Open Source Linux Large Language Models (LLM) - Page 5
Sort By:
Large Language Models (LLM) for Linux
View 99 business solutions-
Rezku Point of SaleRezku is an all-inclusive ordering platform and management solution for all types of restaurant and bar concepts. You can now get a fully custom branded downloadable smartphone ordering app for your restaurant exclusively from Rezku.
-
Online Project Management Platform - ZohoZoho Projects is a cloud-based project management solution that helps teams plan, track, collaborate, and achieve project goals.
-
1
LangGraph.js
Framework to build resilient language agents as graphs
LangGraphJS is a JavaScript framework designed to build stateful AI applications and autonomous agents using graph-based execution models. Developed as part of the LangChain ecosystem, the framework allows developers to represent complex AI workflows as graphs where nodes represent tasks and edges define the flow of execution. This structure makes it easier to implement long-running agents, multi-step reasoning pipelines, and workflows that require persistent state. LangGraphJS supports advanced capabilities such as branching logic, loops, and conditional execution, enabling developers to build sophisticated AI systems that can adapt to dynamic conditions. The framework integrates seamlessly with language models, tools, and external APIs, allowing agents to retrieve information and perform actions across different systems. Developers can also build applications that maintain conversation history and state across multiple interactions. -
2
MiniMax-M2.5
State of the art LLM and coding model
MiniMax-M2.5 is a state-of-the-art foundation model extensively trained with reinforcement learning across hundreds of thousands of real-world environments. It delivers leading performance in coding, agentic tool use, search, and complex office workflows, achieving top benchmark scores such as 80.2% on SWE-Bench Verified and 76.3% on BrowseComp. Designed to reason efficiently and decompose tasks like an experienced architect, M2.5 plans features, structure, and system design before generating code. The model supports full-stack development across web, mobile, and desktop platforms, covering the entire lifecycle from system design to testing and code review. With native serving speeds of up to 100 tokens per second, it completes complex agentic tasks significantly faster than previous versions while maintaining high token efficiency. M2.5 is built to be highly cost-effective, enabling continuous deployment of powerful AI agents at a fraction of the cost of other frontier models. -
3
MusicGPT
Generate music based on natural language prompts using LLMs
MusicGPT is an open-source application designed to generate music from natural language prompts using locally executed artificial intelligence models. The software allows users to run advanced music generation systems directly on their own devices without requiring heavy dependencies such as Python or full machine learning frameworks. Instead, it provides a lightweight environment capable of executing music generation models locally on CPUs or GPUs while maintaining strong performance across operating systems including Windows, macOS, and Linux. Users can describe a musical style, mood, or instrumentation using text prompts, and the system produces original audio samples based on those instructions. The application currently integrates with models such as MusicGen and is designed to support additional models transparently in the future. In addition to a command-line interface, the project includes a web-based interface that enables conversational interaction with the AI model. -
4
Nanocoder
A beautiful local-first coding agent running in your terminal
Nanocoder is an open-source, local-first coding assistant that runs in the command line and allows developers to use AI models to assist with programming tasks directly from their terminal environment. The tool is designed as a privacy-focused alternative to proprietary AI coding assistants, allowing users to run local models or connect to external APIs while keeping full control over their data and development workflow. Built with TypeScript and distributed as a CLI application, nanocoder enables developers to interact with AI agents that can read files, modify code, execute commands, and assist with debugging tasks. The platform supports multiple AI providers through OpenAI-compatible APIs and can also integrate with local model runtimes such as Ollama or LM Studio. Its architecture emphasizes extensibility through custom commands and integration with Model Context Protocol servers that allow the AI agent to access additional tools. -
Fax.Cloud delivers encrypted, point-to-point faxing with guaranteed delivery and built-in audit trailsUnlike email or file-sharing tools, Fax.Cloud doesn’t bounce around the internet, exposed and vulnerable. It’s direct, encrypted, and verified. You get delivery confirmation, audit trails, and peace of mind, without the spam filters, metadata leaks, or cyber threats.
