LLMs & GenAI
147 repositories · AI, LLMs & Data
All subcategories in AI, LLMs & Data
Repositories — sorted by stars
| Repository | Stars | Language | Description |
|---|---|---|---|
| Significant-Gravitas/AutoGPT | ⭐ 184.0K | Python | AutoGPT is the vision of accessible AI for everyone, to use and to build on. Our mission is to provide the tools, so that you can focus on what matters. |
| obra/superpowers | ⭐ 177.3K | Shell | An agentic skills framework & software development methodology that works. |
| ollama/ollama | ⭐ 170.6K | Go | Get up and running with Kimi-K2.5, GLM-5, MiniMax, DeepSeek, gpt-oss, Qwen, Gemma and other models. |
| huggingface/transformers | ⭐ 160.2K | Python | 🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training. |
| langgenius/dify | ⭐ 140.0K | TypeScript | Production-ready platform for agentic workflow development. |
| langchain-ai/langchain | ⭐ 135.7K | Python | The agent engineering platform. Available in TypeScript! |
| open-webui/open-webui | ⭐ 135.4K | Python | User-friendly AI Interface (Supports Ollama, OpenAI API, ...) |
| anthropics/skills | ⭐ 127.7K | Python | Public repository for Agent Skills |
| ggml-org/llama.cpp | ⭐ 108.1K | C++ | LLM inference in C/C++ |
| google-gemini/gemini-cli | ⭐ 103.1K | TypeScript | An open-source AI agent that brings the power of Gemini directly into your terminal. |
| openai/whisper | ⭐ 98.8K | Python | Robust Speech Recognition via Large-Scale Weak Supervision |
| hacksider/Deep-Live-Cam | ⭐ 92.6K | Python | real time face swap and one-click video deepfake with only a single image |
| deepseek-ai/DeepSeek-R1 | ⭐ 92.0K | — | |
| browser-use/browser-use | ⭐ 91.9K | Python | 🌐 Make websites accessible for AI agents. Automate tasks online with ease. |
| openai/codex | ⭐ 79.8K | Rust | Lightweight coding agent that runs in your terminal |
| infiniflow/ragflow | ⭐ 79.6K | Python | RAGFlow is a leading open-source Retrieval-Augmented Generation (RAG) engine that fuses cutting-edge RAG with Agent capabilities to create a superior context layer for LLMs |
| nomic-ai/gpt4all | ⭐ 77.4K | C++ | GPT4All: Run Local LLMs on Any Device. Open-source and available for commercial use. |
| PaddlePaddle/PaddleOCR | ⭐ 77.0K | Python | Turn any PDF or image document into structured data for your AI. A powerful, lightweight OCR toolkit that bridges the gap between images/PDFs and LLMs. Supports 100+ languages. |
| CompVis/stable-diffusion | ⭐ 73.0K | Jupyter Notebook | A latent text-to-image diffusion model |
| paperclipai/paperclip | ⭐ 62.4K | TypeScript | Open-source orchestration for zero-human companies |
| gsd-build/get-shit-done | ⭐ 59.7K | JavaScript | A light-weight and powerful meta-prompting, context engineering and spec-driven development system for Claude Code by TÂCHES. |
| meta-llama/llama | ⭐ 59.4K | Python | Inference code for Llama models |
| 666ghj/MiroFish | ⭐ 59.0K | Python | A Simple and Universal Swarm Intelligence Engine, Predicting Anything. 简洁通用的群体智能引擎,预测万物 |
| zylon-ai/private-gpt | ⭐ 57.2K | Python | Interact with your documents using the power of GPT, 100% privately, no data leaks |
| code-yeongyu/oh-my-openagent | ⭐ 55.6K | TypeScript | omo; the best agent harness - previously oh-my-opencode |
