Open-source large-language-models software
3737 open-source libraries, tools and applications tagged large-language-models, ranked by how closely large-language-models is their primary purpose, then by adoption and maintenance health. Each entry links to a page with sources, use cases and when to choose or avoid it.
3737 products, primary matches first, then adoption-weighted; health v2 shown.
| Product | Health v2 | Stars | Maturity |
|---|---|---|---|
| dataelement/Clawith Clawith is an open-source multi-agent collaboration platform where each AI agent has a persistent identity, long-term memory, and its own w… | 76 | 4164 | active |
| nageoffer/ragent Ragent AI is a production-grade Java platform for building Agentic RAG applications, covering document ingestion, hybrid retrieval (vector,… | 75 | 4164 | active |
| UsefulSoftwareCo/executor Executor is an open-source integration layer and MCP gateway for AI agents, letting you configure MCP servers, OpenAPI specs, GraphQL APIs,… | 77 | 4162 | active |
| Spark NLP Spark NLP is an open-source natural language processing library built natively on Apache Spark, providing scalable NLP annotations and tran… | 98 | 4160 | stable |
| OpenManus/OpenManus-RL OpenManus-RL is an open-source project for reinforcement-learning-based tuning of LLM agents, built on the verl training framework. It prov… | 44 | 4159 | active |
| ericc-ch/copilot-api A reverse-engineered proxy that exposes the GitHub Copilot API as OpenAI and Anthropic compatible endpoints, letting any OpenAI/Anthropic-c… | 44 | 4148 | active |
| zml/zml ZML is a production LLM inference stack written in Zig, built on MLIR and OpenXLA, that compiles models to run at peak performance across N… | 69 | 4136 | active |
| marcelroed/gigatoken Gigatoken is a Rust-based tokenizer library for language modeling that tokenizes text at GB/s throughput, claiming ~1000x speedups over Hug… | 58 | 4134 | active |
| IDEA-CCNL/Fengshenbang-LM Fengshenbang-LM is an open-source suite of Chinese large language models and a PyTorch training framework from IDEA Research's CCNL lab, ai… | 67 | 4123 | active |
| openai/transformer-debugger Transformer Debugger (TDB) is an OpenAI tool for investigating specific behaviors of small language models, combining automated interpretab… | 57 | 4123 | active |
| Langroid Langroid is a Python framework for building LLM-powered applications using multi-agent programming, where agents encapsulate LLM conversati… | 94 | 4120 | active |
| CSGHub CSGHub is an open-source, self-hostable platform for managing the full lifecycle of LLM assets including models, datasets, spaces, and agen… | 90 | 4115 | active |
| ucbepic/docetl DocETL is a Python library and CLI for building LLM-powered data processing and ETL pipelines over structured and unstructured data using d… | 78 | 4114 | active |
| CommandCodeAI/command-code Command Code is a terminal-based AI coding agent that builds full-stack projects, fixes bugs, writes tests, and refactors code. Its disting… | 66 | 4112 | active |
| microsoft/apm APM (Agent Package Manager) is an open-source dependency manager for AI coding agents, letting teams declare skills, prompts, instructions,… | 81 | 4106 | active |
| PaddlePaddle/PaddleRec PaddleRec is a large-scale recommendation algorithm library built on PaddlePaddle, containing classic and state-of-the-art recommendation m… | 26 | 4086 | active |
| TransformerOptimus/SuperAGI SuperAGI is a dev-first open source framework for building, managing, and running autonomous AI agents powered by large language models. It… | 21 | 17702 | maintenance |
| QwenLM/Qwen2.5-Omni Qwen2.5-Omni is an end-to-end multimodal model from Alibaba's Qwen team that understands text, images, audio, and video, and generates stre… | 29 | 4075 | active |