-
5
OllamaSharp
The easiest way to use Ollama in .NET
OllamaSharp is an open-source .NET library that provides strongly typed bindings for interacting with the Ollama API, making it easier for developers to integrate local large language models into C# and .NET applications. The project acts as a wrapper around the Ollama API, exposing all endpoints through asynchronous methods that allow developers to perform tasks such as generating text, creating embeddings, and managing models. It supports both local and remote Ollama instances, enabling developers to run AI models on their own hardware or connect to remote model servers. The library is designed to simplify integration by allowing developers to interact with AI models using just a few lines of code while still supporting advanced functionality. OllamaSharp also includes real-time streaming capabilities that allow applications to display generated responses incrementally as they are produced. -
6
OmniBox
Collect, organize, use, and share, all in OmniBox
Omnibox (mirror) is a SourceForge mirror of the Omnibox open-source project, which provides a software interface designed to simplify interaction with multiple tools and services through a unified command or search interface. The project focuses on creating a centralized input field where users can enter commands, queries, or shortcuts that trigger actions across different applications or services. Inspired by the omnibox concept used in modern browsers, the system combines search functionality with command execution so that users can access information and perform tasks without navigating complex menus. The mirrored distribution on SourceForge exists to provide an additional download source and preserve access to the software’s source code independent of its original repository. Tools like Omnibox typically emphasize extensibility, allowing developers to add plugins or integrations that connect the interface to other systems such as APIs, search engines, or automation tools. -
7
OpenOutreach
Linkedin Automation Tool
OpenOutreach is a self-hosted, open-source LinkedIn automation platform built for B2B lead generation and outbound prospecting. Instead of requiring a prebuilt contact list, it starts from a product description and target market definition, then uses AI to discover and prioritize likely leads on LinkedIn. The system generates search queries, evaluates candidate profiles, and learns over time which contacts best match the ideal customer profile. According to the repository, it combines large language model classification with a Bayesian machine learning layer based on profile embeddings, which helps it shift from broad exploration to more confident qualification as it gathers more decisions. It is designed to automate personalized outreach as well, including connection requests and follow-up messaging, while keeping deployment under the user’s control through a local or self-hosted setup. -
8
Prompt Engineering Techniques
Collection of tutorials for Prompt Engineering techniques
Prompt Engineering Techniques is a focused companion repository that teaches prompt engineering systematically, from fundamentals to advanced strategies. It contains around twenty-plus hands-on Jupyter notebooks, each dedicated to a specific technique such as basic prompt structures, prompt templates and variables, zero-shot prompting, few-shot prompting, chain-of-thought, self-consistency, constrained generation, role prompting, task decomposition, and more. The tutorials are designed to be practical; you can run them directly, examine the prompts, and see how small changes affect model behavior and quality. The repository is framed as a “techniques library” that complements a more detailed book, which expands on the same topics with deeper explanations and exercises. It is intended for a wide audience, from beginners learning how to structure their first prompts to advanced practitioners optimizing stability, controllability, and reliability in production systems. -
9
Read Frog
Open Source Immersive Translate
Read Frog is an open-source browser extension designed to transform everyday web reading into an immersive language learning experience powered by artificial intelligence. The tool integrates translation, contextual explanations, and content analysis directly into the browsing workflow so users can learn languages naturally while reading authentic online content. Instead of forcing learners to switch between translation tools and the original text, the extension displays translations alongside the source language, making comprehension immediate and continuous. The system automatically extracts the main content of an article using intelligent parsing techniques, allowing users to focus on the most relevant text without distractions. AI models are used to generate summaries, introductions, and explanations for words, phrases, and sentences based on the learner’s language level, making the experience personalized and adaptive. -
The top-rated AI recruiting platform for faster, smarter hiring.Humanly is an AI-first recruiting platform that helps talent teams hire in days, not months—without adding headcount. Our intuitive CRM pairs with powerful agentic AI to engage and screen every candidate instantly, surfacing top talent fast. Built on insights from over 4 million candidate interactions, Humanly delivers speed, structure, and consistency at scale—engaging 100% of interested candidates and driving pipeline growth through targeted outreach and smart re-engagement. We integrate seamlessly with all major ATSs to reduce manual work, improve data flow, and enhance recruiter efficiency and candidate experience. Independent audits ensure our AI remains fair and bias-free, so you can hire confidently.
