llmware and llm-kelt
These are complements: llmware provides the unified RAG and fine-tuning framework, while llm-kelt specializes in the prerequisite context management (facts storage and feedback collection) that feeds into llmware's fine-tuning pipeline.
About llmware
llmware-ai/llmware
Unified framework for building enterprise RAG pipelines with small, specialized models
Brings together prepackaged quantized models (50+ specialized for RAG tasks like extraction, classification, and summarization) and a modular RAG pipeline with multi-format document parsing, vector embedding with multiple backends (Chromadb, Milvus), and hybrid query capabilities (text, semantic, metadata filters). The unified ModelCatalog interface abstracts over diverse inference engines—GGUF, OpenVINO, ONNX-Runtime, HuggingFace—enabling the same code to run on-device across CPUs, GPUs, and NPUs on Windows, Mac, and Linux. Prompt objects orchestrate end-to-end knowledge retrieval and generation, automatically batching sources to fit model context windows while tracking provenance for fact-checking against source materials.
About llm-kelt
llm-works/llm-kelt
Framework for collecting and managing LLM context: facts storage, feedback collection, RAG retrieval, and LoRA fine-tuning
Related comparisons
Scores updated daily from GitHub, PyPI, and npm data. How scores work