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 |
|---|---|---|---|
| 1rgs/claude-code-proxy A Python proxy server that translates Anthropic API requests so Anthropic clients like Claude Code can run against OpenAI, Gemini, or Anthr… | 56 | 3753 | active |
| zou-group/textgrad TextGrad is a Python framework that implements automatic 'differentiation' via text, using LLM-generated natural language feedback as gradi… | 26 | 3750 | active |
| google-antigravity/antigravity-sdk-python A Python SDK for building AI agents powered by Google Antigravity and Gemini, abstracting the agentic loop behind a stateful, secure infras… | 59 | 3744 | active |
| shobrook/adrenaline Adrenaline is an AI-powered assistant that answers technical questions about programming concepts, GitHub repositories, documentation, and … | 32 | 3741 | active |
| foryourhealth111-pixel/Vibe-Skills VibeSkills is a general-purpose Skill that automatically routes locally installed Skills and orchestrates multi-step harness workflows for … | 83 | 3729 | active |
| OvidijusParsiunas/deep-chat Deep Chat is a fully customizable, framework-agnostic AI chatbot web component that can be added to any website with one line of code. It s… | 90 | 3722 | active |
| PaddlePaddle/FastDeploy FastDeploy is a high-performance inference and deployment toolkit for large language models and vision-language models built on PaddlePaddl… | 82 | 3719 | active |
| llm-workflow-engine/llm-workflow-engine LLM Workflow Engine (LWE) is a power CLI and workflow manager for interacting with LLMs like ChatGPT/GPT-4 from the terminal. It supports m… | 86 | 3715 | active |
| strukto-ai/mirage Mirage is a unified virtual filesystem for AI agents that mounts services like S3, Google Drive, Slack, Gmail, Postgres, and Redis side-by-… | 82 | 3715 | active |
| morphik-org/morphik-core Morphik Core is an open-source, source-available multimodal retrieval engine for building RAG applications over unstructured data like PDFs… | 65 | 3711 | active |
| memodb-io/Acontext Acontext is an open-source memory layer for AI agents that captures learnings from agent runs and stores them as human-readable Markdown sk… | 65 | 3696 | active |
| Butterbase Butterbase is an open-source, AI-native backend-as-a-service platform built on Postgres, providing auth, storage, serverless functions, an … | 59 | 3687 | active |
| Deepractice/PromptX PromptX is an AI Agent Context Platform built on the Model Context Protocol (MCP) that injects professional AI roles, a cognitive memory sy… | 66 | 3686 | active |
| Stability-AI/StableLM StableLM is Stability AI's repository of open-weight decoder-only transformer language models, including the 3B-parameter StableLM-3B-4E1T … | 30 | 15671 | maintenance |
| Letta Code Letta is a platform for building stateful AI agents with persistent memory that can learn and improve over time. It provides a CLI, server,… | 81 | 3669 | active |
| NVIDIA/skills A catalog of NVIDIA-verified Agent Skills — portable instruction sets that teach AI coding agents like Claude Code and Codex how to use NVI… | 61 | 3668 | active |
| PublicAffairs/openai-gemini A serverless proxy that translates OpenAI API requests into Google Gemini API calls, letting any OpenAI-only tool use Gemini's free tier. I… | 53 | 3664 | active |
| hamed-elfayome/Claude-Usage-Tracker A native macOS menu bar application built with Swift/SwiftUI that monitors Claude AI usage limits in real time, including 5-hour session wi… | 79 | 3658 | active |
| laravel/boost Laravel Boost is an official MCP (Model Context Protocol) server that gives AI coding agents like Claude Code and Cursor deep insight into … | 82 | 3655 | active |
| CopilotC-Nvim/CopilotChat.nvim A Neovim plugin that brings GitHub Copilot Chat capabilities directly into the editor, supporting multiple AI models including GPT-4o, Clau… | 71 | 3652 | active |
| Yue-Yang/ChatGPT-Siri A set of Apple Shortcuts that connect Siri to the ChatGPT API, turning Siri into an AI chat assistant on iPhone, iPad, Mac, HomePod, and Ca… | 69 | 3650 | active |
| LangChain A lightweight Python library that adapts Anthropic Model Context Protocol (MCP) tools into LangChain/LangGraph-compatible tools. It provide… | 10 | 3650 | active |
| zai-org/ChatGLM2-6B ChatGLM2-6B is an open-source bilingual (Chinese-English) 6B-parameter conversational large language model built on the GLM architecture. I… | 29 | 15505 | maintenance |
| mit-han-lab/llm-awq AWQ is a Python library implementing Activation-aware Weight Quantization for compressing large language models to low-bit (INT3/4) weights… | 41 | 3638 | active |
