| 1 |
ollama |
157511 |
13903 |
Go |
1930 |
Get up and running with OpenAI gpt-oss, DeepSeek-R1, Gemma 3 and other models. |
2025-12-13T03:29:00Z |
| 2 |
unsloth |
49360 |
4079 |
Python |
805 |
Fine-tuning & Reinforcement Learning for LLMs. 🦥 Train OpenAI gpt-oss, DeepSeek-R1, Qwen3, Gemma 3, TTS 2x faster with 70% less VRAM. |
2025-12-12T13:53:46Z |
| 3 |
LocalAI |
40070 |
3206 |
Go |
199 |
: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, MCP, Audio, Video, Images, Voice Cloning, Distributed, P2P and decentralized inference |
2025-12-12T23:37:41Z |
| 4 |
LibreChat |
32362 |
6393 |
TypeScript |
231 |
Enhanced ChatGPT Clone: Features Agents, MCP, DeepSeek, Anthropic, AWS, OpenAI, Responses API, Azure, Groq, o1, GPT-5, Mistral, OpenRouter, Vertex AI, Gemini, Artifacts, AI model switching, message search, Code Interpreter, langchain, DALL-E-3, OpenAPI Actions, Functions, Secure Multi-User Auth, Presets, open-source for self-hosting. Active. |
2025-12-12T23:46:41Z |
| 5 |
khoj |
31909 |
1893 |
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. |
2025-12-08T04:36:04Z |
| 6 |
OpenLLM |
11993 |
798 |
Python |
3 |
Run any open-source LLMs, such as DeepSeek and Llama, as OpenAI compatible API endpoint in the cloud. |
2025-12-08T16:56:47Z |
| 7 |
ludwig |
11627 |
1219 |
Python |
42 |
Low-code framework for building custom LLMs, neural networks, and other AI models |
2025-12-08T21:22:04Z |
| 8 |
mistral-inference |
10589 |
999 |
Jupyter Notebook |
130 |
Official inference library for Mistral models |
2025-11-21T11:07:09Z |
| 9 |
inference |
8838 |
775 |
Python |
136 |
Swap GPT for any LLM by changing a single line of code. Xinference lets you run open-source, speech, and multimodal models on cloud, on-prem, or your laptop — all through one unified, production-ready inference API. |
2025-12-12T09:04:21Z |
| 10 |
ipex-llm |
8534 |
1387 |
Python |
1216 |
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 |
| 11 |
awesome-LLM-resources |
6940 |
671 |
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. |
2025-12-11T01:46:23Z |
| 12 |
Firefly |
6610 |
588 |
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 |
| 13 |
opencompass |
6413 |
700 |
Python |
363 |
OpenCompass is an LLM evaluation platform, supporting a wide range of models (Llama3, Mistral, InternLM2,GPT-4,LLaMa2, Qwen,GLM, Claude, etc) over 100+ datasets. |
2025-12-11T10:51:11Z |
| 14 |
mistral.rs |
6269 |
491 |
Rust |
171 |
Blazingly fast LLM inference. |
2025-12-12T21:04:41Z |
| 15 |
Liger-Kernel |
5940 |
446 |
Python |
84 |
Efficient Triton Kernels for LLM Training |
2025-12-12T10:36:07Z |
| 16 |
enchanted |
5742 |
387 |
Swift |
99 |
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 |
| 17 |
chinese-llm-benchmark |
5266 |
211 |
None |
10 |
ReLE评测：中文AI大模型能力评测（持续更新）：目前已囊括318个大模型，覆盖chatgpt、gpt-5.1、o4-mini、谷歌gemini-3-pro、Claude-4.5、文心ERNIE-X1.1、ERNIE-5.0-Thinking、qwen3-max、百川、讯飞星火、商汤senseChat等商用模型， 以及kimi-k2、ernie4.5、minimax-M2、deepseek-v3.2、qwen3-2507、llama4、智谱GLM-4.6、gemma3、mistral等开源大模型。不仅提供排行榜，也提供规模超200万的大模型缺陷库！方便广大社区研究分析、改进大模型。 |
