awesome-repositories.com
Blog
MCP
awesome-repositories.com

Discover the best open-source repositories with AI-powered search.

ExploreCurated searchesOpen-source alternativesSelf-hosted softwareBlogSitemap
ProjectMCP serverAboutHow we rankPress
LegalPrivacyTerms
© 2026 Bringes Technology SRL·VAT RO45896025·hello@awesome-repositories.com
OpenLMLab avatar

OpenLMLab/MOSS

0
View on GitHub↗
12,140 stars·1,134 forks·Python·Apache-2.0·20 viewstxsun1997.github.io/blogs/moss.html↗

MOSS

MOSS is a conversational AI platform, fine-tuning toolkit, and quantized model runtime. It provides a framework for deploying large language models capable of multi-turn dialogue, general-purpose response generation, and following complex instructions.

The system functions as a tool-augmented framework that extends model knowledge through external plugins and tool-call loops. This allows the model to execute tasks via search engines and calculators to augment responses with external data.

The project covers model training through supervised conversational fine-tuning and optimizes deployment via low-bit weight quantization to reduce GPU memory usage. It includes a REST-based API with stateful session management and a web interface for interactive chat sessions.

Features

  • Conversational AI Platforms - Provides a complete platform for deploying large language models with multi-turn dialogue and web interfaces.
  • Conversational Dialogue Systems - Provides a comprehensive platform for building and deploying interactive AI systems capable of complex multi-turn dialogue.
  • Multi-turn Interaction Managers - Manages stateful multi-turn conversations that follow complex instructions while applying safety filters.
  • External Tool Execution - Enables the model to execute external tools like search engines and calculators to augment responses.
  • Fine-Tuning Toolkits - Includes a specialized toolkit for supervised conversational fine-tuning of pre-trained language models.
  • Tool-Augmented Language Models - Connects large language models to external plugins and tools to perform tasks beyond static text generation.
  • Tool Augmentations - Extends model capabilities beyond static training data by allowing active invocation of external functions and APIs.
  • Quantized Model Deployments - Deploys large language models with reduced memory footprints using INT4 and INT8 quantization for efficient inference.
  • Language Model Fine-Tuning - Implements specialized workflows for adapting pre-trained language models to conversational tasks using custom datasets.
  • Quantized Inference Runtimes - Implements a quantized runtime using low-bit weight precision to reduce GPU memory usage during inference.
  • Weight Quantization - Compresses model weights to INT4 or INT8 precision to significantly reduce GPU memory usage during inference.
  • Supervised Fine-Tuning - Implements supervised fine-tuning methods to optimize pre-trained models for specific conversational tasks.
  • Tool-Execution Loops - Orchestrates the request-response loop between model tool requests and the execution of external functions.
  • General Purpose Models - Produces human-like responses for diverse tasks including coding, mathematical problem solving, and general conversation.
  • Plugin-Based Agent Integrations - Integrates external plugins by generating tool calls to enhance the accuracy of AI responses.
  • Chatbot Hosting Services - Offers network APIs and hosting capabilities to provide model responses to external applications while maintaining state.
  • Conversational Session Management - Tracks unique session identifiers to maintain context and conversation history across multi-turn interactions.
  • Stateful - Provides a REST-based API that uses unique identifiers to maintain conversation state across multiple interactions.
  • RESTful APIs - Exposes language model functionality through a standardized RESTful HTTP interface for external client integration.
  • Plugin-Based Architectures - Uses a modular plugin architecture to integrate search engines and calculators for expanding the model's knowledge base.
  • Web Chat Interfaces - Provides a graphical web-based user interface for interacting with the conversational AI model.
  • Conversational and Dialog Datasets - Conversational data labeled for usefulness, loyalty, and harmlessness.
  • Foundation Models - Conversational language model supporting multiple plugins and tools.
  • Language Models - A tool-augmented conversational model for research and dialogue.
  • LLM Frameworks - Bilingual conversational model supporting plugins and multi-turn dialogue.
  • Open Source Models - Offers a conversational model capable of running on consumer hardware.
  • Specialized Domain Models - Research-oriented conversational model.
  • Text LLM Models - Conversational model supporting plugins and multi-turn dialogue.

