| 1 |
ollama |
154520 |
13435 |
Go |
1840 |
Get up and running with OpenAI gpt-oss, DeepSeek-R1, Gemma 3 and other models. |
2025-10-22T02:01:30Z |
| 2 |
llama.cpp |
88135 |
13398 |
C++ |
283 |
LLM inference in C/C++ |
2025-10-21T15:02:05Z |
| 3 |
vllm |
60655 |
10700 |
Python |
1848 |
A high-throughput and memory-efficient inference and serving engine for LLMs |
2025-10-22T03:30:03Z |
| 4 |
LLaMA-Factory |
60576 |
7335 |
Python |
719 |
Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024) |
2025-10-21T10:26:12Z |
| 5 |
llama |
58859 |
9815 |
Python |
449 |
Inference code for Llama models |
2025-01-26T21:42:26Z |
| 6 |
unsloth |
47258 |
3865 |
Python |
803 |
Fine-tuning & Reinforcement Learning for LLMs. 🦥 Train OpenAI gpt-oss, DeepSeek-R1, Qwen3, Gemma 3, TTS 2x faster with 70% less VRAM. |
2025-10-21T18:33:42Z |
| 7 |
llama_index |
44839 |
6466 |
Python |
216 |
LlamaIndex is the leading framework for building LLM-powered agents over your data. |
2025-10-20T15:36:55Z |
| 8 |
quivr |
38530 |
3680 |
Python |
2 |
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. |
2025-07-09T12:55:23Z |
| 9 |
aider |
38034 |
3597 |
Python |
1060 |
aider is AI pair programming in your terminal |
2025-10-05T19:11:17Z |
| 10 |
Langchain-Chatchat |
36308 |
6045 |
TypeScript |
29 |
Langchain-Chatchat（原Langchain-ChatGLM）基于 Langchain 与 ChatGLM, Qwen 与 Llama 等语言模型的 RAG 与 Agent 应用 | Langchain-Chatchat (formerly langchain-ChatGLM), local knowledge based LLM (like ChatGLM, Qwen and Llama) RAG and Agent app with langchain |
2025-09-29T06:47:27Z |
| 11 |
LocalAI |
35944 |
2853 |
Go |
272 |
:robot: The free, Open Source alternative to OpenAI, Claude and others. Self-hosted and local-first. Drop-in replacement for OpenAI, running on consumer-grade hardware. No GPU required. Runs gguf, transformers, diffusers and many more. Features: Generate Text, Audio, Video, Images, Voice Cloning, Distributed, P2P and decentralized inference |
2025-10-21T21:15:27Z |
| 12 |
khoj |
31370 |
1846 |
Python |
75 |
Your AI second brain. Self-hostable. Get answers from the web or your docs. Build custom agents, schedule automations, do deep research. Turn any online or local LLM into your personal, autonomous AI (gpt, claude, gemini, llama, qwen, mistral). Get started - free. |
2025-09-16T09:17:58Z |
| 13 |
llama3 |
29052 |
3470 |
Python |
175 |
The official Meta Llama 3 GitHub site |
2025-01-26T21:39:06Z |
| 14 |
LLaVA |
23793 |
2648 |
Python |
1086 |
[NeurIPS’23 Oral] Visual Instruction Tuning (LLaVA) built towards GPT-4V level capabilities and beyond. |
2024-08-12T09:52:38Z |
| 15 |
fish-speech |
23341 |
1930 |
Python |
21 |
SOTA Open Source TTS |
2025-10-20T00:12:51Z |
| 16 |
llamafile |
23227 |
1228 |
C++ |
171 |
Distribute and run LLMs with a single file. |
2025-06-30T19:03:06Z |
| 17 |
Awesome-Chinese-LLM |
21479 |
2046 |
None |
5 |
整理开源的中文大语言模型，以规模较小、可私有化部署、训练成本较低的模型为主，包括底座模型，垂直领域微调及应用，数据集与教程等。 |
2025-05-19T06:11:57Z |
| 18 |
repomix |
19832 |
901 |
TypeScript |
111 |