| FedML FedML (TensorOpera) is a unified Python library for large-scale distributed training, model serving, and federated learning across GPU clou… | 41 | 4070 | active |
| StarsfieldAI/R1-V R1-V is an open-source research codebase for training vision-language models with reinforcement learning (RLVR/GRPO), demonstrating strong … | 18 | 4063 | active |
| ginobefun/BestBlogs BestBlogs.dev is an AI-powered personal reading assistant and content curation platform that aggregates articles, podcasts, videos, tweets,… | 64 | 4053 | active |
| hanshuaikang/AI-Media2Doc A self-hostable web application that uses AI large language models to convert video and audio into various document styles such as Xiaohong… | 51 | 4052 | active |
| yifanfeng97/Hyper-Extract Hyper-Extract is a Python CLI tool that transforms unstructured documents into structured knowledge using LLMs, producing graphs, hypergrap… | 82 | 4051 | active |
| defog-ai/sqlcoder SQLCoder is a family of fine-tuned open-weight LLMs that convert natural language questions into SQL queries, outperforming GPT-4 on text-t… | 29 | 4048 | active |
| kagent-dev/kagent kagent is a Kubernetes-native framework for building, deploying, and managing AI agents as first-class Kubernetes resources via CRDs. It su… | 84 | 4047 | active |
| xintaofei/codeg Codeg is a multi-agent AI coding workspace that aggregates sessions from agent CLIs like Claude Code, Codex, and OpenCode into one searchab… | 79 | 4042 | active |
| Codex-X Codex-X is a cross-platform desktop GUI tool built with Tauri 2, React, and Rust for managing OpenAI Codex desktop and CLI configurations. … | 79 | 4036 | active |
| googleapis/python-genai The official Google Gen AI Python SDK for integrating Google's generative models (Gemini Developer API and Gemini Enterprise Agent Platform… | 85 | 4035 | active |
| OpenBMB/PilotDeck PilotDeck is an open-source, task-oriented AI agent productivity platform built around the concept of 'WorkSpace', developed by THUNLP, Mod… | 80 | 4031 | active |
| steipete/oracle Oracle is a TypeScript CLI and MCP server that bundles a prompt with selected project files and sends that context to frontier AI models (G… | 82 | 4030 | active |
| QwenLM/Qwen3-Omni Qwen3-Omni is a natively end-to-end omni-modal large language model from Alibaba Cloud's Qwen team that understands text, images, audio, an… | 49 | 4028 | active |
| knownsec/aipyapp AiPy (Python-Use) is an AI desktop assistant from Knownsec that implements a 'Code is Agent' paradigm: it gives an LLM a full Python execut… | 57 | 4027 | active |
| MikeChongCan/scylla Scylla is an intelligent proxy pool service that automatically crawls, validates, and serves proxy IPs via a JSON API and web UI. It integr… | 30 | 4023 | active |
| OSU-NLP-Group/HippoRAG HippoRAG is a Python RAG framework inspired by human long-term memory that combines LLMs, knowledge graphs, and Personalized PageRank to in… | 57 | 4021 | active |
| microsoft/PromptWizard PromptWizard is a discrete prompt optimization framework from Microsoft that uses a self-evolving mechanism where an LLM generates, critiqu… | 42 | 4020 | active |
| muxuuu/serenity-skill An Agent Skill (SKILL.md-based prompt/methodology package) that encodes a Serenity-style investment research workflow for supply-chain bott… | 57 | 4013 | active |
| Rapid-MLX Rapid-MLX is a local LLM inference engine for Apple Silicon Macs built on MLX, exposing a drop-in OpenAI/Anthropic-compatible API. It offer… | 79 | 4012 | active |
| Leonxlnx/unlazy unlazy is a skill for AI coding agents (Claude Code, Codex CLI) that enforces completion discipline via the Depth Tree method, splitting ta… | 55 | 4006 | active |
| badrisnarayanan/antigravity-claude-proxy A Node.js proxy server that exposes Antigravity's Cloud Code Claude and Gemini models behind an Anthropic-compatible Messages API. It trans… | 74 | 4004 | active |
