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 |
|---|---|---|---|
| ridgerchu/matmulfreellm A Python implementation of MatMul-Free LM, a language model architecture that eliminates matrix multiplication operations using ternary wei… | 76 | 3093 | active |
| robert-mcdermott/ai-knowledge-graph A Python CLI tool that uses an LLM to extract Subject-Predicate-Object triplets from unstructured text documents and renders them as an int… | 84 | 3088 | active |
| Project-N-E-K-O/N.E.K.O Project N.E.K.O. is an open-source AI companion application — a proactive catgirl-style AI that lives on your desktop, initiates interactio… | 84 | 3087 | active |
| Nutlope/self.so Self.so is an open-source web application that turns a resume or LinkedIn profile into a professional personal website in one click. It use… | 62 | 3085 | active |
| containers/ramalama RamaLama is a Python CLI tool that simplifies serving and running AI/LLM models locally by leveraging OCI containers (Podman/Docker). It au… | 85 | 3079 | active |
| dwgx/WindsurfAPI A zero-dependency Node.js reverse proxy that exposes Windsurf/Devin Desktop's 100+ cloud AI models (Claude, GPT, Gemini, DeepSeek, Kimi, GL… | 77 | 3079 | active |
| MemMachine/MemMachine MemMachine is an open-source memory layer for AI agents and LLM applications, providing episodic, profile, and working memory that persists… | 85 | 3076 | active |
| realiti4/claude-swap A Python CLI/TUI tool for switching between multiple Claude Code accounts without logging out, with automatic rotation before rate limits a… | 81 | 3061 | active |
| vanzan01/cursor-memory-bank A documentation-driven framework for the Cursor editor that provides persistent memory and a structured development workflow through six co… | 56 | 3060 | active |
| MiniMax-AI/Mini-Agent A minimal yet professional Python demo project showcasing best practices for building a single LLM agent on the MiniMax M2.5 model via an A… | 44 | 3060 | active |
| hegelai/prompttools PromptTools is an open-source Python library for testing, experimenting with, and evaluating prompts, LLMs (OpenAI, Anthropic, LLaMA, etc.)… | 46 | 3056 | active |
| UKGovernmentBEIS/inspect_ai Inspect is an open-source Python framework from the UK AI Security Institute for running large language model evaluations, with composable … | 95 | 3054 | active |
| vectorize-io/self-driving-agents A collection of 179 ready-to-use, self-learning AI agent definitions organized into 13 departments (design, engineering, marketing, sales, … | 74 | 3047 | active |
| swirlai/swirl-search SWIRL is an open-source federated AI search and RAG platform that queries enterprise apps and data sources live, re-ranks results with a hy… | 92 | 3046 | active |
| nerding-io/n8n-nodes-mcp An n8n community node that lets workflows connect to Model Context Protocol (MCP) servers to access resources, execute tools, and use promp… | 52 | 3043 | active |
| Natively-AI-assistant/natively-cluely-ai-assistant Natively is a free, source-available desktop AI meeting assistant and interview copilot that provides real-time transcription, AI-generated… | 83 | 3036 | active |
| ianarawjo/ChainForge ChainForge is an open-source visual programming environment for battle-testing prompts to LLMs, built on ReactFlow and Flask. It lets users… | 92 | 3035 | active |
| oxylabs/perplexity-scraper A repository of code examples and documentation for Oxylabs' Perplexity Scraper API, which sends prompts to Perplexity and returns AI-gener… | 61 | 3029 | active |
| x-dr/chatgptProxyAPI A self-deployable reverse proxy for the OpenAI API built on Cloudflare Workers and Cloudflare Pages, letting users replace api.openai.com w… | 10 | 3029 | active |
| dw-dengwei/daily-arXiv-ai-enhanced A tool that automatically crawls daily arXiv papers and summarizes them using LLMs like DeepSeek, publishing the results as a browsable sit… | 62 | 3027 | active |
| luminal-ai/luminal Luminal is a high-performance general-purpose ML inference compiler written in Rust that lowers models to a minimal 15-op dataflow IR and c… | 77 | 3026 | active |
| Simon-He95/markstream-vue A family of streaming Markdown renderer components for AI chat and LLM token-stream UIs, with markstream-vue as the stable Vue 3/Nuxt/ViteP… | 81 | 3024 | stable |
| betalgo/openai A community .NET library (Betalgo.Ranul.OpenAI) for accessing OpenAI's API, including ChatGPT, DALL-E, Whisper, and Azure OpenAI. It lets .… | 63 | 3021 | active |
| TheBlewish/Automated-AI-Web-Researcher-Ollama A Python application that turns a locally-run Ollama LLM into an automated web research assistant. Given a single query, it generates focus… | 64 | 3017 | active |