| AntonOsika/gpt-engineer | ⭐ 55.2K | Python | CLI platform to experiment with codegen. Precursor to: https://lovable.dev |
| mem0ai/mem0 | ⭐ 54.7K | Python | Universal memory layer for AI Agents |
| upstash/context7 | ⭐ 54.4K | TypeScript | Context7 Platform -- Up-to-date code documentation for LLMs and AI code editors |
| facebookresearch/segment-anything | ⭐ 54.1K | Jupyter Notebook | The repository provides code for running inference with the SegmentAnything Model (SAM), links for downloading the trained model checkpoints, and example notebooks that show how to use the model. |
| run-llama/llama_index | ⭐ 49.1K | Python | LlamaIndex is the leading document agent and OCR platform |
| mudler/LocalAI | ⭐ 46.0K | Go | LocalAI is the open-source AI engine. Run any model - LLMs, vision, voice, image, video - on any hardware. No GPU required. |
| BerriAI/litellm | ⭐ 45.6K | Python | Python SDK, Proxy Server (AI Gateway) to call 100+ LLM APIs in OpenAI (or native) format, with cost tracking, guardrails, loadbalancing and logging. [Bedrock, Azure, OpenAI, VertexAI, Cohere, Anthropic, Sagemaker, HuggingFace, VLLM, NVIDIA NIM] |
| Aider-AI/aider | ⭐ 44.3K | Python | aider is AI pair programming in your terminal |
| badlogic/pi-mono | ⭐ 44.2K | TypeScript | AI agent toolkit: coding agent CLI, unified LLM API, TUI & web UI libraries, Slack bot, vLLM pods |
| aaif-goose/goose | ⭐ 43.7K | Rust | an open source, extensible AI agent that goes beyond code suggestions - install, execute, edit, and test with any LLM |
| HKUDS/nanobot | ⭐ 41.6K | Python | "🐈 nanobot: The Ultra-Lightweight Personal AI Agent" |
| lm-sys/FastChat | ⭐ 39.5K | Python | An open platform for training, serving, and evaluating large language models. Release repo for Vicuna and Chatbot Arena. |
| QuivrHQ/quivr | ⭐ 39.1K | Python | Opiniated RAG for integrating GenAI in your apps 🧠 Focus on your product rather than the RAG. Easy integration in existing products with customisation! Any LLM: GPT4, Groq, Llama. Any Vectorstore: PGVector, Faiss. Any Files. Anyway you want. |
| suno-ai/bark | ⭐ 39.1K | Jupyter Notebook | 🔊 Text-Prompted Generative Audio Model |
| LAION-AI/Open-Assistant | ⭐ 37.4K | Python | OpenAssistant is a chat-based assistant that understands tasks, can interact with third-party systems, and retrieve information dynamically to do so. |
| google/langextract | ⭐ 36.4K | Python | A Python library for extracting structured information from unstructured text using LLMs with precise source grounding and interactive visualization. |
| stanfordnlp/dspy | ⭐ 34.2K | Python | DSPy: The framework for programming—not prompting—language models |
| Pythagora-io/gpt-pilot | ⭐ 33.8K | Python | The first real AI developer |
| zeroclaw-labs/zeroclaw | ⭐ 31.0K | Rust | Fast, small, and fully autonomous AI personal assistant infrastructure, ANY OS, ANY PLATFORM |
| karpathy/llm.c | ⭐ 29.8K | Cuda | LLM training in simple, raw C/CUDA |
| sipeed/picoclaw | ⭐ 28.7K | Go | Tiny, Fast, and Deployable anywhere — automate the mundane, unleash your creativity |
| qwibitai/nanoclaw | ⭐ 28.6K | TypeScript | A lightweight alternative to OpenClaw that runs in containers for security |
| stanford-oval/storm | ⭐ 28.2K | Python | An LLM-powered knowledge curation system that researches a topic and generates a full-length report with citations. |