| gusye1234/nano-graphrag nano-graphrag is a lightweight, ~1100-line Python implementation of Microsoft's GraphRAG, designed to be small, fast, and easy to read or h… | 40 | 4001 | active |
| RavenDB RavenDB is an open-source (AGPLv3) ACID NoSQL document database written in C#, featuring full-text search, vector search, time series, shar… | 92 | 4000 | stable |
| Marin Marin is an open-source Python framework and research program for training foundation models, covering the full pipeline from data curation… | 79 | 3995 | active |
| matt1398/claude-devtools A free, open-source Electron desktop app that acts as missing DevTools for Claude Code, reading local ~/.claude/ session logs to reconstruc… | 73 | 3993 | active |
| BenedictKing/ccx CCX is a self-hosted AI API proxy and protocol translation gateway written in Go that unifies access to Claude, OpenAI Chat/Images/Embeddin… | 72 | 3992 | active |
| jackMort/ChatGPT.nvim A Neovim plugin written in Lua that integrates OpenAI's ChatGPT API directly into the editor. It provides interactive Q&A, persona-based co… | 47 | 3992 | active |
| sourcebot-dev/sourcebot Sourcebot is a self-hosted code search and code intelligence platform that indexes repos across GitHub, GitLab, Bitbucket, Azure DevOps, Ge… | 86 | 3990 | active |
| LLaDA Official PyTorch implementation of LLaDA, a family of large language diffusion models (8B base/instruct, MoE, and iLLaDA variants) with pre… | 59 | 3986 | active |
| nicobailon/pi-subagents A Pi extension that lets the Pi coding agent delegate tasks to focused child subagents with async execution, truncation, artifacts, and ses… | 80 | 3967 | active |
| AnswerDotAI/RAGatouille RAGatouille is a Python library that makes it easy to use and train state-of-the-art late-interaction retrieval models like ColBERT in any … | 23 | 3964 | active |
| circlemind-ai/fast-graphrag fast-graphrag is a Python library providing a streamlined, promptable GraphRAG framework for interpretable, high-precision retrieval workfl… | 41 | 3960 | active |
| aurelio-labs/semantic-router Semantic Router is a Python library that provides a fast decision-making layer for LLMs and agents, routing requests based on semantic vect… | 95 | 3959 | active |
| Lightning-AI/LitServe LitServe is a Python framework for building custom AI inference servers with full control over batching, routing, streaming, and scaling lo… | 92 | 3956 | active |
| thu-ml/SageAttention SageAttention is a family of quantized attention kernels (INT8/FP8/FP4) that accelerate transformer inference 2-5x over FlashAttention with… | 38 | 3956 | active |
| OpenHealthForAll/open-health OpenHealth is a self-hostable AI health assistant that consolidates personal health data (blood tests, checkups, wearables, symptoms) into … | 46 | 3954 | active |
| Anthropic Python SDK The official Python SDK for accessing the Anthropic Claude API. It provides a typed client for creating messages, streaming responses, and … | 93 | 3951 | stable |
| TransformerLensOrg/TransformerLens TransformerLens is a Python library for mechanistic interpretability of GPT-style transformer language models. It lets researchers load tho… | 98 | 3949 | active |
| duolahypercho/codex-router A local model router that lets external LLM providers (Anthropic, Kimi, DeepSeek, xAI, GitHub Copilot, and others) be used inside the Codex… | 79 | 3949 | active |
| parcadei/Continuous-Claude-v3 A framework that turns Claude Code into a persistent, multi-agent development environment with context management across sessions. It uses … | 42 | 3944 | active |
| lemony-ai/cascadeflow Cascadeflow is an open-source agent runtime intelligence layer (Python and TypeScript SDKs) that sits inside the AI agent loop to observe, … | 73 | 3941 | active |