📦 Repomix is a powerful tool that packs your entire repository into a single, AI-friendly file. Perfect for when you need to feed your codebase to Large Language Models (LLMs) or other AI tools like Claude, ChatGPT, DeepSeek, Perplexity, Gemini, Gemma, Llama, Grok, and more. |
2025-10-21T01:11:54Z |
| 19 |
sglang |
19092 |
3126 |
Python |
528 |
SGLang is a fast serving framework for large language models and vision language models. |
2025-10-22T03:32:52Z |
| 20 |
alpaca-lora |
18971 |
2221 |
Jupyter Notebook |
333 |
Instruct-tune LLaMA on consumer hardware |
2024-07-29T13:37:49Z |
| 21 |
Chinese-LLaMA-Alpaca |
18932 |
1877 |
Python |
1 |
中文LLaMA&Alpaca大语言模型+本地CPU/GPU训练部署 (Chinese LLaMA & Alpaca LLMs) |
2025-07-15T00:53:02Z |
| 22 |
llama2.c |
18869 |
2390 |
C |
125 |
Inference Llama 2 in one file of pure C |
2024-08-06T09:44:40Z |
| 23 |
llama-cookbook |
17964 |
2631 |
Jupyter Notebook |
18 |
Welcome to the Llama Cookbook! This is your go to guide for Building with Llama: Getting started with Inference, Fine-Tuning, RAG. We also show you how to solve end to end problems using Llama model family and using them on various provider services |
2025-10-17T15:17:32Z |
| 24 |
mastra |
17658 |
1207 |
TypeScript |
271 |
The TypeScript AI agent framework. ⚡ Assistants, RAG, observability. Supports any LLM: GPT-4, Claude, Gemini, Llama. |
2025-10-22T02:00:50Z |
| 25 |
ChuanhuChatGPT |
15433 |
2267 |
Python |
124 |
GUI for ChatGPT API and many LLMs. Supports agents, file-based QA, GPT finetuning and query with web search. All with a neat UI. |
2025-08-15T02:25:50Z |
| 26 |
llama3-from-scratch |
15180 |
1292 |
Jupyter Notebook |
14 |
llama3 implementation one matrix multiplication at a time |
2024-05-23T14:34:05Z |
| 27 |
Llama-Chinese |
14719 |
1305 |
Python |
195 |
Llama中文社区，实时汇总最新Llama学习资料，构建最好的中文Llama大模型开源生态，完全开源可商用 |
2025-04-06T09:16:55Z |
| 28 |
dalai |
13047 |
1376 |
CSS |
291 |
The simplest way to run LLaMA on your local machine |
2024-06-18T20:29:46Z |
| 29 |
PaddleNLP |
12813 |
3077 |
Python |
132 |
Easy-to-use and powerful LLM and SLM library with awesome model zoo. |
2025-10-22T03:04:37Z |
| 30 |
AstrBot |
12759 |
932 |
Python |
284 |
✨ 一站式 LLM 聊天机器人平台及开发框架 ✨ 支持 QQ、QQ频道、Telegram、企微、飞书、钉钉 | 知识库、MCP 服务器、OpenAI、DeepSeek、Gemini、硅基流动、月之暗面、Ollama、OneAPI、Dify |
2025-10-21T06:19:45Z |
| 31 |
h2ogpt |
11930 |
1305 |
Python |
291 |
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/ |
2025-10-09T23:30:01Z |
| 32 |
OpenLLM |
11864 |
782 |
Python |
3 |
Run any open-source LLMs, such as DeepSeek and Llama, as OpenAI compatible API endpoint in the cloud. |
2025-10-20T18:40:39Z |
| 33 |
ludwig |
11604 |
1220 |
Python |
42 |
Low-code framework for building custom LLMs, neural networks, and other AI models |
2025-10-20T22:50:11Z |
| 34 |
shell_gpt |
11435 |
919 |
Python |
91 |
A command-line productivity tool powered by AI large language models like GPT-4, will help you accomplish your tasks faster and more efficiently. |
2025-07-17T04:13:14Z |
| 35 |
llama-gpt |
10992 |
709 |
TypeScript |
84 |
A self-hosted, offline, ChatGPT-like chatbot. Powered by Llama 2. 100% private, with no data leaving your device. New: Code Llama support! |