| assafelovic/gpt-researcher | ⭐ 26.8K | Python | An autonomous agent that conducts deep research on any data using any LLM providers |
| langfuse/langfuse | ⭐ 26.5K | TypeScript | 🪢 Open source LLM engineering platform: LLM Observability, metrics, evals, prompt management, playground, datasets. Integrates with OpenTelemetry, Langchain, OpenAI SDK, LiteLLM, and more. 🍊YC W23 |
| microsoft/JARVIS | ⭐ 24.7K | Python | JARVIS, a system to connect LLMs with ML community. Paper: https://arxiv.org/pdf/2303.17580.pdf |
| multica-ai/multica | ⭐ 24.5K | TypeScript | The open-source managed agents platform. Turn coding agents into real teammates |
| toon-format/toon | ⭐ 24.1K | TypeScript | 🎒 Token-Oriented Object Notation (TOON) – Compact, human-readable, schema-aware JSON for LLM prompts. Spec, benchmarks, TypeScript SDK. |
| vercel/ai | ⭐ 24.0K | TypeScript | The AI Toolkit for TypeScript. From the creators of Next.js, the AI SDK is a free open-source library for building AI-powered applications and agents |
| oraios/serena | ⭐ 23.8K | Python | A powerful MCP toolkit for coding, providing semantic retrieval and editing capabilities - the IDE for your agent |
| mastra-ai/mastra | ⭐ 23.5K | TypeScript | From the team behind Gatsby, Mastra is a framework for building AI-powered applications and agents with a modern TypeScript stack. |
| ScrapeGraphAI/Scrapegraph-ai | ⭐ 23.4K | Python | Python scraper based on AI |
| deepseek-ai/DeepSeek-Coder | ⭐ 23.2K | Python | DeepSeek Coder: Let the Code Write Itself |
| mlc-ai/mlc-llm | ⭐ 22.6K | Python | Universal LLM Deployment Engine with ML Compilation |
| supermemoryai/supermemory | ⭐ 22.4K | TypeScript | Memory engine and app that is extremely fast, scalable. The Memory API for the AI era. |
| yoheinakajima/babyagi | ⭐ 22.3K | Python | |
| openai/chatgpt-retrieval-plugin | ⭐ 21.2K | Python | The ChatGPT Retrieval Plugin lets you easily find personal or work documents by asking questions in natural language. |
| transitive-bullshit/agentic | ⭐ 18.1K | TypeScript | Your API ⇒ Paid MCP. Instantly. |
| openai/tiktoken | ⭐ 18.1K | Python | tiktoken is a fast BPE tokeniser for use with OpenAI's models. |
| mlc-ai/web-llm | ⭐ 17.9K | TypeScript | High-performance In-browser LLM Inference Engine |
| agentskills/agentskills | ⭐ 17.8K | Python | Specification and documentation for Agent Skills |
| langchain-ai/langchainjs | ⭐ 17.6K | TypeScript | The agent engineering platform |
| leon-ai/leon | ⭐ 17.2K | TypeScript | 🧠 Leon is your open-source personal assistant. |
| manaflow-ai/cmux | ⭐ 16.1K | Swift | Ghostty-based macOS terminal with vertical tabs and notifications for AI coding agents |
| Stability-AI/StableLM | ⭐ 15.7K | Jupyter Notebook | StableLM: Stability AI Language Models |
| neonbjb/tortoise-tts | ⭐ 14.8K | Jupyter Notebook | A multi-voice TTS system trained with an emphasis on quality |
| dottxt-ai/outlines | ⭐ 13.8K | Python | Structured Outputs |
| microsoft/LoRA | ⭐ 13.5K | Python | Code for loralib, an implementation of "LoRA: Low-Rank Adaptation of Large Language Models" |
| cocktailpeanut/dalai | ⭐ 12.9K | CSS | The simplest way to run LLaMA on your local machine |