2025-12-12T09:38:07Z |
| 18 |
agentops |
5119 |
499 |
Python |
72 |
Python SDK for AI agent monitoring, LLM cost tracking, benchmarking, and more. Integrates with most LLMs and agent frameworks including CrewAI, Agno, OpenAI Agents SDK, Langchain, Autogen, AG2, and CamelAI |
2025-10-30T18:52:13Z |
| 19 |
paperless-ai |
4721 |
217 |
JavaScript |
31 |
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. |
2025-12-02T20:05:07Z |
| 20 |
json_repair |
4146 |
160 |
Python |
0 |
A python module to repair invalid JSON from LLMs |
2025-11-25T19:30:56Z |
| 21 |
local-deep-research |
3701 |
357 |
Python |
43 |
Local Deep Research achieves ~95% on SimpleQA benchmark (tested with GPT-4.1-mini). Supports local and cloud LLMs (Ollama, Google, Anthropic, …). Searches 10+ sources - arXiv, PubMed, web, and your private documents. Everything Local & Encrypted. |
2025-12-13T00:22:15Z |
| 22 |
AI-Infra-from-Zero-to-Hero |
3461 |
351 |
None |
13 |
🚀 Awesome System for Machine Learning ⚡️ AI System Papers and Industry Practice. ⚡️ System for Machine Learning, LLM (Large Language Model), GenAI (Generative AI). 🍻 OSDI, NSDI, SIGCOMM, SoCC, MLSys, etc. 🗃️ Llama3, Mistral, etc. 🧑💻 Video Tutorials. |
2025-07-25T02:24:35Z |
| 23 |
ruby_llm |
3302 |
337 |
Ruby |
41 |
One beautiful Ruby API for OpenAI, Anthropic, Gemini, Bedrock, OpenRouter, DeepSeek, Ollama, VertexAI, Perplexity, Mistral, GPUStack & OpenAI compatible APIs. Chat, Vision, Audio, PDF, Images, Embeddings, Tools, Streaming & Rails integration. |
2025-11-19T01:54:08Z |
| 24 |
lsp-ai |
3062 |
112 |
Rust |
38 |
LSP-AI is an open-source language server that serves as a backend for AI-powered functionality, designed to assist and empower software engineers, not replace them. |
2025-01-07T22:17:38Z |
| 25 |
mistral-finetune |
3046 |
302 |
Python |
35 |
None |
2025-11-21T10:27:03Z |
| 26 |
secret-llama |
2675 |
174 |
TypeScript |
19 |
Fully private LLM chatbot that runs entirely with a browser with no server needed. Supports Mistral and LLama 3. |
2024-06-05T02:04:17Z |
| 27 |
xTuring |
2663 |
206 |
Python |
10 |
Build, personalize and control your own LLMs. From data pre-processing to fine-tuning, xTuring provides an easy way to personalize open-source LLMs. Join our discord community: https://discord.gg/TgHXuSJEk6 |
2025-12-02T03:36:51Z |
| 28 |
elia |
2389 |
152 |
Python |
14 |
A snappy, keyboard-centric terminal user interface for interacting with large language models. Chat with ChatGPT, Claude, Llama 3, Phi 3, Mistral, Gemma and more. |
2024-10-10T19:12:52Z |
| 29 |
maid |
2215 |
232 |
Dart |
20 |
Maid is a cross-platform Flutter app for interfacing with GGUF / llama.cpp models locally, and with Ollama and OpenAI models remotely. |
2025-07-28T13:24:29Z |
| 30 |
floneum |
2096 |
118 |
Rust |
46 |
Instant, controllable, local pre-trained AI models in Rust |
2025-12-10T13:55:18Z |
| 31 |
maxtext |