-
10
Rogue
AI Agent Evaluator & Red Team Platform
Rogue is an open-source evaluation and red-team framework designed to test the reliability, safety, and policy compliance of AI agents. The platform automatically interacts with an AI agent by generating dynamic scenarios and multi-turn conversations that simulate real-world interactions. Instead of relying solely on static test scripts, Rogue uses an agent-as-a-judge architecture where one agent probes another agent to detect failures or unexpected behaviors. The system allows developers to define specific scenarios, expected outcomes, and business rules so that the framework can verify whether an agent behaves according to required policies. During testing, Rogue records conversations and produces detailed reports that explain whether the agent passed or failed each scenario. These reports include reasoning and evidence, helping developers understand why a particular failure occurred. -
11
SWIFT LLM
Use PEFT or Full-parameter to CPT/SFT/DPO/GRPO 600+ LLMs
SWIFT LLM is a comprehensive framework developed within the ModelScope ecosystem for training, fine-tuning, evaluating, and deploying large language models and multimodal models. The platform provides a full machine learning pipeline that supports tasks ranging from model pre-training to reinforcement learning alignment techniques. It integrates with popular inference engines such as vLLM and LMDeploy to accelerate deployment and runtime performance. The framework also includes support for many modern training strategies, including preference learning methods and parameter-efficient fine-tuning techniques. ms-swift is designed to work with hundreds of language and multimodal models, providing a unified environment for experimentation and production deployment. -
12
Strix
Open-source AI hackers to find and fix your app’s vulnerabilities
Strix is an open source agent-driven security platform that uses autonomous AI agents to identify, investigate, and validate vulnerabilities in software applications. The system is designed to mimic the behavior of real attackers by executing dynamic testing and verifying findings through proof-of-concept exploitation. Unlike traditional vulnerability scanners that rely heavily on static analysis, Strix agents actively run code, probe systems, and attempt exploitation to confirm whether vulnerabilities are genuinely exploitable. The platform is intended for developers and security teams that need rapid security assessments without the overhead of manual penetration testing engagements. Strix can orchestrate multiple cooperating agents that divide investigation tasks and collaboratively analyze complex applications or infrastructure. -
13
Zep
Zep: A long-term memory store for LLM / Chatbot applications
Easily add relevant documents, chat history memory & rich user data to your LLM app's prompts. Understands chat messages, roles, and user metadata, not just texts and embeddings. Zep Memory and VectorStore implementations are shipped with your favorite frameworks: LangChain, LangChain.js, LlamaIndex, and more. Automatically embed texts and messages using state-of-the-art opeb source models, OpenAI, or bring your own vectors. Zep’s local embedding models and async enrichment ensure a snappy user experience. -
14
dive-into-llms
"Dive into LLMs" series of practical programming tutorials
The dive-into-llms project is an educational resource designed to provide a comprehensive introduction to large language models and their underlying concepts. It combines theoretical explanations with practical examples, guiding users through topics such as model architecture, training processes, and inference techniques. The repository is structured as a learning pathway, making it accessible to both beginners and intermediate practitioners interested in understanding how LLMs work. It includes code samples, tutorials, and conceptual breakdowns that bridge the gap between academic research and real-world implementation. The project also highlights best practices for working with LLMs, including prompt design and optimization strategies. By focusing on clarity and depth, it serves as both a teaching tool and a reference for developers. Overall, dive-into-llms provides a structured and practical approach to mastering modern language model technology. -
15
llama.cpp Python Bindings
Python bindings for llama.cpp
llama-cpp-python provides Python bindings for llama.cpp, enabling the integration of LLaMA (Large Language Model Meta AI) language models into Python applications. This facilitates the use of LLaMA's capabilities in natural language processing tasks within Python environments. -
16
llama2.c
Inference Llama 2 in one file of pure C
llama2.c is a minimalist implementation of the Llama 2 language model architecture designed to run entirely in pure C. Created by Andrej Karpathy, this project offers an educational and lightweight framework for performing inference on small Llama 2 models without external dependencies. It provides a full training and inference pipeline: models can be trained in PyTorch and later executed using a concise 700-line C program (run.c). While it can technically load Meta’s official Llama 2 models, current support is limited to fp32 precision, meaning practical use is capped at models up to around 7B parameters. The goal of llama2.c is to demonstrate how a compact and transparent implementation can perform meaningful inference even with small models, emphasizing simplicity, clarity, and accessibility. The project builds upon lessons from nanoGPT and takes inspiration from llama.cpp, focusing instead on minimalism and educational value over large-scale performance. -
17
node-llama-cpp
Run AI models locally on your machine with node.js bindings for llama
node-llama-cpp is a JavaScript and Node.js binding that allows developers to run large language models locally using the high-performance inference engine provided by llama.cpp. The library enables applications built with Node.js to interact directly with local LLM models without requiring a remote API or external service. By using native bindings and optimized model execution, the framework allows developers to integrate advanced language model capabilities into desktop applications, server software, and command-line tools. The system automatically detects the available hardware on a machine and selects the most appropriate compute backend, including CPU or GPU acceleration. Developers can use the library to perform tasks such as text generation, conversational chat, embedding generation, and structured output generation. Because it runs models locally, the platform is particularly useful for privacy-sensitive environments or offline AI deployments. -
18
python-whatsapp-bot
Build AI WhatsApp Bots with Pure Python