2024-04-23T18:56:06Z |
| 36 |
ms-swift |
10558 |
911 |
Python |
601 |
Use PEFT or Full-parameter to CPT/SFT/DPO/GRPO 500+ LLMs (Qwen3, Qwen3-MoE, Llama4, GLM4.5, InternLM3, DeepSeek-R1, …) and 200+ MLLMs (Qwen3-VL, Qwen3-Omni, InternVL3.5, Ovis2.5, Llava, GLM4v, Phi4, …) (AAAI 2025). |
2025-10-22T02:59:50Z |
| 37 |
tensorzero |
10437 |
717 |
Rust |
333 |
TensorZero is an open-source stack for industrial-grade LLM applications. It unifies an LLM gateway, observability, optimization, evaluation, and experimentation. |
2025-10-22T02:41:21Z |
| 38 |
petals |
9819 |
579 |
Python |
92 |
🌸 Run LLMs at home, BitTorrent-style. Fine-tuning and inference up to 10x faster than offloading |
2024-09-07T11:54:28Z |
| 39 |
bisheng |
9767 |
1597 |
TypeScript |
96 |
BISHENG is an open LLM devops platform for next generation Enterprise AI applications. Powerful and comprehensive features include: GenAI workflow, RAG, Agent, Unified model management, Evaluation, SFT, Dataset Management, Enterprise-level System Management, Observability and more. |
2025-10-21T12:59:24Z |
| 40 |
llama-cpp-python |
9671 |
1238 |
Python |
576 |
Python bindings for llama.cpp |
2025-08-15T06:23:26Z |
| 41 |
langchain4j |
9349 |
1719 |
Java |
513 |
LangChain4j is an open-source Java library that simplifies the integration of LLMs into Java applications through a unified API, providing access to popular LLMs and vector databases. It makes implementing RAG, tool calling (including support for MCP), and agents easy. LangChain4j integrates seamlessly with various enterprise Java frameworks. |
2025-10-21T17:18:08Z |
| 42 |
promptfoo |
8780 |
739 |
TypeScript |
172 |
Test your prompts, agents, and RAGs. AI Red teaming, pentesting, and vulnerability scanning for LLMs. Compare performance of GPT, Claude, Gemini, Llama, and more. Simple declarative configs with command line and CI/CD integration. |
2025-10-22T01:25:13Z |
| 43 |
TinyLlama |
8775 |
570 |
Python |
45 |
The TinyLlama project is an open endeavor to pretrain a 1.1B Llama model on 3 trillion tokens. |
2024-05-03T20:21:20Z |
| 44 |
inference |
8643 |
749 |
Python |
125 |
Replace OpenAI GPT with another LLM in your app by changing a single line of code. Xinference gives you the freedom to use any LLM you need. With Xinference, you’re empowered to run inference with any open-source language models, speech recognition models, and multimodal models, whether in the cloud, on-premises, or even on your laptop. |
2025-10-22T03:34:34Z |
| 45 |
oumi |
8563 |
650 |
Python |
15 |
Easily fine-tune, evaluate and deploy gpt-oss, Qwen3, DeepSeek-R1, or any open source LLM / VLM! |
2025-10-20T15:44:42Z |
| 46 |
ipex-llm |
8400 |
1381 |
Python |
1211 |
Accelerate local LLM inference and finetuning (LLaMA, Mistral, ChatGLM, Qwen, DeepSeek, Mixtral, Gemma, Phi, MiniCPM, Qwen-VL, MiniCPM-V, etc.) on Intel XPU (e.g., local PC with iGPU and NPU, discrete GPU such as Arc, Flex and Max); seamlessly integrate with llama.cpp, Ollama, HuggingFace, LangChain, LlamaIndex, vLLM, DeepSpeed, Axolotl, etc. |