2041 |
438 |
Python |
73 |
A simple, performant and scalable Jax LLM! |
2025-12-13T03:53:02Z |
| 32 |
OnnxStream |
2012 |
90 |
C++ |
65 |
Lightweight inference library for ONNX files, written in C++. It can run Stable Diffusion XL 1.0 on a RPI Zero 2 (or in 298MB of RAM) but also Mistral 7B on desktops and servers. ARM, x86, WASM, RISC-V supported. Accelerated by XNNPACK. Python, C# and JS(WASM) bindings available. |
2025-11-18T08:11:21Z |
| 33 |
papersgpt-for-zotero |
2003 |
65 |
JavaScript |
60 |
A powerful Zotero AI and MCP plugin with ChatGPT, Gemini 3, Claude, Grok, DeepSeek, OpenRouter, Kimi, GLM, SiliconFlow, GPT-oss, Gemma 3, Qwen 3 |
2025-11-26T17:17:43Z |
| 34 |
Ollamac |
1889 |
103 |
Swift |
41 |
Mac app for Ollama |
2025-03-12T22:28:22Z |
| 35 |
lemonade |
1853 |
154 |
Python |
72 |
Lemonade helps users run local LLMs with the highest performance by configuring state-of-the-art inference engines for their NPUs and GPUs. Join our discord: https://discord.gg/5xXzkMu8Zk |
2025-12-12T16:44:48Z |
| 36 |
mistral-vibe |
1843 |
125 |
Python |
69 |
Minimal CLI coding agent by Mistral |
2025-12-12T16:58:05Z |
| 37 |
dialoqbase |
1786 |
279 |
TypeScript |
41 |
Create chatbots with ease |
2024-10-15T14:24:20Z |
| 38 |
witsy |
1776 |
147 |
TypeScript |
36 |
Witsy: desktop AI assistant / universal MCP client |
2025-12-12T03:01:51Z |
| 39 |
paperless-gpt |
1649 |
88 |
Go |
97 |
Use LLMs and LLM Vision (OCR) to handle paperless-ngx - Document Digitalization powered by AI |
2025-12-13T00:44:24Z |
| 40 |
nextjs-ollama-llm-ui |
1369 |
330 |
TypeScript |
16 |
Fully-featured web interface for Ollama LLMs |
2025-06-05T13:13:19Z |
| 41 |
aws-genai-llm-chatbot |
1352 |
424 |
TypeScript |
15 |
A modular and comprehensive solution to deploy a Multi-LLM and Multi-RAG powered chatbot (Amazon Bedrock, Anthropic, HuggingFace, OpenAI, Meta, AI21, Cohere, Mistral) using AWS CDK on AWS |
2025-12-06T05:30:11Z |
| 42 |
ai-dev-gallery |
1343 |
183 |
C# |
65 |
An open-source project for Windows developers to learn how to add AI with local models and APIs to Windows apps. |
2025-12-12T18:54:21Z |
| 43 |
modelfusion |
1305 |
91 |
TypeScript |
33 |
The TypeScript library for building AI applications. |
2024-07-19T15:17:19Z |
| 44 |
gp.nvim |
1293 |
124 |
Lua |
49 |
Gp.nvim (GPT prompt) Neovim AI plugin: ChatGPT sessions & Instructable text/code operations & Speech to text [OpenAI, Ollama, Anthropic, ..] |
2025-08-11T09:04:31Z |
| 45 |
search2ai |
1285 |
192 |
JavaScript |
19 |
Help your LLMs online |
2025-02-19T16:26:01Z |
| 46 |
airunner |
1270 |
98 |
Python |
15 |
Offline inference engine for art, real-time voice conversations, LLM powered chatbots and automated workflows |
2025-12-11T20:00:41Z |
| 47 |
generative-ai-use-cases |
1240 |
371 |
TypeScript |
68 |
Application implementation with business use cases for safely utilizing generative AI in business operations |
2025-12-12T08:40:09Z |
| 48 |
RisuAI |
1221 |
238 |
TypeScript |
87 |