| deepseek-ai/DualPipe DualPipe is a Python library implementing a bidirectional pipeline parallelism algorithm that overlaps forward and backward computation wit… | 45 | 3017 | active |
| Eladlev/AutoPrompt AutoPrompt is a Python framework for optimizing LLM prompts using Intent-based Prompt Calibration. It iteratively generates challenging edg… | 39 | 3017 | active |
| thu-pacman/chitu Chitu (赤兔) is a high-performance inference framework for large language models, positioned as a production-grade LLM serving engine. It sup… | 82 | 3009 | active |
| qxcnm/Codex-Manager CodexManager is a local desktop application plus service process for managing multiple Codex CLI accounts, API keys, and usage quotas in on… | 79 | 3009 | active |
| leigest519/OpenGame OpenGame is an open-source agentic framework for end-to-end web game creation from a single prompt, built around a reusable 'Game Skill' sy… | 56 | 3009 | active |
| vercel-labs/opensrc opensrc is a Rust-based CLI that fetches and caches the source code of packages from npm, PyPI, crates.io, and GitHub so AI coding agents c… | 75 | 3008 | active |
| leigest519/ScreenCoder ScreenCoder is a UI-to-code generation system that converts screenshots or design mockups into clean, editable HTML/CSS using a modular mul… | 61 | 3006 | active |
| confident-ai/deepteam DeepTeam is an open-source Python framework for red teaming LLM systems, AI agents, RAG pipelines, and chatbots. It simulates adversarial a… | 65 | 3005 | active |
| J-Space Cognition Suite A model-agnostic inference-time control suite packaged as an installable AI agent Skill (SKILL.md with modules, references, and Python veri… | 77 | 3002 | active |
| pytorch/ao TorchAO is a PyTorch-native library for model optimization through quantization and sparsity. It supports quantizing weights, gradients, op… | 87 | 3001 | active |
| hi-godot/godot-ai A Godot engine plugin paired with an MCP server that connects AI assistants like Claude Code and Codex to a live Godot editor. It exposes ~… | 77 | 3001 | active |
| Dicklesworthstone/llm_aided_ocr A Python tool that converts scanned PDFs to text via Tesseract OCR, then uses LLMs (local or API-based like OpenAI/Anthropic) to correct OC… | 68 | 3001 | active |
| signerless/llm-checker A Node.js CLI tool that scans your hardware (GPU, VRAM, CPU, memory) and recommends which LLM or small language models you can run locally,… | 80 | 2998 | active |
| vLLM vllm-ascend is a community-maintained hardware plugin that enables vLLM to run large language model inference on Huawei Ascend NPUs. It imp… | 83 | 2996 | active |
| ulab-uiuc/LLMRouter LLMRouter is an open-source Python library that intelligently routes queries to the most suitable LLM based on task complexity, cost, and p… | 62 | 2995 | active |
| Flow2API Flow2API is a self-hosted Python/FastAPI service that exposes an OpenAI- and Gemini-compatible API on top of Google Flow (VideoFX/ImageFX) … | 60 | 2989 | active |
| CLIP Interrogator A Python library that combines OpenAI's CLIP and Salesforce's BLIP to reverse-engineer text prompts from images, optimized for use with tex… | 23 | 2986 | stable |
| OpenMOSS/MOSS MOSS is an open-source tool-augmented conversational large language model from Fudan University, released with base models, SFT models, plu… | 72 | 12253 | maintenance |
| omnara-ai/omnara Omnara is an open-source platform for running managed, durable AI agents, handling execution and state while you bring your own models, too… | 82 | 2984 | active |
| togethercomputer/MoA Together AI's Mixture-of-Agents (MoA) is a Python implementation of a layered LLM architecture where multiple open-source models answer pro… | 25 | 2982 | active |
| michaelshimeles/ralphy Ralphy is a CLI tool (npm package and bash script) that runs AI coding agents like Claude Code, Codex, OpenCode, Cursor, Qwen-Code, and Fac… | 42 | 2979 | active |
| NVIDIA/NeMo-Retriever NVIDIA's scalable document content and metadata extraction library (also known as NVIDIA Ingest) that splits documents, classifies and extr… | 82 | 2978 | active |
| codigoencasa/builderbot BuilderBot is an open-source TypeScript framework for building WhatsApp (and Telegram) chatbots with keyword-driven conversation flows, plu… | 98 | 2975 | active |
| smol-ai/developer smol developer is a 'junior developer' AI agent that scaffolds an entire codebase from a product spec, and can be embedded as a library to … | 30 | 12188 | maintenance |
| leo-lilinxiao/codex-autoresearch A Codex skill that runs a self-directed iterative loop: it makes one focused change, measures it against a target metric, keeps improvement… | 73 | 2968 | active |
| michaelfeil/infinity Infinity is a high-throughput, low-latency serving engine that exposes text-embedding, reranking, CLIP, CLAP and ColPali models via an Open… | 96 | 2966 | active |
