14 projects
vLLM
The mission of the Project is to develop an open-source library for fast LLM inference and serving.
Contributors
23,083
Organizations
2,459
Software value
$78M
Ollama
Ollama is an open-source project that allows running, managing and serving large language models (LLMs) locally. It provides a simple API to run models like Llama 2, Mistral, and others on your own hardware, with features for model management, customization, and efficient inference.
Contributors
16,780
Organizations
2,715
Software value
$30M
LiteLLM
LiteLLM is a unified interface for calling AI large language models (LLMs) that provides a consistent API for working with various LLM providers including OpenAI, Anthropic, Cohere, Hugging Face, and others. It simplifies LLM integration by standardizing model inputs/outputs and handling provider-specific requirements.
Contributors
8,612
Organizations
1,587
Software value
$44M
SGLang
SGLang is a structured generation language and runtime system designed for efficient text generation and large language model inference. It provides a Python-based DSL for defining generation workflows with features like speculative decoding and token healing.
Contributors
6,052
Organizations
688
Software value
$31M
Spring AI
An Application Framework for AI Engineering
Contributors
2,945
Organizations
412
Software value
$11M
llama-cpp-python
A Python binding for llama.cpp, enabling integration of the llama.cpp library for running large language models locally. It provides a Python interface to load and run various LLM models compatible with llama.cpp, supporting both CPU and GPU acceleration.
Contributors
2,622
Organizations
424
Software value
$822K
LocalAI
LocalAI is an open-source project that provides a self-hosted, local alternative to OpenAI's APIs. It allows running LLMs (Large Language Models), text generation, embeddings, and image generation locally without requiring cloud services, supporting multiple model formats and hardware acceleration.
Contributors
1,674
Organizations
322
Software value
$14M
SillyTavern
A web-based chat interface for interacting with large language models and AI assistants, featuring character creation, conversation management, and customizable settings. It provides a frontend for various AI backends and models.
Contributors
1,638
Organizations
115
Software value
$6.8M
Unstructured
Open source libraries and APIs to build custom preprocessing pipelines for labeling, training, or production machine learning pipelines.
Contributors
1,323
Organizations
221
Software value
$38M
Quivr
Opiniated RAG for integrating GenAI in your apps 🧠 Focus on your product rather than the RAG. Easy integration in existing products with customisation! Any LLM: GPT4, Groq, Llama. Any Vectorstore: PGVector, Faiss. Any Files. Anyway you want.
Contributors
1,279
Organizations
148
Software value
$512K
Quarkus LangChain4j
Quarkus LangChain4j is an integration project that enables the use of LangChain4j, a Java framework for building applications with large language models (LLMs), within Quarkus applications. It provides Quarkus extensions and configurations for working with AI/ML models and language processing capabilities.
Contributors
317
Organizations
67
Software value
$6.8M
Instill Core
Instill Core is an open-source MLOps platform that provides infrastructure for building and deploying AI applications. It enables integration of various AI models and data sources through a unified API and pipeline system.
Contributors
136
Organizations
26
Software value
$2.1M
Agno
Agno is a lightweight library for building multi-modal Agents
This project hasn't been onboarded to LFX Insights.