43 projects
LangChain
LangChain is a framework for developing applications powered by language models, offering tools and abstractions for building LLM-powered applications. It provides components for working with language models, document processing, memory/state management, and chains/agents for complex reasoning.
Contributors
23,182
Organizations
2,754
Software value
$9.6M
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
16,681
Organizations
2,700
Software value
$30M
Dify
Dify is an open-source LLM application development platform that enables developers to create, deploy and manage AI applications with visual tools. It provides features for prompt engineering, API integration, and conversation management to build production-ready AI applications.
Contributors
11,857
Organizations
855
Software value
$38M
llama cpp
A port of Facebook's LLaMA model in C/C++, focusing on efficient inference and deployment of large language models on consumer hardware. The project provides optimized implementations for running LLaMA models with minimal dependencies and memory requirements.
Contributors
11,848
Organizations
1,789
Software value
$29M
Open WebUI
Open WebUI is a web interface for interacting with large language models (LLMs), providing a user-friendly chat interface and management system for AI models. It supports various LLM backends and offers features like conversation history, model switching, and system prompts management.
Contributors
9,224
Organizations
1,299
Software value
$13M
LLamaIndex
LlamaIndex is an open-source data framework for building LLM applications, providing tools to connect custom data sources to large language models, with features for data ingestion, structuring, retrieval, and natural language querying.
Contributors
8,510
Organizations
1,086
Software value
$62M
AutoGPT
AutoGPT is an experimental open-source application that demonstrates autonomous AI agents. It implements GPT-4 to create AI agents that can independently perform tasks and achieve specified goals through chain-of-thought reasoning and task decomposition.
Contributors
7,408
Organizations
837
Software value
$38M
Continue
Continue is an open-source AI coding assistant and IDE extension that helps developers write, understand, and improve code through natural language interactions. It features context-aware code completion, automated debugging, and code explanations while keeping all code processing local for privacy.
Contributors
6,413
Organizations
931
Software value
$15M
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
5,974
Organizations
685
Software value
$30M
RAGFlow
RAGFlow is an open-source RAG (Retrieval-Augmented Generation) engine based on deep document understanding.
Contributors
5,551
Organizations
293
Software value
$14M
Vercel AI SDK
The Vercel AI SDK is a library that helps developers build AI-powered streaming text and chat UIs using React and JavaScript. It provides components and utilities for integrating large language models and AI services into web applications with features like real-time streaming responses and built-in React hooks.
Contributors
5,069
Organizations
1,249
Software value
$17M
LangChain-Chatchat
Langchain-Chatchat（原Langchain-ChatGLM）基于 Langchain 与 ChatGLM, Qwen 与 Llama 等语言模型的 RAG 与 Agent 应用 | Langchain-Chatchat (formerly langchain-ChatGLM), local knowledge based LLM (like ChatGLM, Qwen and Llama) RAG and Agent app with langchain
Contributors
4,623
Organizations
202
Software value
$1.2M
Lobe Chat
Lobe Chat is an open-source chatbot framework and interface that provides an AI chat assistant experience. It features a modern UI, plugin support, multi-modal interactions, and various AI model integrations.
Contributors
4,276
Organizations
468
Software value
$48M
Langflow
Langflow is an open-source UI tool for building and prototyping LangChain pipelines using a visual drag-and-drop interface. It allows users to experiment with LLMs, prompt templates, and chains without writing code, making it easier to create and test language model workflows.
Contributors
4,196
Organizations
425
Software value
$23M
Llama Models
A collection of large language models (LLMs) developed by Meta AI, including the Llama family of models. These models are designed for natural language processing tasks and are made available for research and commercial use under specific licensing terms.
Contributors
4,004
Organizations
669
Software value
$425K
Unsloth
Unsloth is an open-source project focused on optimizing and accelerating Large Language Models (LLMs) through efficient fine-tuning techniques. It provides tools and methods for faster LLM training and inference while reducing memory usage and computational requirements.
Contributors
3,838
Organizations
505
Software value
$1.5M
ChatGPT-on-WeChat
A WeChat bot that integrates ChatGPT functionality, allowing users to interact with ChatGPT through the WeChat messaging platform. The project provides a bridge between OpenAI's ChatGPT API and WeChat's messaging interface.
Contributors
3,361
Organizations
115
Software value
$469K
FastChat
FastChat is an open-source platform for training, serving, and evaluating large language models (LLMs). It provides tools for training and deploying LLM-based chatbots, including implementations of models like Vicuna and support for various model architectures.