| ShishirPatil/gorilla | ⭐ 12.9K | Python | Gorilla: Training and Evaluating LLMs for Function Calls (Tool Calls) |
| neuml/txtai | ⭐ 12.5K | Python | 💡 All-in-one AI framework for semantic search, LLM orchestration and language model workflows |
| sapientinc/HRM | ⭐ 12.4K | Python | Hierarchical Reasoning Model Official Release |
| nearai/ironclaw | ⭐ 12.1K | Rust | IronClaw is an Agent OS focused on privacy, security and extensibility |
| h2oai/h2ogpt | ⭐ 12.0K | Python | Private chat with local GPT with document, images, video, etc. 100% private, Apache 2.0. Supports oLLaMa, Mixtral, llama.cpp, and more. Demo: https://gpt.h2o.ai/ https://gpt-docs.h2o.ai/ |
| 0xk1h0/ChatGPT_DAN | ⭐ 12.0K | — | ChatGPT DAN, Jailbreaks prompt |
| tambo-ai/tambo | ⭐ 11.1K | TypeScript | Generative UI SDK for React |
| artidoro/qlora | ⭐ 10.9K | Jupyter Notebook | QLoRA: Efficient Finetuning of Quantized LLMs |
| openai/openai-node | ⭐ 10.9K | TypeScript | Official JavaScript / TypeScript library for the OpenAI API |
| browseros-ai/BrowserOS | ⭐ 10.7K | TypeScript | 🌐 The open-source Agentic browser; alternative to ChatGPT Atlas, Perplexity Comet, Dia. |
| huggingface/chat-ui | ⭐ 10.7K | TypeScript | The open source codebase powering HuggingChat |
| bigscience-workshop/petals | ⭐ 10.1K | Python | 🌸 Run LLMs at home, BitTorrent-style. Fine-tuning and inference up to 10x faster than offloading |
| Arize-ai/phoenix | ⭐ 9.5K | Python | AI Observability & Evaluation |
| davidkimai/Context-Engineering | ⭐ 8.8K | Python | "Context engineering is the delicate art and science of filling the context window with just the right information for the next step." — Andrej Karpathy. A frontier, first-principles handbook inspired by Karpathy and 3Blue1Brown for moving beyond prompt engineering to the wider discipline of context design, orchestration, and optimization. |
| ogx-ai/ogx | ⭐ 8.4K | Python | Open GenAI Stack |
| weaviate/Verba | ⭐ 7.7K | Python | Retrieval Augmented Generation (RAG) chatbot powered by Weaviate |
| openlm-research/open_llama | ⭐ 7.5K | — | OpenLLaMA, a permissively licensed open source reproduction of Meta AI’s LLaMA 7B trained on the RedPajama dataset |
| nullclaw/nullclaw | ⭐ 7.4K | Zig | Fastest, smallest, and fully autonomous AI assistant infrastructure written in Zig |
| tailcallhq/forgecode | ⭐ 7.2K | Rust | AI enabled pair programmer for Claude, GPT, O Series, Grok, Deepseek, Gemini and 300+ models |
| traceloop/openllmetry | ⭐ 7.1K | Python | Open-source observability for your GenAI or LLM application, based on OpenTelemetry |
| deepseek-ai/DeepSeek-LLM | ⭐ 6.9K | Makefile | DeepSeek LLM: Let there be answers |
| mnfst/manifest | ⭐ 6.0K | TypeScript | Smart Model Routing for Agents. Cut Costs up to 70% 🦚 |
| Helicone/helicone | ⭐ 5.6K | TypeScript | 🧊 Open source LLM observability platform. One line of code to monitor, evaluate, and experiment. YC W23 🍓 |
| MrLesk/Backlog.md | ⭐ 5.5K | TypeScript | Backlog.md - A tool for managing project collaboration between humans and AI Agents in a git ecosystem |
| katanaml/sparrow | ⭐ 5.2K | Python | Structured data extraction and instruction calling with ML, LLM and Vision LLM |
| google-deepmind/gemma | ⭐ 5.1K | Python | Gemma open-weight LLM library, from Google DeepMind |