2025-10-14T06:04:12Z |
| 47 |
PowerInfer |
8366 |
448 |
C++ |
120 |
High-speed Large Language Model Serving for Local Deployment |
2025-08-02T03:36:13Z |
| 48 |
reor |
8328 |
505 |
JavaScript |
110 |
Private & local AI personal knowledge management app for high entropy people. |
2025-05-13T21:28:59Z |
| 49 |
BELLE |
8240 |
767 |
HTML |
105 |
BELLE: Be Everyone’s Large Language model Engine（开源中文对话大模型） |
2024-10-16T11:38:59Z |
| 50 |
llama-stack |
8119 |
1193 |
Python |
151 |
Composable building blocks to build Llama Apps |
2025-10-22T01:31:21Z |
| 51 |
GPTCache |
7799 |
567 |
Python |
72 |
Semantic cache for LLMs. Fully integrated with LangChain and llama_index. |
2025-07-11T09:04:36Z |
| 52 |
ART |
7644 |
587 |
Python |
45 |
Agent Reinforcement Trainer: train multi-step agents for real-world tasks using GRPO. Give your agents on-the-job training. Reinforcement learning for Qwen2.5, Qwen3, Llama, and more! |
2025-10-21T00:17:51Z |
| 53 |
open_llama |
7526 |
405 |
None |
37 |
OpenLLaMA, a permissively licensed open source reproduction of Meta AI’s LLaMA 7B trained on the RedPajama dataset |
2023-07-16T13:42:13Z |
| 54 |
llama-models |
7305 |
1258 |
Python |
135 |
Utilities intended for use with Llama models. |
2025-10-10T00:22:06Z |
| 55 |
lmdeploy |
7194 |
610 |
Python |
488 |
LMDeploy is a toolkit for compressing, deploying, and serving LLMs. |
2025-10-20T04:17:09Z |
| 56 |
Chinese-LLaMA-Alpaca-2 |
7171 |
569 |
Python |
0 |
中文LLaMA-2 & Alpaca-2大模型二期项目 + 64K超长上下文模型 (Chinese LLaMA-2 & Alpaca-2 LLMs with 64K long context models) |
2025-07-15T00:47:22Z |
| 57 |
k8sgpt |
7059 |
886 |
Go |
85 |
Giving Kubernetes Superpowers to everyone |
2025-10-20T01:38:59Z |
| 58 |
llamacoder |
6657 |
1601 |
TypeScript |
24 |
Open source Claude Artifacts – built with Llama 3.1 405B |
2025-09-08T12:10:47Z |
| 59 |
Firefly |
6577 |
585 |
Python |
204 |
Firefly: 大模型训练工具，支持训练Qwen2.5、Qwen2、Yi1.5、Phi-3、Llama3、Gemma、MiniCPM、Yi、Deepseek、Orion、Xverse、Mixtral-8x7B、Zephyr、Mistral、Baichuan2、Llma2、Llama、Qwen、Baichuan、ChatGLM2、InternLM、Ziya2、Vicuna、Bloom等大模型 |
2024-10-24T02:27:42Z |
| 60 |
mergekit |
6387 |
624 |
Python |
228 |
Tools for merging pretrained large language models. |
2025-09-17T22:20:17Z |
| 61 |
awesome-LLM-resources |
6386 |
628 |
None |
0 |
🧑🚀 全世界最好的LLM资料总结（语音视频生成、Agent、辅助编程、数据处理、模型训练、模型推理、o1 模型、MCP、小语言模型、视觉语言模型） | Summary of the world’s best LLM resources. |
2025-10-21T05:24:01Z |
| 62 |
airllm |
6271 |
480 |
Jupyter Notebook |
114 |
AirLLM 70B inference with single 4GB GPU |
2025-09-03T13:50:08Z |
| 63 |
free-llm-api-resources |
6141 |
569 |
Python |
12 |
A list of free LLM inference resources accessible via API. |
2025-10-22T01:26:28Z |
| 64 |
lit-llama |
6078 |
524 |
Python |
108 |
Implementation of the LLaMA language model based on nanoGPT. Supports flash attention, Int8 and GPTQ 4bit quantization, LoRA and LLaMA-Adapter fine-tuning, pre-training. Apache 2.0-licensed. |
2025-07-01T16:31:39Z |
| 65 |
llm-scraper |
6063 |
363 |
TypeScript |
8 |
Turn any webpage into structured data using LLMs |
2025-10-21T02:44:13Z |