Star history

Star history chart for openlmlab/mossStar history chart for openlmlab/moss

How this analysis was created: This summary and feature list are AI-generated from collected project material and can contain mistakes. Stars, license and language are imported from GitHub. Inclusion does not mean that we have tested or audited this project. Check the source documentation for any feature you depend on. Learn more on our About page.

AI search

Explore more awesome repositories

Describe what you need in plain English — the AI ranks thousands of curated open-source projects by relevance.

Start searching with AI

Frequently asked questions

What does openlmlab/moss do?

MOSS is a conversational AI platform, fine-tuning toolkit, and quantized model runtime. It provides a framework for deploying large language models capable of multi-turn dialogue, general-purpose response generation, and following complex instructions.

What are the main features of openlmlab/moss?

The main features of openlmlab/moss are: Conversational AI Platforms, Conversational Dialogue Systems, Multi-turn Interaction Managers, External Tool Execution, Fine-Tuning Toolkits, Tool-Augmented Language Models, Tool Augmentations, Quantized Model Deployments.

Which projects share features with openlmlab/moss?

Projects with overlapping indexed features include: thudm/chatglm3 — ChatGLM3 is an open-weights large language model designed for bilingual conversational interactions in English and… lianjiatech/belle — BELLE is a specialized implementation of Chinese conversational large language models, encompassing a full instruction… openmoss/moss — MOSS is a conversational AI API server and framework designed to manage stateful multi-turn dialogues via session… lm-sys/fastchat — FastChat is a training and serving platform for large language models that provides an integrated toolkit for… openbmb/minicpm — MiniCPM is a collection of small language models designed for local, on-device deployment in resource-constrained… 01-ai/yi — Yi is a bilingual language model and foundation model designed for natural language processing, reasoning, and reading…

Projects sharing features with MOSS

These projects share indexed features with MOSS. Shared tags can include platform or build tooling; verify the primary use case before treating a result as a replacement.
  • thudm/chatglm3THUDM avatar

    THUDM/ChatGLM3

    13,676View on GitHub↗

    ChatGLM3 is an open-weights large language model designed for bilingual conversational interactions in English and Chinese. It functions as a tool-augmented system capable of calling external functions and executing internal code to resolve complex tasks. The model utilizes four-bit quantization to reduce memory requirements, enabling inference on consumer hardware and diverse processing units including GPUs and CPUs. It features an expanded context window for processing and summarizing long documents and includes a supervised fine-tuning pipeline for adapting the model to specialized domains

    Python
    View on GitHub↗13,676
  • lianjiatech/belleLianjiaTech avatar

    LianjiaTech/BELLE

    8,273View on GitHub↗

    BELLE is a specialized implementation of Chinese conversational large language models, encompassing a full instruction tuning framework. It provides a pipeline for training, evaluating, and deploying models optimized for natural language understanding and dialogue tasks in the Chinese language. The project is distinguished by its integrated approach to model refinement, combining the curation of multi-million entry instruction datasets with a distributed training pipeline. This pipeline supports both full fine-tuning and low-rank adaptation to optimize conversational performance. The system

    HTMLbloomchinese-nlpgpt-evaluation
    View on GitHub↗8,273
  • openmoss/mossOpenMOSS avatar

    OpenMOSS/MOSS

    12,140View on GitHub↗

    MOSS is a conversational AI API server and framework designed to manage stateful multi-turn dialogues via session identifiers for remote interaction. It functions as a tool-augmented language model framework and a quantized inference engine. The project integrates external plugins, such as search engines and calculators, to provide factual and computed data within model responses. It also includes a supervised fine-tuning toolkit for adapting base language models to specific conversational datasets and behavioral instructions. The system supports inference optimization through 4-bit and 8-bi

    Pythonchatgptdeep-learningdialogue-systems
    View on GitHub↗12,140
  • lm-sys/fastchatlm-sys avatar

    lm-sys/FastChat

    39,472View on GitHub↗

    FastChat is a training and serving platform for large language models that provides an integrated toolkit for fine-tuning, hosting, and benchmarking chatbots. It functions as an inference server capable of hosting multiple models and exposing them via a standardized API for chat applications. The platform distinguishes itself through a distributed model controller that manages worker nodes and routes requests across a hardware-agnostic inference layer supporting various accelerators. It includes a dedicated evaluation framework for assessing model quality using automated judges, multi-turn di

    Python
    View on GitHub↗39,472
Compare all 30 related projects→