| h2oai/h2o-llmstudio | ⭐ 4.9K | Python | H2O LLM Studio - a framework and no-code GUI for fine-tuning LLMs. Documentation: https://docs.h2o.ai/h2o-llmstudio/ |
| neo4j-labs/llm-graph-builder | ⭐ 4.7K | Jupyter Notebook | Neo4j graph construction from unstructured data using LLMs |
| getzep/zep | ⭐ 4.5K | Python | Zep | Examples, Integrations, & More |
| ogx-ai/llama-stack-apps | ⭐ 4.3K | — | Agentic components of the Llama Stack APIs |
| Agenta-AI/agenta | ⭐ 4.1K | TypeScript | The open-source LLMOps platform: prompt playground, prompt management, LLM evaluation, and LLM observability all in one place. |
| CaviraOSS/OpenMemory | ⭐ 4.1K | TypeScript | Local persistent memory store for LLM applications including claude desktop, github copilot, codex, antigravity, etc. |
| latitude-dev/latitude-llm | ⭐ 4.0K | TypeScript | Latitude is the open-source agent engineering platform |
| mlc-ai/web-stable-diffusion | ⭐ 3.7K | Jupyter Notebook | Bringing stable diffusion models to web browsers. Everything runs inside the browser with no server support. |
| benjitaylor/agentation | ⭐ 3.5K | TypeScript | The visual feedback tool for agents. |
| pashpashpash/vault-ai | ⭐ 3.4K | JavaScript | OP Vault ChatGPT: Give ChatGPT long-term memory using the OP Stack (OpenAI + Pinecone Vector Database). Upload your own custom knowledge base files (PDF, txt, epub, etc) using a simple React frontend. |
| CodedotAl/gpt-code-clippy | ⭐ 3.3K | Python | Full description can be found here: https://discuss.huggingface.co/t/pretrain-gpt-neo-for-open-source-github-copilot-model/7678?u=ncoop57 |
| ob-f/OpenBot | ⭐ 3.3K | Swift | OpenBot leverages smartphones as brains for low-cost robots. We have designed a small electric vehicle that costs about $50 and serves as a robot body. Our software stack for Android smartphones supports advanced robotics workloads such as person following and real-time autonomous navigation. |
| langwatch/langwatch | ⭐ 3.2K | TypeScript | The platform for LLM evaluations and AI agent testing |
| jehna/humanify | ⭐ 3.2K | TypeScript | Deobfuscate Javascript code using ChatGPT |
| noahshinn/reflexion | ⭐ 3.1K | Python | [NeurIPS 2023] Reflexion: Language Agents with Verbal Reinforcement Learning |
| agentclientprotocol/agent-client-protocol | ⭐ 3.0K | Rust | A protocol for connecting any editor to any agent |
| FreedomIntelligence/LLMZoo | ⭐ 2.9K | Python | ⚡LLM Zoo is a project that provides data, models, and evaluation benchmark for large language models.⚡ |
| spiceai/spiceai | ⭐ 2.9K | Rust | A portable accelerated SQL query, search, and LLM-inference engine, written in Rust, for data-grounded AI apps and agents. |
| janhq/cortex.cpp | ⭐ 2.8K | C++ | Local AI API Platform |
| TanStack/ai | ⭐ 2.6K | TypeScript | 🤖 SDK that enhances your applications with AI capabilities |
| ymichael/open-codex | ⭐ 2.2K | TypeScript | Lightweight coding agent that runs in your terminal |
| shcherbak-ai/contextgem | ⭐ 1.8K | Python | ContextGem: Effortless LLM extraction from documents |
| yusufcanb/tlm | ⭐ 1.5K | Go | Local CLI Copilot, powered by Ollama. 💻🦙 |
| Yifan-Song793/RestGPT | ⭐ 1.4K | Python | An LLM-based autonomous agent controlling real-world applications via RESTful APIs |
| ThousandBirdsInc/chidori | ⭐ 1.3K | Rust | A reactive runtime for building durable AI agents |