| 66 |
LaWGPT |
6024 |
553 |
Python |
86 |
🎉 Repo for LaWGPT, Chinese-Llama tuned with Chinese Legal knowledge. 基于中文法律知识的大语言模型 |
2024-06-11T07:20:19Z |
| 67 |
LLaMA-Adapter |
5906 |
383 |
Python |
107 |
[ICLR 2024] Fine-tuning LLaMA to follow Instructions within 1 Hour and 1.2M Parameters |
2024-03-14T08:12:53Z |
| 68 |
Liger-Kernel |
5764 |
418 |
Python |
70 |
Efficient Triton Kernels for LLM Training |
2025-10-20T20:44:47Z |
| 69 |
serge |
5753 |
402 |
Svelte |
18 |
A web interface for chatting with Alpaca through llama.cpp. Fully dockerized, with an easy to use API. |
2025-10-21T08:11:13Z |
| 70 |
Baichuan-7B |
5683 |
506 |
Python |
85 |
A large-scale 7B pretraining language model developed by BaiChuan-Inc. |
2024-07-18T14:23:01Z |
| 71 |
enchanted |
5680 |
380 |
Swift |
98 |
Enchanted is iOS and macOS app for chatting with private self hosted language models such as Llama2, Mistral or Vicuna using Ollama. |
2025-03-19T20:19:21Z |
| 72 |
llama-fs |
5671 |
377 |
TypeScript |
52 |
A self-organizing file system with llama 3 |
2025-08-08T02:27:02Z |
| 73 |
YuE |
5608 |
648 |
Python |
74 |
YuE: Open Full-song Music Generation Foundation Model, something similar to Suno.ai but open |
2025-06-04T13:08:48Z |
| 74 |
nexa-sdk |
5447 |
708 |
Go |
30 |
Run the latest LLMs and VLMs across GPU, NPU, and CPU with PC (Python/C++) & mobile (Android & iOS) support, running quickly with OpenAI gpt-oss, Granite4, Qwen3VL, Gemma 3n and more. |
2025-10-22T03:42:53Z |
| 75 |
llm-answer-engine |
4919 |
790 |
TypeScript |
26 |
Build a Perplexity-Inspired Answer Engine Using Next.js, Groq, Llama-3, Langchain, OpenAI, Upstash, Brave & Serper |
2025-06-27T03:35:14Z |
| 76 |
Huatuo-Llama-Med-Chinese |
4878 |
493 |
Python |
28 |
Repo for BenTsao [original name: HuaTuo (华驼)], Instruction-tuning Large Language Models with Chinese Medical Knowledge. 本草（原名：华驼）模型仓库，基于中文医学知识的大语言模型指令微调 |
2025-02-21T02:04:37Z |
| 77 |
smolvlm-realtime-webcam |
4795 |
763 |
HTML |
11 |
Real-time webcam demo with SmolVLM and llama.cpp server |
2025-05-12T17:24:39Z |
| 78 |
h2o-llmstudio |
4688 |
497 |
Python |
40 |
H2O LLM Studio - a framework and no-code GUI for fine-tuning LLMs. Documentation: https://docs.h2o.ai/h2o-llmstudio/ |
2025-09-25T15:18:10Z |
| 79 |
transformerlab-app |
4455 |
438 |
TypeScript |
59 |
Open Source Application for Advanced LLM + Diffusion Engineering: interact, train, fine-tune, and evaluate large language models on your own computer. |
2025-10-21T21:38:33Z |
| 80 |
paperless-ai |
4426 |
199 |
JavaScript |
15 |
An automated document analyzer for Paperless-ngx using OpenAI API, Ollama, Deepseek-r1, Azure and all OpenAI API compatible Services to automatically analyze and tag your documents. |
2025-10-07T00:15:57Z |
| 81 |
GPT-4-LLM |
4334 |
306 |
HTML |
12 |
Instruction Tuning with GPT-4 |
2023-06-11T13:40:30Z |
| 82 |
llama-stack-apps |
4272 |
634 |
None |
20 |
Agentic components of the Llama Stack APIs |
2025-08-05T14:49:58Z |
| 83 |
g1 |
4223 |
377 |
Python |
0 |
g1: Using Llama-3.1 70b on Groq to create o1-like reasoning chains |
