llm-engineer-toolkit
A curated list of 120+ LLM libraries category wise.
What is llm-engineer-toolkit?
A curated list of 120+ LLM libraries category wise.
Overview of llm-engineer-toolkit
What it is
LLM Engineer Toolkit is a curated list of over 120 LLM libraries organized by category. The repository serves as a reference for developers and researchers working with large language models.
Key features
- Curated collection of 120+ LLM libraries grouped into categories such as training, fine-tuning, application development, RAG, agents, evaluation, and more.
- Includes libraries for LLM training and fine-tuning (e.g., unsloth, PEFT, TRL, Transformers, Axolotl, LitGPT, Llama-Factory, DeepSpeed, torchtune, etc.).
- Covers LLM application development frameworks (LangChain, Llama Index, HayStack, Prompt flow, Griptape, Weave, Llama Stack) and data preparation tools (Data Prep Kit).
- Provides multi-API access libraries (LiteLLM, AI Gateway, Bifrost), routers (OpenRoutiQ, RouteLLM), and memory solutions.
- Also lists libraries for LLM inference, serving, data extraction, data generation, agents, evaluation, monitoring, prompts, structured outputs, safety and security, and embedding models.
- References related repositories for LLM interview questions, prompt engineering techniques, and survey papers.
Use cases
- Discovering and selecting appropriate LLM libraries for tasks such as training, fine-tuning, application development, RAG, agents, evaluation, monitoring, and safety.
- Finding tools for data preparation, multi-provider API access, routing, and memory management in LLM applications.
- Exploring libraries for structured outputs, embedding models, and prompt engineering.
Getting started
See the repository README for details.
License and pricing
Apache-2.0 license. Open source.
Based on the project's public README and repository metadata.