the LICENSE file for details.

Acknowledgments

  • The original ChatGPT Wrapper project (which LWE grew from) was created and maintained by mmabrouk
  • The original ChatGPT Wrapper project is a modification from Taranjeet code which is a modification of Daniel Gross code.

Star History

Star History Chart

Core symbols most depended-on inside this repo

make_api_request
called by 107
tests/base.py
debug
called by 99
lwe/core/config.py
get
called by 87
lwe/core/config.py
set
called by 44
lwe/core/config.py
get_conversation
called by 24
tests/base.py
_handle_error
called by 22
lwe/backends/api/orm.py
set_request_llm
called by 21
lwe/backends/api/request.py
ask
called by 20
tests/base.py

Shape

Method 576
Function 321
Class 56
Route 7

Languages

Python100%

Modules by API surface

tests/unit/test_request.py93 symbols
lwe/core/repl.py85 symbols
tests/unit/test_util.py53 symbols
lwe/backends/api/repl.py53 symbols
lwe/backends/api/backend.py51 symbols
lwe/core/provider.py45 symbols
lwe/core/util.py42 symbols
lwe/backends/api/request.py37 symbols
lwe/backends/api/orm.py28 symbols
tests/unit/test_template_manager.py23 symbols
tests/system/test_api_backend.py23 symbols
lwe/core/template_manager.py23 symbols

Dependencies from manifests, versioned

Jinja2
PyYAML
Sphinx7.3.7 · 1×
alabaster0.7.16 · 1×
ansible8.0 · 1×
ansible-core2.15 · 1×
babel2.17.0 · 1×
beautifulsoup4
certifi2025.1.31 · 1×
charset-normalizer3.4.1 · 1×
docutils0.20.1 · 1×

For agents

$ claude mcp add llm-workflow-engine \
  -- python -m otcore.mcp_server <graph>

⬇ download graph artifact