| huggingface/tau Tau is a small, readable terminal coding agent written in Python, inspired by Pi, that can read files, edit code, run commands, and maintai… | 81 | 2966 | active |
| ax-llm/ax Ax is a TypeScript-first LLM programming framework implementing the DSPy model, providing typed signatures, agents, flows, and optimizers l… | 93 | 2961 | active |
| li-plus/chatglm.cpp A pure C++ implementation of ChatGLM-6B, ChatGLM2-6B, ChatGLM3, and GLM-4(V) based on ggml, enabling memory-efficient real-time chatting on… | 21 | 2957 | active |
| OpenGAP OpenGAP (Git Agent Protocol) is a framework-agnostic, git-native open standard for defining AI agents as repository files, with a reference… | 70 | 2955 | active |
| MacPaw/OpenAI A community-maintained Swift package that wraps the OpenAI public API, supporting chat completions, responses, function calling, MCP tools,… | 100 | 2952 | active |
| turboderp/exllama ExLlama is a standalone Python/C++/CUDA implementation of the Llama architecture optimized for running 4-bit GPTQ quantized weights on mode… | 30 | 2947 | active |
| Luce-Org/lucebox Lucebox is an open-source LLM inference engine written in C++ with custom CUDA/HIP kernels, focused on speculative decoding and speculative… | 60 | 2941 | active |
| memodb-io/memobase Memobase is a user profile-based long-term memory system for LLM applications, providing per-user profiles and event timelines that chatbot… | 47 | 2936 | active |
| qingchencloud/clawpanel ClawPanel is a cross-platform desktop and web control panel for managing multiple AI agent runtimes (OpenClaw, Hermes Agent, DeepSeek Harne… | 79 | 2934 | active |
| OpenMind/OM1 OM1 is a modular AI runtime and hardware abstraction layer for building multimodal AI agents that run on physical robots and in simulators.… | 77 | 2933 | active |
| zjunlp/EasyEdit EasyEdit is an easy-to-use knowledge editing framework for large language models, supporting methods that modify model parameters or steer … | 74 | 2929 | active |
| ErlichLiu/DeepClaude DeepClaude is a self-hostable service that chains DeepSeek R1's reasoning output with Claude Sonnet or Gemini models to produce a combined … | 48 | 2928 | active |
| InternLM/InternLM-XComposer InternLM-XComposer is a family of large vision-language models from the InternLM team, including XComposer2.5 for long-context multimodal u… | 35 | 2927 | active |
| langchain-ai/social-media-agent A TypeScript AI agent built on LangGraph that takes a URL, scrapes its content, and generates Twitter and LinkedIn posts using LLMs. It inc… | 67 | 2920 | active |
| decoderesearch/circuit-tracer A Python library for circuit tracing and attribution graphs in language model interpretability, based on cross-layer MLP transcoders. It co… | 77 | 2918 | active |
| JunChenMoCode/ChatGPT_JCM A Vue2 + ElementUI web management interface that aggregates OpenAI API endpoints (models, chat, images, audio, fine-tuning, files) into a g… | 22 | 2917 | active |
| eric-mitchell/direct-preference-optimization A reference implementation of Direct Preference Optimization (DPO) for training language models from human preference data, built on Huggin… | 29 | 2916 | stable |
| rilldata/rill Rill is an open-source business intelligence tool that combines a local developer application and cloud platform for building interactive d… | 93 | 2915 | active |
| supercorp-ai/supergateway Supergateway is a CLI tool that runs MCP stdio-based servers over SSE, WebSockets, or Streamable HTTP, and vice versa, with a single comman… | 89 | 2905 | active |
| MartialBE/one-hub One Hub is a self-hosted OpenAI-compatible API management and distribution system forked from songquanpeng/one-api, written in Go. It aggre… | 62 | 2896 | active |
| jnsahaj/lumen Lumen is a fast terminal-based git diff viewer and code review TUI written in Rust, shipped as a single static binary. It offers side-by-si… | 83 | 2894 | active |
| CCS CCS is a TypeScript CLI tool that manages multiple AI provider profiles and accounts for Claude Code and compatible CLIs, switching between… | 78 | 2892 | active |
| KellerJordan/Muon Muon is a PyTorch optimizer for the hidden layers of neural networks, based on orthogonalized momentum updates via Newton-Schulz iteration.… | 56 | 2887 | active |
| GCWing/BitFun BitFun is a cross-platform desktop AI agent application with a high-performance Rust agent runtime that writes code, produces documents, an… | 84 | 2876 | active |
| Y-Research-SBU/QuantHarness QuantHarness is a multi-agent LLM framework for high-frequency trading analysis, built on LangChain and LangGraph. Specialized agents compu… | 59 | 2874 | active |