2025-09-11T16:29:17Z |
| 84 |
obsidian-smart-connections |
4198 |
252 |
JavaScript |
419 |
Chat with your notes & see links to related content with AI embeddings. Use local models or 100+ via APIs like Claude, Gemini, ChatGPT & Llama 3 |
2025-10-21T18:45:15Z |
| 85 |
llama_cloud_services |
4184 |
460 |
TypeScript |
302 |
Knowledge Agents and Management in the Cloud |
2025-10-21T20:37:41Z |
| 86 |
llama3-Chinese-chat |
4168 |
338 |
Python |
29 |
Llama3、Llama3.1 中文后训练版仓库 - 微调、魔改版本有趣权重 & 训练、推理、评测、部署教程视频 & 文档。 |
2025-05-07T06:09:40Z |
| 87 |
MedicalGPT |
4159 |
609 |
Python |
50 |
MedicalGPT: Training Your Own Medical GPT Model with ChatGPT Training Pipeline. 训练医疗大模型，实现了包括增量预训练(PT)、有监督微调(SFT)、RLHF、DPO、ORPO、GRPO。 |
2025-08-30T12:31:36Z |
| 88 |
llama-dl |
4155 |
410 |
Shell |
9 |
High-speed download of LLaMA, Facebook’s 65B parameter GPT model |
2023-06-28T16:56:55Z |
| 89 |
casibase |
4147 |
493 |
Go |
45 |
⚡️AI Cloud OS: Open-source enterprise-level AI knowledge base and MCP (model-context-protocol)/A2A (agent-to-agent) management platform with admin UI, user management and Single-Sign-On⚡️, supports ChatGPT, Claude, Llama, Ollama, HuggingFace, etc., chat bot demo: https://ai.casibase.com, admin UI demo: https://ai-admin.casibase.com |
2025-10-21T14:26:02Z |
| 90 |
Chinese-Vicuna |
4145 |
413 |
C |
65 |
Chinese-Vicuna: A Chinese Instruction-following LLaMA-based Model —— 一个中文低资源的llama+lora方案，结构参考alpaca |
2025-04-18T02:41:35Z |
| 91 |
tiny-universe |
3900 |
396 |
Jupyter Notebook |
9 |
《大模型白盒子构建指南》：一个全手搓的Tiny-Universe |
2025-08-30T08:03:41Z |
| 92 |
gpustack |
3888 |
391 |
Python |
498 |
Simple, scalable AI model deployment on GPU clusters |
2025-10-21T11:56:52Z |
| 93 |
PurpleLlama |
3825 |
652 |
Python |
15 |
Set of tools to assess and improve LLM security. |
2025-10-02T11:35:37Z |
| 94 |
sdk-python |
3788 |
446 |
Python |
219 |
A model-driven approach to building AI agents in just a few lines of code. |
2025-10-21T19:29:38Z |
| 95 |
langroid |
3727 |
351 |
Python |
48 |
Harness LLMs with Multi-Agent Programming |
2025-10-19T00:23:35Z |
| 96 |
zero_nlp |
3675 |
440 |
Jupyter Notebook |
101 |
中文nlp解决方案(大模型、数据、模型、训练、推理) |
2025-08-05T01:26:45Z |
| 97 |
LightLLM |
3664 |
280 |
Python |
81 |
LightLLM is a Python-based LLM (Large Language Model) inference and serving framework, notable for its lightweight design, easy scalability, and high-speed performance. |
2025-10-21T12:24:52Z |
| 98 |
llms-from-scratch-cn |
3634 |
504 |
Jupyter Notebook |
13 |
仅需Python基础，从0构建大语言模型；从0逐步构建GLM4\Llama3\RWKV6， 深入理解大模型原理 |
2024-08-15T02:19:06Z |
| 99 |
ClaraVerse |
3520 |
385 |
TypeScript |
53 |
ClaraVerse is a privacy-first, fully local AI workspace featuring a Local LLM chat powered by LLama.cpp, along with support for any provider, tool calling, agent building, Stable Diffusion, and n8n-style automation. It requires no backend or API keys—just your stack and machine. |
2025-10-21T05:29:58Z |
| 100 |
lorax |
3518 |
280 |
Python |
148 |
Multi-LoRA inference server that scales to 1000s of fine-tuned LLMs |
2025-05-21T17:40:25Z |