whereismyai
LLM Workflow Engine
LLM Workflow Engine is a command-line interface and workflow manager for interacting with large language models.
LLM Workflow Engine is a power CLI and workflow manager designed for interacting with large language models from the terminal. It runs in the shell and supports the official ChatGPT API, GPT-4, GPT-3, Cohere, Huggingface, and other providers through a plugin architecture. Users can build workflows by integrating LLM calls into Ansible Playbooks and utilize a Python API for scripts. The tool also features support for custom plugins and tool use for compatible providers. It is available as an open-source project under the MIT License and includes a Docker image option.
LLM Workflow Engine at a glance
Key features
- Command line interface for ChatGPT and GPT-4
- Official ChatGPT API integration
- Plugin architecture for custom functionality
- Multiple LLM provider support including Cohere and Huggingface
- Workflow integration via Ansible Playbooks
- Tool use for supported providers
- Python API for scripts
Use it for
- Run ChatGPT and GPT-4 from the command line
- Integrate LLM calls into Ansible Playbooks
- Build custom functionality with plugins
- Use LLMs within Python scripts
Alternatives to LLM Workflow Engine
- LLM CLI — It enables command-line interaction with remote APIs and local machine models.
- Mesh LLM — Run large local models across multiple machines through one OpenAI-compatible endpoint.
- llmware — Build private, local RAG pipelines with 300+ prepackaged models and integrated document parsing.
- LiteLLM — One OpenAI-format API for 100+ LLM providers
- WebLLM — Runs high-performance language models directly inside web browsers.
- llm-d — Deploys production-grade LLM serving on existing hardware clusters.
- LangChain4j — Integrates LLMs and vector stores directly into Java applications.
- llmspy.org — Self-host access to 530+ AI models across 24 providers with built-in tools.
- vLLM — Maximizes throughput with PagedAttention and continuous batching.
- LightLLM — It delivers high-speed inference and serving performance for large language models.
- MLC LLM — Enables native optimization and deployment of AI models across platforms.
- Manifest LLM Gateway — It autofixes bad requests and routes calls across multiple providers with zero downtime.
All LLM Workflow Engine alternatives