Make your own story. User-friendly software for LLM roleplaying |
2025-12-09T05:43:13Z |
| 49 |
BaseAI |
1180 |
105 |
TypeScript |
4 |
BaseAI — The Web AI Framework. The easiest way to build serverless autonomous AI agents with memory. Start building local-first, agentic pipes, tools, and memory. Deploy serverless with one command. |
2025-12-12T17:19:46Z |
| 50 |
poe-api-wrapper |
1114 |
150 |
Python |
27 |
👾 A Python API wrapper for Poe.com. With this, you will have free access to GPT-4, Claude, Llama, Gemini, Mistral and more! 🚀 |
2025-08-31T05:29:09Z |
| 51 |
graphrag-local-ollama |
1085 |
165 |
Python |
50 |
Local models support for Microsoft’s graphrag using ollama (llama3, mistral, gemma2 phi3)- LLM & Embedding extraction |
2024-09-30T02:43:30Z |
| 52 |
chatd |
1076 |
79 |
JavaScript |
26 |
Chat with your documents using local AI |
2024-07-06T01:21:36Z |
| 53 |
web-llm-chat |
905 |
172 |
TypeScript |
12 |
Chat with AI large language models running natively in your browser. Enjoy private, server-free, seamless AI conversations. |
2025-09-03T16:52:44Z |
| 54 |
Hexabot |
900 |
194 |
TypeScript |
140 |
Hexabot is an open-source AI chatbot / agent builder. It allows you to create and manage multi-channel and multilingual chatbots / agents with ease. |
2025-12-12T08:49:05Z |
| 55 |
mistral-common |
827 |
116 |
Python |
2 |
Official inference library for pre-processing of Mistral models |
2025-12-12T17:26:27Z |
| 56 |
docs |
826 |
6 |
TypeScript |
7 |
Use 150k+ serverless AI models through a unified API. Deploy, stream, and compare in seconds — fast, affordable, production-ready. ✨ |
2025-11-22T00:04:16Z |
| 57 |
MixtralKit |
773 |
76 |
Python |
12 |
A toolkit for inference and evaluation of ‘mixtral-8x7b-32kseqlen’ from Mistral AI |
2023-12-15T19:10:55Z |
| 58 |
BambooAI |
752 |
82 |
Python |
14 |
A Python library powered by Language Models (LLMs) for conversational data discovery and analysis. |
2025-12-04T02:55:06Z |
| 59 |
ai-commits-intellij-plugin |
738 |
54 |
Kotlin |
23 |
AI Commits for IntelliJ based IDEs/Android Studio. |
2025-12-12T22:50:35Z |
| 60 |
llmcord |
733 |
167 |
Python |
3 |
Make Discord your LLM frontend - Supports any OpenAI compatible API (Ollama, xAI, Gemini, OpenRouter and more) |
2025-12-06T23:08:49Z |
| 61 |
fine-tune-mistral |
721 |
64 |
Python |
3 |
Fine-tune mistral-7B on 3090s, a100s, h100s |
2023-10-11T17:25:59Z |
| 62 |
llamafarm |
697 |
31 |
Python |
51 |
Deploy any AI model, agent, database, RAG, and pipeline locally or remotely in minutes |
2025-12-12T22:36:01Z |
| 63 |
ComfyUI-IF_AI_tools |
687 |
53 |
Python |
0 |
ComfyUI-IF_AI_tools is a set of custom nodes for ComfyUI that allows you to generate prompts using a local Large Language Model (LLM) via Ollama. This tool enables you to enhance your image generation workflow by leveraging the power of language models. |
2025-09-15T09:05:20Z |
| 64 |
client-python |
679 |
156 |
Python |
26 |
Python client library for Mistral AI platform |
