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 |
|---|---|---|---|
| XInTheDark/raycast-g4f A Raycast extension that provides free access to GPT-4, Claude, Llama, Gemini and other AI models via GPT4Free providers, with full support… | 51 | 1087 | active |
| ufy2024/AuC AuC (Agents-ufy-Core) is a Python single-agent framework built on asyncio with a pluggable ReAct reasoning loop, LLM adapters, tiered tool … | 53 | 1086 | active |
| andrepimenta/claude-code-chat A VS Code extension that provides a graphical chat interface for Claude Code, replacing terminal-based interaction with a visual UI inside … | 79 | 1085 | active |
| tigicion/dao-code Dao Code is an open-source terminal-native AI coding agent written in TypeScript, targeting DeepSeek V4 with 1M context and Claude Code-com… | 75 | 1084 | active |
| QwenLM/Qwen2.5-Math Qwen2.5-Math is a series of math-specialized large language models (1.5B/7B/72B base and instruct variants plus a 72B reward model) built o… | 24 | 1084 | active |
| kimiyoung/transformer-xl Official implementation of Transformer-XL, an attention-based language model architecture that extends context beyond a fixed length via se… | 32 | 3717 | maintenance |
| XiaomiMiMo/MiMo-Audio Xiaomi's open-source 7B audio language model family (Base and Instruct) plus a 1.2B RVQ audio tokenizer, pretrained on 100M+ hours of audio… | 53 | 1083 | active |
| StreetLamb/tribe Tribe AI is a low-code web application for rapidly building and coordinating multi-agent teams using drag-and-drop, built on LangChain and … | 35 | 1083 | active |
| mit-han-lab/streaming-vlm StreamingVLM is a vision-language model framework from MIT Han Lab for real-time understanding of effectively infinite video streams. It ma… | 35 | 1083 | active |
| GAIR-NLP/LIMO LIMO is a research project and training framework demonstrating that large language models can achieve strong mathematical reasoning with o… | 33 | 1083 | active |
| FalkorDB/QueryWeaver QueryWeaver is an open-source Text2SQL tool that converts plain-English questions into SQL queries using graph-powered schema understanding… | 82 | 1082 | active |
| GradientHQ/symphony-coord Symphony-Coord is a decentralized multi-agent framework that treats agent selection as an online multi-armed bandit problem, allowing roles… | 60 | 1081 | active |
| LangSmith Official Python and JavaScript/TypeScript client SDKs for the LangSmith platform, enabling tracing, debugging, evaluation, and monitoring o… | 10 | 1081 | active |
| ikechan8370/chatgpt-plugin A ChatGPT/LLM chat plugin for Yunzai-Bot (Miao-Yunzai) QQ bots, built on the Chaite kernel. It provides multi-model channels, presets, grou… | 74 | 1080 | active |
| BruceMacD/chatd Chatd is an Electron desktop application that lets you chat with your local documents using a local large language model (Mistral-7B) via O… | 18 | 1080 | active |
| THU-BPM/MarkLLM MarkLLM is an open-source Python toolkit for watermarking large language model outputs, implementing multiple LLM watermarking algorithms w… | 67 | 1078 | active |
| open-webui/openapi-servers A collection of reference OpenAPI Tool Server implementations that expose external tools and data sources to LLM agents over standard REST … | 36 | 1078 | active |
| Pokee-AI/PokeeResearchOSS An open-source repository for Pokee's 7B-parameter DeepResearch agent that performs multi-turn web search and content reading to answer com… | 35 | 1078 | active |
| weiesky/cc-viewer CC-Viewer is a request monitoring tool for Claude Code that captures and visualizes all API requests and responses in real time via a web v… | 81 | 1077 | active |
| tryAGI/LangChain LangChain .NET is a C#/.NET implementation of the LangChain framework for building LLM-powered applications through composability. It provi… | 64 | 1077 | active |
| vstorm-co/pydantic-deepagents Pydantic Deep Agents is an open-source, self-hosted terminal AI assistant (a Claude Code alternative) plus the Python framework behind it, … | 79 | 1076 | active |
| arcee-ai/DistillKit DistillKit is an open-source Python toolkit for knowledge distillation of large language models, supporting both online and offline distill… | 57 | 1076 | active |
| mskayyali/nodepad nodepad is a spatial note-taking web application where notes are placed on a canvas and AI quietly classifies them, infers connections, and… | 54 | 1074 | active |
| orange2ai/renwei-writing An open-source AI agent skill (a prompt/instruction pack) called 'Renwei Writing' that guides AI editors to revise text while preserving th… | 50 | 1074 | active |
| agenmod/immortal-skill An open-source 'digital immortality' framework that distills a person's persona from chat logs and documents across 12+ platforms (WeChat, … | 46 | 1074 | active |