| mendersoftware/mender | ⭐ 1.2K | C++ | Mender over-the-air software updater client. |
| CASIA-LMC-Lab/AnomalyGPT | ⭐ 1.1K | Python | [AAAI 2024 Oral] AnomalyGPT: Detecting Industrial Anomalies Using Large Vision-Language Models |
| SalesforceAIResearch/promptomatix | ⭐ 952 | Python | An Automatic Prompt Optimization Framework for Large Language Models |
| jonwiggins/optio | ⭐ 934 | TypeScript | Workflow orchestration for AI coding agents, from task to merged PR. |
| kardolus/chatgpt-cli | ⭐ 921 | Go | ChatGPT CLI is a powerful, multi-provider command-line interface for working with modern LLMs. It supports OpenAI, Azure, Perplexity, LLaMA, and more, with features like streaming, interactive chat, prompt files, image/audio I/O, MCP tool calls, and an experimental agent mode for safe, multi-step automation. |
| QuantGeekDev/mcp-framework | ⭐ 917 | TypeScript | The Typescript MCP Framework |
| Atome-FE/llama-node | ⭐ 865 | Rust | Believe in AI democratization. llama for nodejs backed by llama-rs, llama.cpp and rwkv.cpp, work locally on your laptop CPU. support llama/alpaca/gpt4all/vicuna/rwkv model. |
| MagnivOrg/prompt-layer-library | ⭐ 762 | Python | 🍰 PromptLayer - Maintain a log of your prompts and OpenAI API requests. Track, debug, and replay old completions. |
| latitudegames/GPT-3-Encoder | ⭐ 722 | JavaScript | Javascript BPE Encoder Decoder for GPT-2 / GPT-3 |
| liveloveapp/hashbrown | ⭐ 686 | TypeScript | Hashbrown is a framework for building agents that run the browser. Built for Angular and React. |
| llm-tools/embedJs | ⭐ 605 | TypeScript | A NodeJS RAG framework to easily work with LLMs and embeddings |
| okuvshynov/slowllama | ⭐ 450 | Python | Finetune llama2-70b and codellama on MacBook Air without quantization |
| simonmysun/ell | ⭐ 435 | Shell | A command-line interface for LLMs written in Bash. |
| zju-vipa/Odyssey | ⭐ 379 | Python | Odyssey: Empowering Minecraft Agents with Open-World Skills |
| yusufhilmi/client-vector-search | ⭐ 231 | TypeScript | A client side vector search library that can embed, store, search, and cache vectors. Works on the browser and node. It outperforms OpenAI's text-embedding-ada-002 and is way faster than Pinecone and other VectorDBs. |
| meilisearch/meilisearch-mcp | ⭐ 185 | Python | A Model Context Protocol (MCP) server for interacting with Meilisearch through LLM interfaces. |
| Anush008/fastembed-js | ⭐ 175 | TypeScript | Generate vector embeddings in NodeJS |
| phil65/agentpool | ⭐ 145 | Python | A unified agent orchestration hub that lets you configure and manage multiple AI agents (native, ACP, AGUI, Claude Code) via YAML, and exposes them through standardized protocols (ACP/OpenCode Server). |
| nordwestt/ollama-ai-provider-v2 | ⭐ 100 | TypeScript | Vercel AI Provider for running LLMs locally using Ollama |
| tkafka/node-elizabot | ⭐ 63 | JavaScript | |
| sbrsv/ai-embed-search | ⭐ 31 | TypeScript | Smart. Simple. Local. AI-powered semantic search in TypeScript using transformer embeddings. No cloud, no API keys — 100% offline. |
| fboerncke/bloom-ai-simple-starter-nodejs | ⭐ 31 | JavaScript | Simple starter BLOOM example showing how to access the web api to get something up and running in short time. |
Showing 147 repositories