| moltis-org/moltis Moltis is a secure, self-hosted personal AI agent server written in Rust that ships as a single binary with sandboxed execution, multi-prov… | 75 | 2867 | active |
| Prism-Shadow/penguin-harness PenguinHarness is an open-source, local-first multi-agent application development platform that automates building, optimizing, and deployi… | 81 | 2864 | active |
| Model Context Protocol (MCP) Official specification and TypeScript SDK for the MCP Apps protocol, a standard for building interactive UIs (charts, forms, dashboards) th… | 80 | 2862 | active |
| VRSEN/OpenSwarm OpenSwarm is an open-source multi-agent system built on Agency Swarm that turns a single terminal prompt into complete deliverables like sl… | 71 | 2861 | active |
| anysphere/priompt Priompt is a JSX-based prompt design library for building LLM prompts with React-like components. It uses priority levels to decide which p… | 47 | 2856 | active |
| songguoxs/seedance-prompt-skill A Claude Code custom skill that turns Claude into an AI video prompt engineer for ByteDance's Seedance 2.0 video generation platform. It co… | 42 | 2849 | active |
| huggingface/nanotron Nanotron is a minimalistic Python library from Hugging Face for pretraining large language models with 3D parallelism (data, tensor, and pi… | 63 | 2843 | active |
| rednote-machine-learning/RedKnot RedKnot is a long-context LLM inference acceleration library built on SGLang, using head-classified KV reuse, offline KV storage with RoPE … | 57 | 2840 | active |
| spcl/graph-of-thoughts Official Python implementation of the Graph of Thoughts (GoT) framework from ETH Zurich, which models complex problem-solving as a Graph of… | 48 | 2840 | active |
| AdapterHub Adapters is a Python add-on library for HuggingFace Transformers that integrates 10+ parameter-efficient fine-tuning methods (bottleneck ad… | 74 | 2831 | active |
| sahibzada-allahyar/YC-Killer A collection of open-source, enterprise-grade AI agents intended as free alternatives to commercial Y Combinator startups. It includes a de… | 60 | 2828 | active |
| OpenDCAI/DataFlex DataFlex is a data-centric training framework built on LLaMA-Factory that dynamically schedules LLM training data during optimization. It p… | 63 | 2824 | active |
| cocoindex-io/cocoindex-code A lightweight AST-based semantic code search CLI built on the CocoIndex Rust data transformation engine, with tree-sitter parsing and embed… | 82 | 2814 | active |
| teaql/teaql-agent-kit TeaQL Agent Kit is a model-mediated harness for coding agents that inserts an inspectable, executable domain model (KSML) between requireme… | 83 | 2813 | active |
| trustgraph-ai/trustgraph TrustGraph is an open-source context interoperability layer that builds unified semantic context layers using hypergraphs, knowledge graphs… | 78 | 2808 | active |
| mll-lab-nu/RAGEN RAGEN is a Python framework for training reasoning LLM agents with multi-turn reinforcement learning using the StarPO algorithm. It also pr… | 62 | 2803 | active |
| facebookresearch/HyperAgents A research framework from Meta AI implementing self-referential, self-improving LLM agents that can optimize their own code for arbitrary c… | 54 | 2803 | active |
| fuergaosi233/claude-code-proxy A Python proxy server that translates Claude API requests (/v1/messages) into OpenAI-compatible API calls, letting the Claude Code CLI work… | 47 | 2799 | active |
| OpenDCAI/Paper2Any Paper2Any is an open-source Python application that turns research papers, text, or topics into editable research figures, technical route … | 59 | 2797 | active |
| jgravelle/jcodemunch-mcp jCodeMunch is an MCP server that indexes codebases with tree-sitter AST parsing and serves symbol-level code retrieval to AI agents, cuttin… | 79 | 2795 | active |
| Mega4alik/ollm oLLM is a lightweight Python library for large-context LLM inference built on Hugging Face Transformers and PyTorch. It offloads weights an… | 57 | 2795 | active |
| RichardAtCT/claude-code-telegram A self-hosted Telegram bot that bridges Telegram to the Claude Code CLI, letting developers chat with an AI assistant about their codebases… | 84 | 2794 | active |
| openlit/openlit OpenLIT is an open-source AI engineering platform providing OpenTelemetry-native LLM observability, evaluations, guardrails, prompt managem… | 86 | 2792 | active |
| Vali-98/ChatterUI ChatterUI is a native mobile frontend for running large language models on-device via llama.cpp or connecting to commercial and open-source… | 89 | 2790 | active |
| vava-nessa/free-coding-models A CLI tool that tracks a large catalog of free coding LLM models across 20+ providers in real time, benchmarking their speed and stability.… | 77 | 2790 | active |