| NExT-GPT/NExT-GPT NExT-GPT is an end-to-end any-to-any multimodal large language model that accepts and generates arbitrary combinations of text, image, vide… | 34 | 3638 | active |
| simonlin1212/TradingAgents-astock A Python multi-agent investment research framework for China's A-share market, deeply forked from TauricResearch/TradingAgents. It runs 7 s… | 80 | 3635 | active |
| bytebase/dbhub DBHub is a minimal, token-efficient MCP server that lets AI clients like Claude, Cursor, and VS Code connect to and explore PostgreSQL, MyS… | 86 | 3621 | active |
| AIDotNet/OpenDeepWiki OpenDeepWiki is an AI-driven platform that turns Git repositories, ZIP archives, and local directories into searchable, structured document… | 85 | 3615 | active |
| openai/openai-realtime-console A React-based example application from OpenAI for inspecting, building, and debugging with the Realtime API over WebRTC. It serves as a min… | 37 | 3614 | active |
| sligter/LandPPT LandPPT is an AI-powered presentation generation platform that turns a topic or uploaded documents (PDF, Word, Markdown, Excel, PPT) into p… | 79 | 3611 | active |
| nextlevelbuilder/goclaw GoClaw is a multi-tenant AI agent platform and gateway rebuilt from OpenClaw in Go, supporting 20+ LLM providers and 7 messaging channels f… | 70 | 3610 | active |
| HolmesGPT/holmesgpt HolmesGPT is an open-source AI agent (CNCF Sandbox project) that investigates production incidents and finds root causes by querying live o… | 87 | 3604 | active |
| truera/trulens TruLens is a Python library for evaluating and tracking LLM-based applications and AI agents. It provides OpenTelemetry-native tracing of e… | 99 | 3601 | active |
| deta/surf Deta Surf is an open-source, local-first AI notebook for macOS, Windows, and Linux that lets users organize files, PDFs, websites, and YouT… | 72 | 3600 | active |
| NVlabs/Eagle Eagle is NVIDIA's family of frontier vision-language models (Eagle, Eagle 2, Eagle 2.5) built with data-centric training strategies, plus L… | 61 | 3599 | active |
| HanaokaYuzu/Gemini-API A reverse-engineered asynchronous Python client library for Google's Gemini web app (formerly Bard), published as gemini-webapi on PyPI. It… | 90 | 3597 | active |
| RUC-NLPIR/FlashRAG FlashRAG is a modular Python toolkit for reproducing and developing Retrieval-Augmented Generation (RAG) research, bundling 36 pre-processe… | 88 | 3590 | active |
| grafana/mcp-grafana A Model Context Protocol (MCP) server for Grafana that exposes Grafana instances and their ecosystem to AI assistants like Claude Desktop a… | 85 | 3584 | active |
| SamurAIGPT/llm-wiki-agent A coding-agent skill that turns source documents into a self-maintaining, interlinked markdown wiki. You drop files into a raw/ folder and … | 73 | 3582 | active |
| zhaoyingjun/chatbot A Chinese chatbot project that trains conversational models (Seq2Seq and GPT-style, including small SLM variants) on custom corpora with lo… | 49 | 3582 | active |
| ChatGPT Java SDK An unofficial Java SDK that wraps OpenAI's ChatGPT API for GPT-3.5, GPT-4, GPT-4o, and GPT-5 models, published on Maven Central with a flue… | 44 | 3579 | active |
| NVIDIA/TransformerEngine Transformer Engine is an NVIDIA library for accelerating Transformer model training and inference on NVIDIA GPUs using low-precision format… | 99 | 3576 | active |
| Dailin521/codex-provider-sync A tool that synchronizes Codex session provider metadata across rollout files and SQLite state so historical sessions remain visible after … | 81 | 3576 | active |
| pathwaycom/bdh BDH (Dragon Hatchling) is a biologically inspired large language model architecture that bridges deep learning and neuroscience, implemente… | 51 | 3571 | active |
| liu-ziting/what-to-eat An AI-powered recipe generation web platform built with Vue 3 and TypeScript that creates recipes across China's eight major cuisines plus … | 42 | 3567 | active |
| CosmosShadow/gptpdf A small Python library that parses PDF files into Markdown using a vision-capable LLM such as GPT-4o. It uses PyMuPDF to detect non-text ar… | 28 | 3559 | active |
| Unity Catalog Unity Catalog is an open-source, multimodal data and AI catalog that provides a unified metadata and governance layer for tables, files, fu… | 88 | 3554 | active |
| SeemSeam/claude_codex_bridge CCB is a lightweight multi-agent terminal UI (TUI) that orchestrates multiple AI coding CLI agents (Codex, Claude, Gemini, Kimi, Qwen, Curs… | 79 | 3553 | active |
| SkyworkAI/DeepResearchAgent DeepResearchAgent is a Python framework for hierarchical multi-agent systems that combines a top-level planning agent with specialized lowe… | 63 | 3552 | active |
| agentscope-ai/ReMe ReMe is a Python memory management kit for AI agents that stores durable memory as ordinary Markdown files with frontmatter and wikilinks. … | 85 | 3551 | active |