2025-12-02T13:40:08Z |
| 65 |
llm-finetuning |
640 |
103 |
Python |
1 |
Guide for fine-tuning Llama/Mistral/CodeLlama models and more |
2025-10-15T13:53:04Z |
| 66 |
Owl |
624 |
59 |
Python |
6 |
A personal wearable AI that runs locally |
2024-03-17T06:37:26Z |
| 67 |
rag-chatbot |
603 |
102 |
Python |
8 |
Chat with multiple PDFs locally |
2025-10-23T02:41:40Z |
| 68 |
DevoxxGenieIDEAPlugin |
594 |
76 |
Java |
67 |
DevoxxGenie is a plugin for IntelliJ IDEA that uses local LLM’s (Ollama, LMStudio, GPT4All, Jan and Llama.cpp) and Cloud based LLMs to help review, test, explain your project code. |
2025-12-10T07:23:52Z |
| 69 |
embedJs |
592 |
72 |
TypeScript |
18 |
A NodeJS RAG framework to easily work with LLMs and embeddings |
2025-11-17T23:50:49Z |
| 70 |
helix |
590 |
64 |
Go |
85 |
♾️ Helix is a private GenAI stack for building AI agents with declarative pipelines, knowledge (RAG), API bindings, and first-class testing. |
2025-12-12T21:21:38Z |
| 71 |
mistral |
576 |
51 |
Python |
18 |
Mistral: A strong, northwesterly wind: Framework for transparent and accessible large-scale language model training, built with Hugging Face 🤗 Transformers. |
2023-11-10T02:55:18Z |
| 72 |
deepwiki-rs |
559 |
71 |
Rust |
4 |
AI-Powered open-source CodeWiki (like devin’s Deepwiki) generator built with Rust – Transform your codebase into professional architecture documentation in minutes |
2025-12-13T01:29:40Z |
| 73 |
yalm |
539 |
49 |
C++ |
3 |
Yet Another Language Model: LLM inference in C++/CUDA, no libraries except for I/O |
2025-09-13T09:22:40Z |
| 74 |
ollama-voice-mac |
514 |
64 |
Python |
9 |
Mac compatible Ollama Voice |
2025-08-21T15:02:52Z |
| 75 |
LESS |
509 |
44 |
Jupyter Notebook |
17 |
[ICML 2024] LESS: Selecting Influential Data for Targeted Instruction Tuning |
2024-10-20T03:11:58Z |
| 76 |
obsidian-bmo-chatbot |
506 |
60 |
TypeScript |
47 |
Generate and brainstorm ideas while creating your notes using Large Language Models (LLMs) from Ollama, LM Studio, Anthropic, Google Gemini, Mistral AI, OpenAI, and more for Obsidian. |
2024-09-12T04:07:29Z |
| 77 |
aikit |
500 |
53 |
Go |
33 |
🏗️ Fine-tune, build, and deploy open-source LLMs easily! |
2025-12-08T02:32:03Z |
| 78 |
kolosal-cli |
470 |
12 |
TypeScript |
10 |
Super lightweight Ollama + Qwen Code alternative to run Llama 3.3, DeepSeek-R1, Phi-4, Gemma 3, Mistral Small 3.1 and other large language models. |
2025-11-08T05:41:11Z |
| 79 |
mlx-llm |
459 |
28 |
Python |
0 |
Large Language Models (LLMs) applications and tools running on Apple Silicon in real-time with Apple MLX. |
2025-01-29T07:13:07Z |
| 80 |
WorkflowAI |
456 |
48 |
Python |
0 |
WorkflowAI is an open-source platform where product and engineering teams
collaborate to build and iterate on AI features. |
2025-11-28T08:35:23Z |
| 81 |
aicommit2 |
454 |
38 |
TypeScript |
5 |
A Reactive CLI that generates commit messages for Git and Jujutsu with Ollama, ChatGPT, Gemini, Claude, Mistral and other AI |