| trendy-design/llmchat LLMChat is a privacy-focused AI chat platform built with Next.js and TypeScript that provides a unified interface for chatting with multipl… | 21 | 1074 | active |
| THUDM/GLM GLM is a general language model pretrained with an autoregressive blank-filling objective, released with pretrained checkpoints and fine-tu… | 32 | 3680 | maintenance |
| MGdaasLab/WHartTest WHartTest is an AI-driven test automation platform built on Django 5.2 + DRF with a Vue frontend, generating and managing executable test c… | 85 | 1073 | active |
| bytedance/SandboxFusion A secure, self-hosted code sandbox service from ByteDance that runs and judges code generated by LLMs across 20+ programming languages via … | 60 | 1072 | active |
| open-gigaai/giga-train GigaTrain is an efficient and scalable Python training framework for large AI models, supporting distributed multi-GPU/multi-node execution… | 59 | 1072 | active |
| dynamiq-ai/dynamiq Dynamiq is an open-source Python orchestration framework for building agentic AI and LLM applications, covering agents, RAG pipelines, work… | 85 | 1071 | active |
| GanymedeNil/document.ai A universal local knowledge base solution that stores documents as vectors in a vector database and uses GPT3.5 to generate answers from re… | 31 | 3666 | maintenance |
| Snow Snow CLI is a terminal-based AI coding agent written in TypeScript that can read, write, and refactor code directly from the command line. … | 82 | 1069 | active |
| JudgmentLabs/judgeval Judgeval is an open-source Python SDK for LLM agent improvement, providing OpenTelemetry-based tracing and prompt-based agent-judge evaluat… | 85 | 1068 | active |
| Wenyan (文颜) Wenyan MCP Server is a Model Context Protocol server that lets AI clients like Claude Desktop format Markdown articles and publish them dir… | 85 | 1068 | active |
| codeacme17/examor Examor is a self-hosted web application that generates exams and review questions from your knowledge notes using LLMs like GPT-4 and Claud… | 28 | 1068 | active |
| X-LANCE/SLAM-LLM SLAM-LLM is a deep learning toolkit for training custom multimodal large language models focused on speech, language, audio, and music proc… | 52 | 1066 | active |
| zai-org/GLM-TTS GLM-TTS is a Python-based text-to-speech synthesis system built on large language models, using a two-stage LLM plus Flow model architectur… | 47 | 1066 | active |
| Dataherald/dataherald Dataherald is an open-source natural language-to-SQL engine for enterprise question answering over relational databases, exposing an API th… | 20 | 3648 | maintenance |
| CRui5in/paper-ppt-agent A self-hosted web application that uses a multi-agent AI pipeline (Strategist, Executor, Critic) to convert academic papers from PDF or LaT… | 73 | 1065 | active |
| LocoreMind/locoagent LocoAgent is an AI-powered social media agent that autonomously operates real accounts through genuine browser automation via Chrome DevToo… | 67 | 1065 | active |
| sybil-solutions/codex-shim A local Python/aiohttp server that exposes an OpenAI Responses-compatible endpoint on loopback, letting Codex Desktop use any BYOK model (O… | 55 | 1065 | active |
| Felix3322/PotPlayer_ChatGPT_Translate A PotPlayer plugin that integrates OpenAI-compatible AI APIs (including ChatGPT and Ollama) to translate video subtitles in real time. It u… | 88 | 1064 | active |
| harehare/mq mq is a jq-like command-line tool and query language for slicing, filtering, and transforming Markdown via its AST, written in Rust as a si… | 84 | 1064 | active |
| rogue-security/rogue Rogue is an open-source AI agent evaluator and red teaming platform that stress-tests agents against business policies and simulated advers… | 72 | 1064 | active |
| metaskills/experts Experts.js is a JavaScript library that simplifies creating and deploying OpenAI Assistants via the Assistants API, hiding Run object manag… | 25 | 1064 | active |
| pepperoni21/ollama-rs A Rust client library for interacting with the Ollama API, supporting completion generation, streaming, chat, model management, embeddings,… | 84 | 1063 | active |
| bigcode-project/bigcode-evaluation-harness A framework for evaluating autoregressive code generation language models on benchmarks like HumanEval, MBPP, MultiPL-E, and HumanEvalPack.… | 34 | 1062 | active |
| centerforaisafety/HarmBench HarmBench is a standardized, open-source evaluation framework for automated red teaming of large language models, comparing attack methods … | 26 | 1062 | active |
| mybigday/llama.rn A React Native binding of llama.cpp that enables on-device LLM inference on iOS and Android. It supports GPU/NPU acceleration (Metal, Hexag… | 93 | 1061 | active |