| rashadphz/farfalle Farfalle is an open-source, self-hosted AI-powered search engine that works like Perplexity, answering questions with cited web search resu… | 25 | 3543 | active |
| Mesh-LLM/mesh-llm Mesh LLM is a Rust-based distributed LLM inference runtime that pools GPUs and memory across machines into a single OpenAI-compatible API. … | 79 | 3540 | active |
| rlaope/oh-my-hermes oh-my-hermes (OMH) is an installable enhancement layer for the Hermes Agent that adds planning, research, coding handoffs, agentic memory, … | 82 | 3535 | active |
| fnnx-ai/scikit-llm Scikit-LLM is a Python library that integrates large language models like GPT into scikit-learn workflows as estimators. It enables tasks s… | 72 | 3533 | active |
| ascending-llc/jarvis-registry Jarvis Registry is an open-source, enterprise-grade MCP and A2A agent gateway and workflow orchestration platform that gives AI copilots an… | 84 | 3531 | active |
| EverMind-AI/MSA MSA (Memory Sparse Attention) is a Python framework for end-to-end trainable sparse latent-memory attention that scales LLM context to 100M… | 50 | 3520 | active |
| google-ai-edge/LiteRT LiteRT is Google's successor to TensorFlow Lite, an on-device runtime for high-performance ML and GenAI inference on edge platforms. It pro… | 86 | 3514 | active |
| sugarforever/chat-ollama ChatOllama is an open-source, self-hosted AI chatbot platform built with Nuxt 3 that supports multiple LLM providers (OpenAI, Anthropic, Ge… | 89 | 3512 | active |
| PKU-YuanGroup/Video-LLaVA Video-LLaVA is a large vision-language model that aligns image and video representations into a unified visual space before projection into… | 28 | 3504 | active |
| huggingface/optimum Optimum is a Hugging Face library that extends Transformers, Diffusers, timm, and Sentence Transformers with hardware-specific optimization… | 91 | 3503 | active |
| openai/openai-go The official Go client library for the OpenAI REST API, providing typed access to models, the Responses API, conversations, and other OpenA… | 87 | 3501 | active |
| sentient-agi/OML-1.0-Fingerprinting A Python library for embedding secret cryptographic fingerprints into LLMs via fine-tuning, so model owners can prove ownership and detect … | 13 | 3493 | active |
| JusticeRage/Gepetto Gepetto is an IDA Pro plugin that queries large language models (OpenAI, Anthropic, Gemini, Ollama, and others) to explain decompiled funct… | 73 | 3487 | active |
| Clowder AI Clowder AI is a TypeScript framework for building teams of AI agents that collaborate across multiple models like Claude, GPT, and Gemini i… | 81 | 3486 | active |
| RunMaestro/Maestro Maestro is a cross-platform desktop application for orchestrating fleets of AI coding agents such as Claude Code, Codex, OpenCode, Factory … | 80 | 3485 | active |
| superagent-ai/grok-cli An open-source terminal-based coding agent that connects to xAI's Grok API, built with TypeScript and Bun. It offers an interactive OpenTUI… | 71 | 3484 | active |
| fauxpilot/fauxpilot FauxPilot is a self-hosted, open-source alternative to the GitHub Copilot code completion server. It serves SalesForce CodeGen models via N… | 32 | 14676 | maintenance |
| Docta-ai/docta Docta is a Python library for data-centric AI that diagnoses and fixes issues in datasets such as label errors, noise, and misannotations. … | 66 | 3479 | active |
| any4ai/AnyCrawl AnyCrawl is a Node.js/TypeScript web crawler and scraping service that converts websites into LLM-ready markdown/JSON data and extracts str… | 85 | 3477 | active |
| Haleclipse/CCometixLine A high-performance statusline tool for Claude Code written in Rust, displaying model, directory, Git branch status, and context window usag… | 58 | 3474 | active |
| imraywang/wewrite WeWrite is a Python-based AI agent skill that automates the full WeChat Official Account content pipeline: topic selection from trending ne… | 77 | 3473 | active |
| MiniMax AI Platform Official repository for MiniMax-Text-01 and MiniMax-VL-01, open-weight large language and vision-language models built on a linear attentio… | 31 | 3469 | active |
| Linly Digital Human System Linly-Talker is a Python-based digital avatar conversational system that combines LLMs (Linly, Qwen, Gemini), speech recognition (Whisper, … | 44 | 3468 | active |
| Toad Toad is a terminal user interface (TUI) that provides a unified interface for running multiple AI coding agents such as Claude Code, Gemini… | 68 | 3467 | active |
| n3d1117/chatgpt-telegram-bot A self-hosted Telegram bot written in Python that integrates with OpenAI's official ChatGPT, DALL·E, and Whisper APIs to answer questions, … | 30 | 3464 | active |