Contributors
2,853
Organizations
425
Software value
$1M
LangGraph
LangGraph is a library for building stateful, multi-agent applications with LangChain. It provides tools and abstractions for creating complex workflows and interactions between language models and other components, with a focus on directed graphs and state management.
Contributors
2,350
Organizations
326
Software value
$3.6M
PEFT
🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.
Contributors
2,326
Organizations
407
Software value
$9.1M
DSPy
DSPy: The framework for programming—not prompting—language models
Contributors
2,302
Organizations
423
Software value
$2.4M
Haystack
AI orchestration framework to build customizable, production-ready LLM applications. Connect components (models, vector DBs, file converters) to pipelines or agents that can interact with your data. With advanced retrieval methods, it's best suited for building RAG, question answering, semantic search or conversational agent chatbots.
Contributors
2,269
Organizations
315
Software value
$18M
Language Model Evaluation Harness
A framework for evaluating language models through automated testing across diverse tasks and benchmarks. It provides standardized evaluation metrics and supports multiple model architectures and datasets.
Contributors
2,165
Organizations
385
Software value
$8M
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
1,672
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
1,633
Organizations
115
Software value
$6.8M
Jan
Jan is an open source alternative to ChatGPT that runs 100% offline on your computer
Contributors
1,630
Organizations
233
Software value
$4.4M
ChatGPT Next Web
A web-based ChatGPT user interface that provides a clean, customizable way to interact with OpenAI's language models through a browser. It offers features like conversation history, prompt templates, and API key management.
Contributors
1,562
Organizations
169
Software value
$1.6M
GPT Researcher
GPT Researcher is an autonomous research agent that conducts comprehensive online research on any given topic by generating and following research questions, collecting relevant information, and synthesizing findings into a structured report. It leverages large language models to automate the research process while maintaining academic rigor.
Contributors
1,146
Organizations
134
Software value
$6.3M
DocsGPT
Chatbot for documentation, that allows you to chat with your data. Privately deployable, provides AI knowledge sharing and integrates knowledge into your AI workflow
Contributors
1,001
Organizations
138
Software value
$2.8M
MaxKB
💬 Ready-to-use & flexible RAG Chatbot, supporting mainstream large language models (LLMs) such as DeepSeek-R1, Llama 3.3, Qwen2, OpenAI, and more.
Contributors
950
Organizations
72
Software value
$5.9M
h2oGPT
h2oGPT is an open-source project focused on creating a privacy-aware, customizable, and document-focused large language model (LLM) framework. It allows users to chat with their documents and data using various LLM backends while maintaining data privacy and supporting both CPU and GPU deployments.
Contributors
669
Organizations
75
Software value
$7.7M
InstructLab
InstructLab Core package. Use this to chat with a model and execute the InstructLab workflow to train a model using custom taxonomy data.
Contributors
617
Organizations
57
Software value
$2M
FlagAI
The mission of the Project is to develop a fast, easy-to-use and extensible toolkit for large-scale AI modeling, with the goal of supporting training, fine-tuning, and deployment of large-scale models on various downstream tasks with multi-modality.
Contributors
364
Organizations
32
Software value
$55M
HolmesGPT
HolmesGPT is an AI-powered detective assistant that aims to help solve mysteries and puzzles through natural language interaction and deductive reasoning
Contributors
169
Organizations
54
Software value
$19M
AGENTS.md
A project focused on AI agents and their capabilities, likely containing documentation or guidelines about agent-based AI systems
Contributors
165
Organizations
70
Software value
$53K
GenAIScript
GenAIScript is a programming language and runtime environment designed for building generative AI applications, developed by Microsoft. It provides a structured way to create and manage AI-powered applications with a focus on generative capabilities.
Contributors
128
Organizations
32
Software value
$3.8M
FlashInfer
FlashInfer: Kernel Library for LLM Serving
This project hasn't been onboarded to LFX Insights.
Llama Cookbook
Welcome to the Llama Cookbook! This is your go to guide for Building with Llama: Getting started with Inference, Fine-Tuning, RAG. We also show you how to solve end to end problems using Llama model family and using them on various provider services
This project hasn't been onboarded to LFX Insights.
Llamafile
Distribute and run LLMs with a single file.
This project hasn't been onboarded to LFX Insights.
NeMo
A scalable generative AI framework built for researchers and developers working on Large Language Models, Multimodal, and Speech AI (Automatic Speech Recognition and Text-to-Speech)
This project hasn't been onboarded to LFX Insights.
The Multi-Agent Framework
🌟 The Multi-Agent Framework: First AI Software Company, Towards Natural Language Programming
This project hasn't been onboarded to LFX Insights.