python-whatsapp-bot is an open-source framework that demonstrates how to build AI-powered WhatsApp bots using pure Python and the official WhatsApp Cloud API. The project provides a practical implementation of a messaging automation system using the Flask web framework to handle webhook events and process incoming messages in real time. Developers can configure the bot to receive user messages through the WhatsApp API, route them through application logic, and generate automated responses powered by AI services such as large language models. The repository includes example scripts and project structures that illustrate how to integrate OpenAI or similar AI models into the bot workflow, enabling conversational agents capable of answering questions or performing automated tasks. -
19
Grok-1
Open-source, high-performance Mixture-of-Experts large language model
Grok-1 is a 314-billion-parameter Mixture-of-Experts (MoE) large language model developed by xAI. Designed to optimize computational efficiency, it activates only 25% of its weights for each input token. In March 2024, xAI released Grok-1's model weights and architecture under the Apache 2.0 license, making them openly accessible to developers. The accompanying GitHub repository provides JAX example code for loading and running the model. Due to its substantial size, utilizing Grok-1 requires a machine with significant GPU memory. The repository's MoE layer implementation prioritizes correctness over efficiency, avoiding the need for custom kernels. This is a full repo snapshot ZIP file of the Grok-1 code. -
20
AReal
Lightning-Fast RL for LLM Reasoning and Agents. Made Simple & Flexible
AReaL is an open source, fully asynchronous reinforcement learning training system. AReal is designed for large reasoning and agentic models. It works with models that perform reasoning over multiple steps, agents interacting with environments. It is developed by the AReaL Team at Ant Group (inclusionAI) and builds upon the ReaLHF project. Release of training details, datasets, and models for reproducibility. It is intended to facilitate reproducible RL training on reasoning / agentic tasks, supporting scaling from single nodes to large GPU clusters. It can streamline the development of AI agents and reasoning systems. Support for algorithm and system co-design optimizations (to improve efficiency and stability). -
21
Advanced RAG Techniques
Advanced techniques for RAG systems
Advanced RAG Techniques is a comprehensive collection of tutorials and implementations focused on advanced Retrieval-Augmented Generation (RAG) systems. It is designed to help practitioners move beyond basic RAG setups and explore techniques that improve retrieval quality, context construction, and answer robustness. The repository organizes techniques into categories such as foundational RAG, query enhancement, context enrichment, and advanced retrieval, making it easier to navigate specific areas of interest. It includes hands-on Jupyter notebooks and runnable scripts that show how to implement ideas like optimizing chunk sizes, proposition chunking, HyDE/HyPE query transformations, fusion retrieval, reranking, and ensemble retrieval. There is also an evaluation section that demonstrates how to measure RAG performance and compare different configurations in a systematic way. -
22
Alpaca.cpp
Locally run an Instruction-Tuned Chat-Style LLM
Run a fast ChatGPT-like model locally on your device. This combines the LLaMA foundation model with an open reproduction of Stanford Alpaca a fine-tuning of the base model to obey instructions (akin to the RLHF used to train ChatGPT) and a set of modifications to llama.cpp to add a chat interface. Download the zip file corresponding to your operating system from the latest release. The weights are based on the published fine-tunes from alpaca-lora, converted back into a PyTorch checkpoint with a modified script and then quantized with llama.cpp the regular way. -
23
Claude Code Bridge
Real-time multi-AI collaboration: Claude, Codex & Gemini
Claude Code Bridge is an open-source command-line tool designed to enable real-time collaboration between multiple AI coding assistants within a unified development environment. The system allows developers to coordinate interactions between models such as Claude, Codex, and Gemini so that they can work together on programming tasks. By maintaining persistent shared context between these models, the tool reduces redundant prompts and minimizes token usage while allowing each AI system to contribute specialized capabilities. The architecture functions as a unified launcher that manages communication between multiple AI providers and coordinates their responses within the same development session. Developers can run the tool in terminal environments and integrate it with terminal multiplexers such as tmux or advanced terminal emulators. -
24
CodeGeeX2
CodeGeeX2: A More Powerful Multilingual Code Generation Model
CodeGeeX2 is the second-generation multilingual code generation model from ZhipuAI, built upon the ChatGLM2-6B architecture and trained on 600B code tokens. Compared to the first generation, it delivers a significant boost in programming ability across multiple languages, outperforming even larger models like StarCoder-15B in some benchmarks despite having only 6B parameters. The model excels at code generation, translation, summarization, debugging, and comment generation, and it supports over 100 programming languages. With improved inference efficiency, quantization options, and multi-query/flash attention, CodeGeeX2 achieves faster generation speeds and lightweight deployment, requiring as little as 6GB GPU memory at INT4 precision. Its backend powers the CodeGeeX IDE plugins for VS Code, JetBrains, and other editors, offering developers interactive AI assistance with features like infilling and cross-file completion. -
25
CogView4
CogView4, CogView3-Plus and CogView3(ECCV 2024)
CogView4 is the latest generation in the CogView series of vision-language foundation models, developed as a bilingual (Chinese and English) open-source system for high-quality image understanding and generation. Built on top of the GLM framework, it supports multimodal tasks including text-to-image synthesis, image captioning, and visual reasoning. Compared to previous CogView versions, CogView4 introduces architectural upgrades, improved training pipelines, and larger-scale datasets, enabling stronger alignment between textual prompts and generated visual content. It emphasizes bilingual usability, making it well-suited for cross-lingual multimodal applications. The model also supports fine-tuning and downstream customization, extending its applicability to creative content generation, human–computer interaction, and research on vision-language alignment.