| aiming-lab/MetaClaw MetaClaw is a continual meta-learning framework that lets an LLM agent evolve from real conversations, combining skill synthesis from failu… | 63 | 3460 | active |
| Mirix-AI/MIRIX MIRIX is a self-hosted multi-agent personal assistant that captures on-screen activity and conversation to build structured long-term memor… | 71 | 3456 | active |
| modelscope/evalscope EvalScope is a Python framework from the ModelScope community for evaluating large language models, vision-language models, embedding model… | 91 | 3454 | active |
| lynote-ai/humanize-text An open-source Python toolkit for making AI-generated drafts read more naturally, offering four documented humanization approaches plus a p… | 67 | 3453 | active |
| entropy-research/Devon Devon is an open-source AI pair programmer that acts as an autonomous software engineering agent, installable via pipx (backend) and npm (U… | 32 | 3450 | active |
| i-am-bee/beeai-framework BeeAI Framework is an open-source, Linux Foundation-hosted framework for building production-grade multi-agent AI systems in Python and Typ… | 86 | 3436 | active |
| NotebookLM MCP An MCP server and Claude Code skill that lets AI coding agents chat directly with Google NotebookLM notebooks, returning source-grounded, c… | 10 | 3432 | active |
| alibaba/ROLL ROLL is an open-source reinforcement learning library from Alibaba for training large language models at scale, supporting algorithms like … | 82 | 3429 | active |
| lmnr-ai/lmnr Laminar is an open-source, OpenTelemetry-native observability platform purpose-built for AI agents, offering tracing, plain-language failur… | 91 | 3422 | active |
| Universal Commerce Protocol The Universal Commerce Protocol (UCP) is an open standard and specification for interoperable, agentic commerce, defining capabilities like… | 77 | 3420 | active |
| superlinked/sie SIE (Superlinked Inference Engine) is an open-source, self-hosted inference server and production cluster that serves 100+ open models (emb… | 95 | 3414 | active |
| OpenBiliClaw OpenBiliClaw is a local-first, open-source AI content discovery agent that builds a private user profile from cross-platform usage, feedbac… | 78 | 3409 | active |
| miaoxworld/OpenClawInstaller A shell-based one-click installer and configuration tool for deploying OpenClaw (ClawdBot), a self-hosted personal AI assistant gateway. It… | 45 | 3409 | active |
| mnemosyne-oss/mnemosyne Mnemosyne is a local-first, SQLite-backed memory layer for AI agents, exposing remember/recall APIs via a Python SDK and 30+ tools over MCP… | 82 | 3407 | active |
| chatgpt-java An unofficial Java SDK for the OpenAI API covering all official endpoints including chat completions (GPT-3.5/GPT-4), DALL-E image generati… | 22 | 3406 | active |
| ding113/claude-code-hub CC Hub is a self-hosted AI API proxy and gateway service for Claude Code, Codex, and other OpenAI/Claude-compatible APIs, built with Next.j… | 83 | 3402 | active |
| HKUDS/VideoRAG VideoRAG is a retrieval-augmented generation framework for chatting with and understanding extremely long-context videos, using a dual-chan… | 50 | 3401 | active |
| NovaSky-AI/SkyThought SkyThought is the open-source repository behind Sky-T1, a family of reasoning language models trained for under $450, including training sc… | 22 | 3401 | active |
| notdog1998/yourself-skill A Claude Code skill that builds a digital persona of yourself from chat logs, diaries, photos, and self-descriptions, structured as a Self … | 45 | 3398 | active |
| taylorwilsdon/google_workspace_mcp A comprehensive Model Context Protocol (MCP) server and CLI tool that gives AI assistants like Claude and ChatGPT full natural-language con… | 83 | 3396 | active |
| automazeio/vibeproxy VibeProxy is a native macOS menu bar app that proxies AI coding tools' API requests through your existing Claude Code, ChatGPT, Gemini, Kim… | 81 | 3393 | active |
| Intelligent-Internet/ii-agent II-Agent is an open-source (Apache-2.0) AI agent framework for building and deploying intelligent assistants that execute complex multi-ste… | 62 | 3391 | active |
| huggingface/datatrove DataTrove is a Python library from Hugging Face for processing, filtering, and deduplicating large-scale text data through customizable pip… | 87 | 3390 | active |
| pashpashpash/vault-ai OP Vault is a self-hosted application combining a Go backend with a React frontend that lets users upload documents (PDF, txt, epub) into a… | 40 | 3389 | active |
| crystaldba/postgres-mcp Postgres MCP Pro is an open-source Model Context Protocol (MCP) server that gives AI agents and developers safe, configurable read/write ac… | 63 | 3388 | active |