2025-11-17T02:05:24Z |
| 82 |
END-TO-END-GENERATIVE-AI-PROJECTS |
440 |
124 |
None |
0 |
End to End Generative AI Industry Projects on LLM Models with Deployment_Awesome LLM Projects |
2025-01-24T07:20:37Z |
| 83 |
bolna |
430 |
114 |
Python |
28 |
End-to-end platform for building voice first multimodal agents |
2024-10-28T05:40:38Z |
| 84 |
Kolosal |
422 |
28 |
C++ |
15 |
Kolosal AI is an OpenSource and Lightweight alternative to LM Studio to run LLMs 100% offline on your device. |
2025-05-22T06:29:28Z |
| 85 |
xllm |
408 |
21 |
Python |
6 |
🦖 X—LLM: Cutting Edge & Easy LLM Finetuning |
2024-01-17T16:43:39Z |
| 86 |
GPTPortal |
397 |
70 |
JavaScript |
2 |
A feature-rich portal to chat with GPT-4, Claude, Gemini, Mistral, & OpenAI Assistant APIs via a lightweight Node.js web app; supports customizable multimodality for voice, images, & files. |
2025-11-10T21:35:16Z |
| 87 |
KVQuant |
395 |
38 |
Python |
16 |
[NeurIPS 2024] KVQuant: Towards 10 Million Context Length LLM Inference with KV Cache Quantization |
2024-08-13T11:19:28Z |
| 88 |
fltr |
386 |
8 |
Rust |
1 |
Like grep but for natural language questions. Based on Mistral 7B or Mixtral 8x7B. |
2024-03-13T11:39:01Z |
| 89 |
NeuralFlow |
381 |
16 |
Python |
4 |
Visualize the intermediate output of Mistral 7B |
2025-01-22T11:25:17Z |
| 90 |
edgen |
367 |
20 |
Rust |
23 |
⚡ Edgen: Local, private GenAI server alternative to OpenAI. No GPU required. Run AI models locally: LLMs (Llama2, Mistral, Mixtral…), Speech-to-text (whisper) and many others. |
2024-05-23T14:21:38Z |
| 91 |
simple-openai |
359 |
51 |
Java |
14 |
A Java library to use the OpenAI Api in the simplest possible way. |
2025-09-17T21:45:15Z |
| 92 |
voice-chat-ai |
357 |
88 |
Python |
0 |
🎙️ Speak with AI - Run locally using Ollama, OpenAI, Anthropic or xAI - Speech uses SparkTTS, OpenAI, ElevenLabs or Kokoro |
2025-12-09T22:07:43Z |
| 93 |
OllamaKit |
319 |
40 |
Swift |
6 |
Ollama client for Swift |
2025-03-09T22:20:34Z |
| 94 |
LLaMa2lang |
315 |
35 |
Python |
0 |
Convenience scripts to finetune (chat-)LLaMa3 and other models for any language |
2024-06-17T14:00:13Z |
| 95 |
ai-playground |
315 |
79 |
Python |
0 |
Code from tutorials presented on the “Code AI with Rok” YouTube channel |
2025-11-27T18:58:50Z |
| 96 |
Heat |
305 |
17 |
Swift |
5 |
An LLM agnostic desktop and mobile client. |
2025-09-13T03:56:57Z |
| 97 |
mistral |
299 |
127 |
Python |
0 |
Workflow Service for OpenStack. Mirror of code maintained at opendev.org. |
2025-11-07T07:14:21Z |
| 98 |
nanodl |
297 |
12 |
Python |
2 |
A Jax-based library for building transformers, includes implementations of GPT, Gemma, LlaMa, Mixtral, Whisper, SWin, ViT and more. |
2024-08-28T21:24:22Z |
| 99 |
pdf-ocr-obsidian |
280 |
37 |
Python |
1 |
Convert your PDFs into Markdown files easily with Mistral OCR Software |
2025-06-05T15:28:06Z |
| 100 |
picollm |
273 |
15 |
Python |
0 |
On-device LLM Inference Powered by X-Bit Quantization |
2025-12-13T00:49:31Z |