| mushan0x0/AI0x0.com AI 0x0 is a multimodal, multi-model desktop AI assistant that lives as a floating ball on macOS and Windows, letting users invoke AI querie… | 33 | 3935 | active |
| yetone/cumora Cumora is a cross-platform team chat application where AI agents participate as first-class teammates alongside humans, with personas, memo… | 77 | 3934 | active |
| evalstate/fast-agent fast-agent is a Python CLI-first framework for building, running, and evaluating LLM agents with first-class MCP, ACP, and A2A protocol sup… | 84 | 3931 | active |
| huggingface/smollm Hugging Face's repository for the SmolLM and SmolVLM families of compact, fully open language and vision-language models, including trainin… | 67 | 3926 | active |
| openai/openai-agents-js A lightweight, provider-agnostic TypeScript/JavaScript framework from OpenAI for building multi-agent LLM workflows, including text agents,… | 82 | 3921 | active |
| seakee/CPA-Manager-Plus A self-hosted management panel and observability dashboard for CLIProxyAPI (CPA) AI gateways, built in Go. It tracks requests, usage, cost,… | 78 | 3907 | active |
| claraverse-space/ClaraVerse ClaraVerse is a self-hosted, privacy-focused AI workspace that combines chat, multi-agent teams, a visual workflow builder, RAG document pr… | 75 | 3905 | active |
| safetensors/safetensors Safetensors is a simple, secure file format and library for storing and distributing tensors, designed as a fast zero-copy alternative to p… | 87 | 3901 | stable |
| vllm-project/llm-compressor LLM Compressor is a Python library for applying quantization and pruning algorithms to large language models, producing compressed-tensors … | 91 | 3897 | active |
| ilysenko/codex-desktop-linux An unofficial community-maintained Linux distribution of OpenAI's ChatGPT desktop app (formerly Codex), repackaged from the official signed… | 61 | 3893 | active |
| LazyAGI/LazyLLM LazyLLM is a low-code Python framework for building multi-agent LLM applications, covering prototype assembly, data feedback, and iterative… | 92 | 3888 | active |
| hkust-nlp/simpleRL-reason A research codebase from HKUST-NLP implementing a simple reinforcement learning recipe (rule-based rewards on GSM8K/Math data) to train LLM… | 44 | 3877 | active |
| synthetic-sciences/openscience OpenScience is an open-source AI workbench for scientific research that runs the full research loop: literature review, hypothesis formatio… | 75 | 3876 | active |
| gnekt/My-Brain-Is-Full-Crew A crew of 8+ AI agents with 14 specialized skills that manages an Obsidian vault through conversational chat, handling knowledge organizati… | 52 | 3874 | active |
| yvgude/lean-ctx LeanCTX is a local-first Rust binary that acts as a context engineering layer for AI coding agents, providing an MCP server, shell output c… | 76 | 3868 | active |
| NVlabs/VILA VILA is a family of open-source vision language models (VLMs) optimized for efficient video and multi-image understanding, spanning edge, d… | 54 | 3865 | active |
| mayooear/ai-pdf-chatbot-langchain A monorepo template for an AI PDF chatbot agent that ingests PDFs, stores embeddings in Supabase, and answers questions using OpenAI via La… | 10 | 16582 | maintenance |
| golutra/golutra Golutra is a Tauri-based desktop application (Vue 3 + Rust) that orchestrates multiple AI coding CLI agents such as Claude Code, Codex CLI,… | 81 | 3853 | active |
| TracecatHQ/tracecat Tracecat is an open-source, AI-native security automation (SOAR) platform that combines low-code workflows, tool-calling agents, case manag… | 90 | 3844 | active |
| HKUDS/Paper2Slides Paper2Slides is a Python application that converts research papers, reports, and documents into professional presentation slides and poster… | 50 | 3840 | active |
| lanqian528/chat2api A Python service that proxies ChatGPT's web interface into an OpenAI-compatible API format, supporting GPT-3.5, GPT-4/4o, O1/O3 models, GPT… | 31 | 3839 | active |