| zhuzilin/ring-flash-attention A Python library implementing RingAttention on top of FlashAttention for distributed long-context transformer training. It provides varlen … | 38 | 1061 | active |
| abertsch72/unlimiformer Unlimiformer is a method and official implementation for augmenting pretrained encoder-decoder transformers with retrieval-based attention,… | 30 | 1061 | stable |
| yokingma/SearChat SearChat is a self-hostable AI-powered conversational search engine that combines web search (Bing, Google, SearXNG) with multi-turn chat b… | 82 | 1060 | active |
| Tencent/WeSmartFlow WeSmartFlow is an agent-native adaptive learning framework that models the full learning process with ReAct-based tutoring agents, graph me… | 57 | 1059 | active |
| apple/security-pcc Apple's source code for Private Cloud Compute (PCC), the infrastructure that runs Apple Intelligence requests in a privacy-preserving cloud… | 56 | 1059 | active |
| NousResearch/DisTrO DisTrO is a family of low-latency distributed optimizers that reduce inter-GPU communication requirements by three to four orders of magnit… | 41 | 1059 | active |
| InternRobotics/PointLLM PointLLM is a multimodal large language model that understands colored 3D point clouds of objects, built on a point cloud encoder fused wit… | 62 | 1058 | active |
| pytorch/torchchat torchchat is a compact PyTorch-native codebase for running large language models locally via Python, a C/C++ runner on desktop/server, or o… | 10 | 3611 | maintenance |
| Emiyaaaaa/HiveMind AgentFlow (repo HiveMind) is a Python-first runtime layer for multi-agent systems that adds persistent run state, ordered step/message/tool… | 63 | 1056 | active |
| splx-ai/agentic-radar Agentic Radar is an open-source security scanner that analyzes LLM agentic workflows built with popular frameworks (e.g., CrewAI, LangGraph… | 47 | 1056 | active |
| lennybase/browsernode Browsernode is a TypeScript implementation of Browser-use that lets LLM-powered AI agents control a web browser via Playwright. It provides… | 31 | 1056 | active |
| metauto-ai/GPTSwarm GPTSwarm is a Python library for building LLM-based agents as computational graphs, with modules for agent graphs, memory, LLM backends, an… | 52 | 1055 | active |
| Minima-AI-Inc/minima Minima is an open-source, on-premises conversational RAG system deployed via Docker containers. It supports fully local operation with Olla… | 38 | 1055 | active |
| BAAI-DCAI/Bunny Bunny is a family of lightweight multimodal vision-language models that combine plug-and-play vision encoders (EVA-CLIP, SigLIP) with langu… | 26 | 1054 | active |
| braintrustdata/autoevals Autoevals is a Python and TypeScript library for automatically evaluating AI model outputs using LLM-as-a-judge, heuristic, and statistical… | 91 | 1053 | active |
| Dicklesworthstone/swiss_army_llama A FastAPI-based REST service that exposes local LLM capabilities including text embeddings, completions, semantic similarity, and semantic … | 29 | 1053 | active |
| shyamsaktawat/OpenAlpha_Evolve OpenAlpha_Evolve is an open-source Python framework inspired by DeepMind's AlphaEvolve that uses LLMs to iteratively generate, test, and ev… | 27 | 1053 | active |
| Arcade Arcade MCP is an open-source Python framework for building Model Context Protocol (MCP) servers and the tools that run inside them, with a … | 70 | 1049 | active |
| scrya-com/rotorquant RotorQuant is a KV cache compression method for LLM inference that replaces full d×d orthogonal rotations with block-diagonal Clifford roto… | 47 | 1049 | active |
| numman-ali/n-skills A curated marketplace of reusable AI agent skills in the universal SKILL.md format, installable via Claude Code plugins or the openskills i… | 67 | 1047 | active |
| tonbistudio/turboquant-pytorch A from-scratch PyTorch implementation of Google's TurboQuant (ICLR 2026) algorithm for compressing LLM key-value caches, including an impro… | 47 | 1047 | active |
| OpenBMB/RepoAgent RepoAgent is an LLM-powered framework that automatically generates repository-level code documentation by detecting changes in Git reposito… | 25 | 1047 | active |
| kreneskyp/ix IX is a self-hosted platform for designing, running, and scaling autonomous and semi-autonomous LLM-powered agents and workflows. It includ… | 66 | 1046 | active |
| wrtnlabs/agentica Agentica is a TypeScript agentic AI framework specialized in LLM function calling, enhanced by compiler-driven validation via typia. Agents… | 65 | 1046 | active |
| Ttungx/codex_auto_register A Python CLI tool that automates ChatGPT/Codex account registration using the DuckMail temporary email service, performs the Codex OAuth fl… | 58 | 1046 | active |