| predibase/lorax LoRAX is a multi-LoRA inference server that serves thousands of fine-tuned LLM adapters on a single GPU by sharing a common base model. It … | 60 | 3835 | active |
| sentient-agi/OpenDeepSearch OpenDeepSearch is an open-source search tool that augments LLMs and reasoning agents with web search capabilities, aiming to match closed-s… | 23 | 3834 | active |
| midday-ai/packrun packrun.dev is a web service and MCP server that scores, compares, and ranks npm packages across 50+ categories using live metrics like dow… | 49 | 3833 | active |
| jmiao24/Paper2Agent Paper2Agent is a multi-agent AI system that automatically converts research paper codebases into interactive AI agents with minimal human i… | 61 | 3831 | active |
| Atmosphere Atmosphere is a portable AI agent runtime for the JVM that lets a single @Agent class run across twelve AI runtimes (Spring AI, LangChain4j… | 95 | 3821 | active |
| aiming-lab/SimpleMem SimpleMem is a Python library and MCP server that provides efficient lifelong memory for LLM agents, storing, compressing, and retrieving l… | 65 | 3821 | active |
| wdcpclover/ai4paper AI4Paper is an AI research workbench delivered primarily as a Zotero 7-10 plugin, with a web app, browser extension, and WeChat mini-progra… | 79 | 3811 | active |
| tbxark/ChatGPT-Telegram-Workers A Telegram ChatGPT bot deployable on Cloudflare Workers, Vercel, or Docker with a single-file, dependency-free setup. It supports multiple … | 94 | 3805 | active |
| SciSharp/LLamaSharp LLamaSharp is a cross-platform C#/.NET library that wraps llama.cpp to run LLaMA-family and other LLMs (including multimodal LLaVA) efficie… | 89 | 3803 | active |
| Polymarket/agents A Python developer framework and utility set for building AI agents that trade autonomously on Polymarket prediction markets. It integrates… | 10 | 3803 | active |
| OpenAvatarChat OpenAvatarChat is a modular interactive digital human (talking avatar) chat application that combines ASR, LLM, TTS, and avatar rendering c… | 69 | 3802 | active |
| stickerdaniel/linkedin-mcp-server An open-source MCP server that gives AI assistants like Claude and ChatGPT access to LinkedIn data (profiles, companies, jobs, messages) th… | 82 | 3800 | active |
| 1186258278/OpenClawChineseTranslation A Chinese-localized distribution of OpenClaw, an open-source personal AI assistant that connects Claude/ChatGPT/Gemini LLMs to messaging pl… | 77 | 3796 | active |
| AminBlg/SimpleEnglish An agent skill (SKILL.md) that makes LLMs write documentation in ASD-STE100 Simplified Technical English, the controlled language used in a… | 79 | 3794 | active |
| tutti-os/tutti Tutti is a local-first desktop workspace where multiple AI coding agents (Claude Code, Codex, Cursor, OpenCode) share one real-time context… | 76 | 3791 | active |
| microsoft/mcp Microsoft's official catalog and monorepo of MCP (Model Context Protocol) server implementations, including Azure MCP and Microsoft Fabric … | 84 | 3790 | active |
| meta-llama/codellama Official Meta repository with inference code for the Code Llama family of large language models for code, based on Llama 2. It provides min… | 10 | 16224 | maintenance |
| Hunyuan-PromptEnhancer/PromptEnhancer PromptEnhancer is a prompt-rewriting framework from Tencent Hunyuan that uses a Chain-of-Thought rewriter trained via reinforcement learnin… | 59 | 3785 | active |
| deanxv/coze-discord-proxy A self-hosted Go service that proxies conversations to a Coze-Bot on Discord, exposing OpenAI-compatible API endpoints (v1/chat/completions… | 55 | 3778 | stable |
| PeterH0323/Streamer-Sales Streamer-Sales is a fine-tuned LLM-based AI sales livestreamer application that generates persuasive product commentary from product descri… | 17 | 3775 | active |