| andyzoujm/representation-engineering Official library for Representation Engineering (RepE), a top-down approach to AI transparency that monitors and manipulates population-lev… | 19 | 1046 | active |
| TIGER-AI-Lab/verl-tool VerlTool is a unified, extensible framework built on verl for training LLM agents with tool use via reinforcement learning. It decouples ac… | 61 | 1045 | active |
| snipeship/ccflare ccflare is a self-hosted multi-provider proxy for Anthropic and OpenAI APIs that routes requests by URL prefix, load-balances across multip… | 50 | 1045 | active |
| octos-org/octos Octos is a self-hosted AI agent runtime that runs a personal AI assistant on your own machine, connecting to providers like Anthropic, Open… | 78 | 1044 | active |
| webwhiz-ai/webwhiz WebWhiz is an open-source, self-hostable application that trains a ChatGPT-powered chatbot on your website data by crawling your pages and … | 45 | 1044 | active |
| myscale/MyScaleDB MyScaleDB is a SQL vector database built as a fork of ClickHouse, adding high-performance vector search and full-text search to a proven OL… | 16 | 1043 | active |
| NVIDIA-NeMo/Skills Nemo-Skills is a collection of Python pipelines for improving the skills of large language models, covering synthetic data generation, mode… | 69 | 1042 | active |
| vercel-labs/tersa Tersa is an open-source visual AI playground built as a Next.js web application where users drag, drop, and connect nodes on a canvas to bu… | 58 | 1042 | active |
| kunal12203/GrapeRoot GrapeRoot is an open-source context engine and MCP server that builds a semantic graph of a codebase (files, symbols, imports, call chains)… | 68 | 1041 | active |
| Refact Refact is an open-source, self-hosted AI coding agent written in Rust that plans and executes engineering tasks end-to-end from your IDE, w… | 10 | 3541 | maintenance |
| canwhite/Krebs Krebs is a self-hosted AI gateway with a general-purpose agent focused on attention management. It provides multi-turn dialogue with tool e… | 57 | 1039 | active |
| ricklamers/gpt-code-ui An open-source, self-hosted implementation of OpenAI's ChatGPT Code Interpreter. Users chat with GPT-3.5/GPT-4 models that generate and exe… | 21 | 3536 | maintenance |
| melandlabs/openloomi OpenLoomi is an open-source desktop AI coworker ('Attention Agent') that connects your work tools (Slack, Gmail, Telegram, WhatsApp, etc.),… | 78 | 1037 | active |
| Goekdeniz-Guelmez/Local-NotebookLM A local, open-source alternative to Google's NotebookLM that converts PDF documents into audio content like podcasts, summaries, and interv… | 68 | 1037 | active |
| Nathan-code-development/AIApplication A cross-platform mobile chat application built with .NET MAUI in C# that lets users converse with multiple AI models including DeepSeek, Do… | 57 | 1037 | active |
| kuleshov-group/bd3lms BD3-LMs is a research implementation of Block Discrete Denoising Diffusion Language Models that interpolate between autoregressive and diff… | 31 | 1037 | active |
| tensorflow/hub TensorFlow Hub is a Python library for reusing parts of trained TensorFlow models (SavedModels) for transfer learning, wrapping them as Ker… | 23 | 3530 | maintenance |
| susiai/susi_chat A chat interface for communicating with a locally hosted LLM (via llama.cpp) through a terminal console, a browser-based console, or a voic… | 57 | 1036 | active |
| darrencxl0301/StageRAG StageRAG is a Python framework/blueprint for building production-ready RAG applications with switchable 3-step (Speed) and 4-step (Precisio… | 35 | 1036 | active |
| m-damien/VisualStoryWriting A web application that automatically visualizes a story's chronology, characters, and their movements, letting writers edit the story by ma… | 29 | 1036 | active |
| beizhu-1209/AIHelms AIHelms is a self-hosted enterprise AI resource governance platform that provides a unified AI gateway for managing models from OpenAI, Azu… | 79 | 1035 | active |
| yongliang-wu/DFT DFT (Dynamic Fine-Tuning) is the official implementation of an ICLR 2026 paper that improves Supervised Fine-Tuning of LLMs by dynamically … | 58 | 1035 | active |
| walter-grace/mac-code A free, local coding agent for Apple Silicon Macs that runs large quantized LLMs (e.g., Qwen 35B) via llama.cpp, using techniques like flas… | 46 | 1035 | active |
| wxywb/history_rag A Chinese history question-answering application built with RAG (retrieval-augmented generation) over a corpus of Chinese historical texts,… | 27 | 1035 | active |
| adrida/tracer TRACER is a Python library that learns a routing policy from LLM classification traces, fitting a lightweight traditional ML surrogate to h… | 75 | 1033 | active |